机器人相关学术速递[10.22]

cs.RO机器人相关，共计35篇

【1】 Motion Planning for Connected Automated Vehicles at Occluded Intersections With Infrastructure Sensors 标题：基于基础设施传感器的闭塞交叉口互联自动车辆运动规划 链接：https://arxiv.org/abs/2110.11246

作者：Johannes Müller,Jan Strohbeck,Martin Herrmann,Michael Buchholz 机构：SUBMITTED TO REVIEW AND POSSIBLE PUBLICATION. COPYRIGHT WILL BE TRANSFERRED WITHOUT NOTICE. Personal, use of this material is permitted. Permission must be obtained for all other uses, in any current or future media, including reprint- 备注：12 pages, 8 figures 摘要：城市交叉口的运动规划是城市自动驾驶道路上的一个重大挑战，它可以解释交通状况、处理遮挡、处理测量和预测不确定性。在这项工作中，我们使用基于采样的优化方法来解决这一挑战。为此，我们制定了一个优化控制问题，以优化低风险和高乘客舒适度。使用风险模型，根据感知信息和相应的不确定性计算风险。风险模型结合了基于集合的方法和概率方法。因此，该方法提供了概率意义上的安全保证，而对于消失风险，则继承了基于集合的方法的形式安全保证。通过探索所有可用的行为选项，我们的方法一步解决了决策和纵向轨迹规划问题。可用的行为选项由情境上下文的正式表示提供，这也用于减少计算工作量。使用安装在基础设施上的传感器的外部感知来解决遮挡问题。然而，这些信息并没有融合外部和自我感知，而是并行使用。通过实际实验验证了运动规划方案的有效性。 摘要：Motion planning at urban intersections that accounts for the situation context, handles occlusions, and deals with measurement and prediction uncertainty is a major challenge on the way to urban automated driving. In this work, we address this challenge with a sampling-based optimization approach. For this, we formulate an optimal control problem that optimizes for low risk and high passenger comfort. The risk is calculated on the basis of the perception information and the respective uncertainty using a risk model. The risk model combines set-based methods and probabilistic approaches. Thus, the approach provides safety guarantees in a probabilistic sense, while for a vanishing risk, the formal safety guarantees of the set-based methods are inherited. By exploring all available behavior options, our approach solves decision making and longitudinal trajectory planning in one step. The available behavior options are provided by a formal representation of the situation context, which is also used to reduce calculation efforts. Occlusions are resolved using the external perception of infrastructure-mounted sensors. Yet, instead of merging external and ego perception with track-to-track fusion, the information is used in parallel. The motion planning scheme is validated through real-world experiments.

【2】 Heritability in Morphological Robot Evolution 标题：形态机器人进化中的遗传力 链接：https://arxiv.org/abs/2110.11187

作者：Matteo De Carlo,Eliseo Ferrante,Daan Zeeuwe,Jacintha Ellers,Gerben Meynen,A. E. Eiben 机构：Vrije Universiteit Amsterdam, Amsterdam, Netherlands, Technology Innovation Institute, Abu Dhabi, United Arab Emirates, A.E.Eiben 摘要：在进化机器人领域，选择正确的编码是非常复杂的，特别是当机器人同时进化行为和形态时。为了提高我们对从编码到功能机器人的映射过程的理解，我们引入了遗传力的生物学概念，它捕获了由基因型变异引起的表型变异量。在我们的分析中，我们测量了由两种不同编码（直接编码和间接编码）进化而来的第一代机器人的遗传力。此外，我们还研究了遗传力和表型多样性在整个进化过程中的相互作用。特别是，我们研究了直接和间接基因型如何在整个进化过程中表现出探索或开发的偏好。我们观察了如何通过检查遗传力和表型多样性的模式更容易理解勘探或开发的权衡。总之，我们展示了遗传力如何成为更好地理解基因型和表型之间关系的有用工具，特别是在设计复杂的系统时，在复杂的个体和环境可以相互适应和影响时，遗传力是非常有用的。 摘要：In the field of evolutionary robotics, choosing the correct encoding is very complicated, especially when robots evolve both behaviours and morphologies at the same time. With the objective of improving our understanding of the mapping process from encodings to functional robots, we introduce the biological notion of heritability, which captures the amount of phenotypic variation caused by genotypic variation. In our analysis we measure the heritability on the first generation of robots evolved from two different encodings, a direct encoding and an indirect encoding. In addition we investigate the interplay between heritability and phenotypic diversity through the course of an entire evolutionary process. In particular, we investigate how direct and indirect genotypes can exhibit preferences for exploration or exploitation throughout the course of evolution. We observe how an exploration or exploitation tradeoff can be more easily understood by examining patterns in heritability and phenotypic diversity. In conclusion, we show how heritability can be a useful tool to better understand the relationship between genotypes and phenotypes, especially helpful when designing more complicated systems where complex individuals and environments can adapt and influence each other.

【3】 Hierarchical Multi-robot Strategies Synthesis and Optimization under Individual and Collaborative Temporal Logic Specifications 标题：个体协同时态逻辑规范下的层次化多机器人策略综合与优化 链接：https://arxiv.org/abs/2110.11162

作者：Ruofei Bai,Ronghao Zheng,Yang Xu,Meiqin Liu,Senlin Zhang 机构： Zhejiang University, China 2State Key Laboratory of Industrial Control Technology, China 3School of Electronics and Information Engineering 备注：14 pages, 6 figures. arXiv admin note: text overlap with arXiv:2108.11597 摘要：本文提出了一个层次化的框架来解决多机器人时间任务规划问题。我们假设每个机器人都有其各自的任务规范，并且机器人必须共同满足一个全局协作任务规范，这两个规范都用线性时序逻辑描述。具体而言，中央服务器首先从对应于协作任务规范的自动机中提取并分解协作任务序列，并将序列中的子任务分配给机器人。然后，机器人可以基于本地构建的产品自动机，结合分配的协作任务和各自的任务规格，综合其初始执行策略。此外，我们还提出了一种分布式执行策略调整机制，通过减少潜在同步约束导致的协作等待时间，迭代地提高时间效率。我们在假设条件下证明了该框架的完备性，并分析了其时间复杂性和最优性。大量仿真结果验证了该方法的可扩展性和优化效率。 摘要：This paper presents a hierarchical framework to solve the multi-robot temporal task planning problem. We assume that each robot has its individual task specification and the robots have to jointly satisfy a global collaborative task specification, both described in linear temporal logic. Specifically, a central server firstly extracts and decomposes a collaborative task sequence from the automaton corresponding to the collaborative task specification, and allocates the subtasks in the sequence to robots. The robots can then synthesize their initial execution strategies based on locally constructed product automatons, combining the assigned collaborative tasks and their individual task specifications. Furthermore, we propose a distributed execution strategy adjusting mechanism to iteratively improve the time efficiency, by reducing wait time in collaborations caused by potential synchronization constraints. We prove the completeness of the proposed framework under assumptions, and analyze its time complexity and optimality. Extensive simulation results verify the scalability and optimization efficiency of the proposed method.

【4】 Control of Humanoid in Multiple Fixed and Moving Unilateral Contacts 标题：多个固定和移动单侧接触中的仿人机器人控制 链接：https://arxiv.org/abs/2110.11137

作者：Julien Roux,Saeid Samadi,Eisoku Kuroiwa,Takahide Yoshiike,Abderrahmane Kheddar 机构： which allows 1CNRS-University of Montpellier, fr 2Honda Research Institute 备注：None 摘要：在多个非共面单侧接触环境中，当一部分此类接触也在运动任务中诱导时，强制多肢机器人保持平衡是一项挑战。本文的第一个贡献是提高了最先进的基于几何质心包容的平衡方法的计算性能，该方法将在线集成为任务空间全身控制框架的一部分。因此，我们的第二个贡献在于，在不预先计算目标质心的情况下，将此类平衡区域与相关接触力分布进行整合。最后一个特性对于让后者自由地更好地遵守经典两级方法中未捕获的其他现有任务至关重要。我们通过使用HRP-4仿人机器人的实验来评估我们提出的方法的性能。 摘要：Enforcing balance of multi-limbed robots in multiple non-coplanar unilateral contact settings is challenging when a subset of such contacts are also induced in motion tasks. The first contribution of this paper is in enhancing the computational performance of state-of-the-art geometric center-of-mass inclusion-based balance method to be integrated online as part of a task-space whole-body control framework. As a consequence, our second contribution lies in integrating such a balance region with relevant contact force distribution without pre-computing a target center-of-mass. This last feature is essential to leave the latter with freedom to better comply with other existing tasks that are not captured in classical twolevel approaches. We assess the performance of our proposed method through experiments using the HRP-4 humanoid robot.

【5】 Enabling a Social Robot to Process Social Cues to Detect when to Help a User 标题：使社交机器人能够处理社交提示以检测何时帮助用户 链接：https://arxiv.org/abs/2110.11075

作者：Jason R. Wilson,Phyo Thuta Aung,Isabelle Boucher 机构：Franklin & Marshall College, Lancaster, Pennsylvania 备注：Presented at AI-HRI symposium as part of AAAI-FSS 2021 (arXiv:2109.10836) 摘要：对于社交辅助机器人来说，能够识别用户何时需要帮助是很重要的。此类机器人需要能够实时识别人类需求，以便及时提供帮助。我们提出了一种使用社会线索来确定机器人何时应该提供帮助的架构。基于眼睛注视和语言模式的多模式融合方法，我们的体系结构基于机器人辅助乐高构建任务中收集的数据进行训练和评估。通过关注社会线索，我们的体系结构对给定任务的细节的依赖性最小，使其能够应用于许多不同的环境。让社交机器人能够通过社交线索识别用户的需求，有助于它适应用户的行为和偏好，从而改善用户体验。 摘要：It is important for socially assistive robots to be able to recognize when a user needs and wants help. Such robots need to be able to recognize human needs in a real-time manner so that they can provide timely assistance. We propose an architecture that uses social cues to determine when a robot should provide assistance. Based on a multimodal fusion approach upon eye gaze and language modalities, our architecture is trained and evaluated on data collected in a robot-assisted Lego building task. By focusing on social cues, our architecture has minimal dependencies on the specifics of a given task, enabling it to be applied in many different contexts. Enabling a social robot to recognize a user's needs through social cues can help it to adapt to user behaviors and preferences, which in turn will lead to improved user experiences.

【6】 Robust Edge-Direct Visual Odometry based on CNN edge detection and Shi-Tomasi corner optimization 标题：基于CNN边缘检测和SHI-TOMASI角点优化的鲁棒边缘直接视觉里程计 链接：https://arxiv.org/abs/2110.11064

作者：Kengdong Lu,Jintao Cheng,Yubin Zhou,Juncan Deng,Rui Fan,Kaiqing Luo 摘要：本文提出了一种基于CNN边缘检测和Shi-Tomasi角点优化的鲁棒边缘直接视觉里程计（VO）。该方法从图像中提取四层金字塔，以减少帧间运动误差。该方案利用CNN边缘检测和Shi-Tomasi角点优化从图像中提取信息。然后，使用Levenberg-Marquardt（LM）算法执行姿势估计并更新关键帧。我们的方法与密集直接法、Canny边缘检测的改进直接法以及基于RGB-D TUM基准的ORB-SLAM2系统进行了比较。实验结果表明，该方法具有较好的鲁棒性和准确性。 摘要：In this paper, we propose a robust edge-direct visual odometry (VO) based on CNN edge detection and Shi-Tomasi corner optimization. Four layers of pyramids were extracted from the image in the proposed method to reduce the motion error between frames. This solution used CNN edge detection and Shi-Tomasi corner optimization to extract information from the image. Then, the pose estimation is performed using the Levenberg-Marquardt (LM) algorithm and updating the keyframes. Our method was compared with the dense direct method, the improved direct method of Canny edge detection, and ORB-SLAM2 system on the RGB-D TUM benchmark. The experimental results indicate that our method achieves better robustness and accuracy.

【7】 Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation 标题：视场之外的转移：基于无监督领域自适应的密集全景语义分割 链接：https://arxiv.org/abs/2110.11062

作者：Jiaming Zhang,Chaoxiang Ma,Kailun Yang,Alina Roitberg,Kunyu Peng,Rainer Stiefelhagen 机构：Segmentation, Network, Domain, Training, Adapting, Before Adaptation, After Adaptation 备注：Accepted to IEEE Transactions on Intelligent Transportation Systems (IEEE T-ITS). Dataset and code will be made publicly available at this https URL arXiv admin note: substantial text overlap with arXiv:2108.06383 摘要：自动驾驶车辆显然受益于360度传感器的扩展视野（FoV），但现代语义分割方法严重依赖于注释训练数据，这在全景图像中很少可用。我们从领域自适应的角度来看待这个问题，并将全景语义分割引入到一个场景中，其中标记的训练数据来自传统针孔相机图像的不同分布。为了实现这一点，我们将全景语义分割的无监督域适配任务形式化，并收集DensePASS——一种新的用于跨域条件下全景分割的密集注释数据集，专门用于研究针孔到全景域的转换，并附带从城市景观中获得的针孔摄像机训练示例。DensePASS涵盖标记和未标记的360度图像，标记数据包括19个类别，这些类别明确符合源（即针孔）域中可用的类别。由于数据驱动模型特别容易受到数据分布变化的影响，我们引入了P2PDA——一种针孔到全景语义分割的通用框架，该框架通过不同类型的注意力增强域适应模块解决了域分化的挑战，实现了输出、特征和，和特征置信空间。P2PDA将不确定性感知适应与通过不同预测的注意头动态调节的置信值交织在一起。我们的框架有助于在学习领域对应时进行上下文交换，并显著提高了以准确性和效率为重点的模型的适应性能。综合实验证明，我们的框架明显优于无监督的领域自适应和专门的全景分割方法。 摘要：Autonomous vehicles clearly benefit from the expanded Field of View (FoV) of 360-degree sensors, but modern semantic segmentation approaches rely heavily on annotated training data which is rarely available for panoramic images. We look at this problem from the perspective of domain adaptation and bring panoramic semantic segmentation to a setting, where labelled training data originates from a different distribution of conventional pinhole camera images. To achieve this, we formalize the task of unsupervised domain adaptation for panoramic semantic segmentation and collect DensePASS - a novel densely annotated dataset for panoramic segmentation under cross-domain conditions, specifically built to study the Pinhole-to-Panoramic domain shift and accompanied with pinhole camera training examples obtained from Cityscapes. DensePASS covers both, labelled- and unlabelled 360-degree images, with the labelled data comprising 19 classes which explicitly fit the categories available in the source (i.e. pinhole) domain. Since data-driven models are especially susceptible to changes in data distribution, we introduce P2PDA - a generic framework for Pinhole-to-Panoramic semantic segmentation which addresses the challenge of domain divergence with different variants of attention-augmented domain adaptation modules, enabling the transfer in output-, feature-, and feature confidence spaces. P2PDA intertwines uncertainty-aware adaptation using confidence values regulated on-the-fly through attention heads with discrepant predictions. Our framework facilitates context exchange when learning domain correspondences and dramatically improves the adaptation performance of accuracy- and efficiency-focused models. Comprehensive experiments verify that our framework clearly surpasses unsupervised domain adaptation- and specialized panoramic segmentation approaches.

【8】 WareVR: Virtual Reality Interface for Supervision of Autonomous Robotic System Aimed at Warehouse Stocktaking 标题：WareVR：面向仓库清点的自主机器人系统监控虚拟现实接口 链接：https://arxiv.org/abs/2110.11052

作者：Ivan Kalinov,Daria Trinitatova,Dzmitry Tsetserukou 机构： most of the stocktaking of such warehousesAll authors are with Skolkovo Institute of Science and Technol-ogy 备注：Accepted to 2021 IEEE International Conference on Systems, Man, and Cybernetics, 7 pages, 8 figures 摘要：WareVR是一种基于虚拟现实（VR）应用程序的新型人机界面，用于与异构机器人系统交互以实现自动化库存管理。我们已经创建了一个界面，从仓库中的一个隐蔽工作站远程监控一个自主机器人，这可能会在当前流行的新冠病毒-19期间受益，因为盘点是仓库中一个必要的常规过程，涉及到一群人。提议的接口允许没有机器人经验的常规仓库工人控制由无人地面车辆（UGV）和无人飞行器（UAV）组成的异构机器人系统。WareVR在仓库的数字孪生模型中提供机器人系统的可视化，并通过机载无人机摄像头提供来自真实环境的实时视频流。使用WareVR界面，操作员可以进行不同级别的盘点，远程监控库存过程，并远程操作无人机进行更详细的检查。此外，开发的界面包括无人机的远程控制，以便与自动机器人进行直观直观的人机交互，以进行盘点。通过“视觉检查”场景中的用户研究，评估了基于虚拟现实的界面的有效性。 摘要：WareVR is a novel human-robot interface based on a virtual reality (VR) application to interact with a heterogeneous robotic system for automated inventory management. We have created an interface to supervise an autonomous robot remotely from a secluded workstation in a warehouse that could benefit during the current pandemic COVID-19 since the stocktaking is a necessary and regular process in warehouses, which involves a group of people. The proposed interface allows regular warehouse workers without experience in robotics to control the heterogeneous robotic system consisting of an unmanned ground vehicle (UGV) and unmanned aerial vehicle (UAV). WareVR provides visualization of the robotic system in a digital twin of the warehouse, which is accompanied by a real-time video stream from the real environment through an on-board UAV camera. Using the WareVR interface, the operator can conduct different levels of stocktaking, monitor the inventory process remotely, and teleoperate the drone for a more detailed inspection. Besides, the developed interface includes remote control of the UAV for intuitive and straightforward human interaction with the autonomous robot for stocktaking. The effectiveness of the VR-based interface was evaluated through the user study in a "visual inspection" scenario.

【9】 Mixer-based lidar lane detection network and dataset for urban roads 标题：基于混频器的城市道路激光雷达车道检测网络和数据集 链接：https://arxiv.org/abs/2110.11048

作者：Donghee Paek,Seung-Hyun Kong,Kevin Tirta Wijaya 备注：15 pages, 12 figures, 8 tables 摘要：在各种路况下，准确的车道检测是自动驾驶的关键功能。通常，当从前置摄像头图像中检测到的车道线投影到用于运动规划的鸟瞰视图（BEV）中时，生成的车道线通常会失真。而基于卷积神经网络（CNN）的特征抽取器在增加感受野以检测车道线等全局特征时往往会失去分辨率。然而，激光雷达点云在BEV投影中几乎没有图像失真。由于车道线很薄，并且在整个BEV图像上延伸，但只占一小部分，因此车道线应作为一个高分辨率的全局特征进行检测。在本文中，我们提出了车道混合网络（LMN），该网络分别使用BEV编码器、基于混合的全局特征提取器和检测头从激光雷达点云中提取局部特征、识别全局特征和检测车道线。此外，我们还为激光雷达提供了世界上第一个大型城市车道数据集K-lane，该数据集在各种城市道路条件下最多有6条车道。我们证明，拟议的LMN达到了最先进的性能，F1分数为91.67%，采用K车道。github提供了K-Lane、LMN训练代码、预训练模型和总体数据集开发平台。 摘要：Accurate lane detection under various road conditions is a critical function for autonomous driving. Generally, when detected lane lines from a front camera image are projected into a birds-eye view (BEV) for motion planning, the resulting lane lines are often distorted. And convolutional neural network (CNN)-based feature extractors often lose resolution when increasing the receptive field to detect global features such as lane lines. However, Lidar point cloud has little image distortion in the BEV-projection. Since lane lines are thin and stretch over entire BEV image while occupying only a small portion, lane lines should be detected as a global feature with high resolution. In this paper, we propose Lane Mixer Network (LMN) that extracts local features from Lidar point cloud, recognizes global features, and detects lane lines using a BEV encoder, a Mixer-based global feature extractor, and a detection head, respectively. In addition, we provide a world-first large urban lane dataset for Lidar, K-Lane, which has maximum 6 lanes under various urban road conditions. We demonstrate that the proposed LMN achieves the state-of-the-art performance, an F1 score of 91.67%, with K-Lane. The K-Lane, LMN training code, pre-trained models, and total dataset development platform are available at github.

【10】 InterpolationSLAM: A Novel Robust Visual SLAM System in Rotational Motion 标题：插值SLAM：一种新的旋转运动鲁棒视觉SLAM系统 链接：https://arxiv.org/abs/2110.11040

作者：Zhenkun Zhu,Jikai Wang 机构： Classic method uses RANdomThe authors are with the with the Department of Automation 备注：arXiv admin note: substantial text overlap with arXiv:2110.02593 摘要：近年来，视觉SLAM在不同的场景中取得了很大的进步和发展，但仍有许多问题需要解决。SLAM系统不仅受外部场景的限制，还受其运动模式的影响，如运动速度、旋转运动等。作为最优秀的帧插值网络的代表，Sepconv slomo和EDSC可以预测前一帧和当前帧之间的高质量中间帧。直观地说，帧插值技术可以丰富图像序列的信息，图像序列的数量受摄像机帧速率的限制，从而降低SLAM系统的故障率。在本文中，我们提出了一个插值lam框架。对于单目和RGB-D配置，InterpolationSLAM在旋转运动中具有鲁棒性。通过检测旋转并在旋转位置执行插值处理，可以更准确地估计系统的姿态，从而提高SLAM系统在旋转运动中的精度和鲁棒性。 摘要：In recent years, visual SLAM has achieved great progress and development in different scenes, however, there are still many problems to be solved. The SLAM system is not only restricted by the external scenes but is also affected by its movement mode, such as movement speed, rotational motion, etc. As the representatives of the most excellent networks for frame interpolation, Sepconv-slomo and EDSC can predict high-quality intermediate frame between the previous frame and the current frame. Intuitively, frame interpolation technology can enrich the information of images sequences, the number of which is limited by the camera's frame rate, and thus decreasing the probability of SLAM system's failure rate. In this article, we propose an InterpolationSLAM framework. InterpolationSLAM is robust in rotational movement for Monocular and RGB-D configurations. By detecting the rotation and performing interpolation processing at the rotated position, pose of the system can be estimated more accurately, thereby improving the accuracy and robustness of the SLAM system in the rotational movement.

【11】 LOA: Logical Optimal Actions for Text-based Interaction Games 标题：LOA：基于文本的交互游戏的逻辑最优动作 链接：https://arxiv.org/abs/2110.10973

作者：Daiki Kimura,Subhajit Chaudhury,Masaki Ono,Michiaki Tatsubori,Don Joven Agravante,Asim Munawar,Akifumi Wachi,Ryosuke Kohita,Alexander Gray 机构：IBM Research 备注：ACL-IJCNLP 2021 (demo paper) 摘要：我们提出了逻辑最优动作（LOA），这是一种强化学习应用的动作决策架构，具有神经-符号框架，该框架是自然语言交互游戏中神经网络和符号知识获取方法的组合。LOA实验的演示包括一个基于web的交互式平台，用于基于文本的游戏和获取知识的可视化，以提高训练规则的可解释性。本演示还提供了一个与其他神经符号方法以及基于文本的相同游戏上的非符号最新代理模型的比较模块。我们的LOA还为强化学习环境提供了Python的开源实现，以促进研究神经符号代理的实验。代码：https://github.com/ibm/loa 摘要：We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games. The demonstration for LOA experiments consists of a web-based interactive platform for text-based games and visualization for acquired knowledge for improving interpretability for trained rules. This demonstration also provides a comparison module with other neuro-symbolic approaches as well as non-symbolic state-of-the-art agent models on the same text-based games. Our LOA also provides open-sourced implementation in Python for the reinforcement learning environment to facilitate an experiment for studying neuro-symbolic agents. Code: https://github.com/ibm/loa

【12】 Neuro-Symbolic Reinforcement Learning with First-Order Logic 标题：基于一阶逻辑的神经符号强化学习 链接：https://arxiv.org/abs/2110.10963

作者：Daiki Kimura,Masaki Ono,Subhajit Chaudhury,Ryosuke Kohita,Akifumi Wachi,Don Joven Agravante,Michiaki Tatsubori,Asim Munawar,Alexander Gray 机构：IBM Research 备注：EMNLP 2021 (main conference) 摘要：深度强化学习（RL）方法在收敛之前通常需要多次试验，并且没有提供训练策略的直接解释能力。为了实现RL策略的快速收敛性和可解释性，我们提出了一种新的文本游戏RL方法，该方法采用了一种称为逻辑神经网络的神经符号框架，可以在可微网络中学习符号规则和可解释规则。该方法首先从文本观察和外部词义网络（ConceptNet）中提取一阶逻辑事实，然后在网络中用可直接解释的逻辑运算符训练策略。我们的实验结果表明，在TextWorld基准测试中，使用该方法的RL训练收敛速度明显快于其他最先进的神经符号方法。 摘要：Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with directly interpretable logical operators. Our experimental results show RL training with the proposed method converges significantly faster than other state-of-the-art neuro-symbolic methods in a TextWorld benchmark.

【13】 Fuzzy-Depth Objects Grasping Based on FSG Algorithm and a Soft Robotic Hand 标题：基于FSG算法和软手的模糊深度目标抓取 链接：https://arxiv.org/abs/2110.10924

作者：Hanwen Cao,Junda Huang,Yichuan Li,Jianshu Zhou,Yunhui Liu 机构：The work was supported in part by Hong Kong RGC via the TRS, project T,-,,-R and , the Hong Kong Centre for, Logistics Robotics, CUHK T Stone Robotics Institute, and in part by, the CUHK Hong Kong-Shenzhen Innovation and Technology Research, Institute (Futian). 备注：accepted by IROS 2021 摘要：自主抓取是机器人与环境进行物理交互和执行多种任务的重要因素。然而，一种普遍适用、经济高效、可快速部署的自主抓取方法仍然受到具有模糊深度信息的目标物体的限制。例如，透明、镜面反射、平面和小对象，其深度难以准确感知。在这项工作中，我们提出了解决这些模糊的深度对象。该方法的框架包括两个主要部分：一个是软机械手，另一个是模糊深度软抓取（FSG）算法。软手可替换为大多数现有的符合人体要求的软手/夹持器。FSG算法利用RGB和深度图像预测抓取，而不尝试重建整个场景。设计了两个抓取原语以进一步提高鲁棒性。在看不见的模糊深度物体抓取实验中，该方法优于参考基线（84%的成功率）。 摘要：Autonomous grasping is an important factor for robots physically interacting with the environment and executing versatile tasks. However, a universally applicable, cost-effective, and rapidly deployable autonomous grasping approach is still limited by those target objects with fuzzy-depth information. Examples are transparent, specular, flat, and small objects whose depth is difficult to be accurately sensed. In this work, we present a solution to those fuzzy-depth objects. The framework of our approach includes two major components: one is a soft robotic hand and the other one is a Fuzzy-depth Soft Grasping (FSG) algorithm. The soft hand is replaceable for most existing soft hands/grippers with body compliance. FSG algorithm exploits both RGB and depth images to predict grasps while not trying to reconstruct the whole scene. Two grasping primitives are designed to further increase robustness. The proposed method outperforms reference baselines in unseen fuzzy-depth objects grasping experiments (84% success rate).

【14】 Efficient Robotic Manipulation Through Offline-to-Online Reinforcement Learning and Goal-Aware State Information 标题：基于离线到在线强化学习和目标感知状态信息的高效机器人操作 链接：https://arxiv.org/abs/2110.10905

作者：Jin Li,Xianyuan Zhan,Zixu Xiao,Guyue Zhou 机构： Guyue Zhou are with the Institute for AI Indus-try Research (AIR), Tsinghua University 摘要：具有高数据效率的端到端学习机器人操作是机器人技术的关键挑战之一。利用人类演示数据和无监督表征学习的最新方法已被证明是提高RL学习效率的一个有希望的方向。使用演示数据还允许使用离线数据和模仿学习或最近出现的离线强化学习算法“预热”RL策略。然而，现有的研究通常将离线策略学习和在线探索视为两个独立的过程，在离线到在线的过渡过程中，这两个过程往往伴随着严重的性能下降。此外，许多机器人操作任务都涉及到复杂的子任务结构，这在报酬稀疏的RL中是一个非常具有挑战性的问题。在这项工作中，我们提出了一个统一的离线到在线的RL框架，解决了转换性能下降的问题。此外，我们将目标感知状态信息引入到RL代理中，这可以大大降低任务的复杂性，加快策略学习。与先进的无监督表示学习模块相结合，我们的框架在多个机器人操作任务中实现了比最先进的方法更高的训练效率和性能。 摘要：End-to-end learning robotic manipulation with high data efficiency is one of the key challenges in robotics. The latest methods that utilize human demonstration data and unsupervised representation learning has proven to be a promising direction to improve RL learning efficiency. The use of demonstration data also allows "warming-up" the RL policies using offline data with imitation learning or the recently emerged offline reinforcement learning algorithms. However, existing works often treat offline policy learning and online exploration as two separate processes, which are often accompanied by severe performance drop during the offline-to-online transition. Furthermore, many robotic manipulation tasks involve complex sub-task structures, which are very challenging to be solved in RL with sparse reward. In this work, we propose a unified offline-to-online RL framework that resolves the transition performance drop issue. Additionally, we introduce goal-aware state information to the RL agent, which can greatly reduce task complexity and accelerate policy learning. Combined with an advanced unsupervised representation learning module, our framework achieves great training efficiency and performance compared with the state-of-the-art methods in multiple robotic manipulation tasks.

【15】 ReachBot: A Small Robot for Large Mobile Manipulation Tasks 标题：ReachBot：一种适用于大型移动操作任务的小型机器人 链接：https://arxiv.org/abs/2110.10829

作者：Stephanie Schneider,Andrew Bylard,Tony G. Chen,Preston Wang,Mark Cutkosky,Marco Pavone 机构：Dept. of Aero. & Astronautics, Stanford University, Lomita Mall, Stanford, CA , Dept. of Mech. Engineering, Escondido Mall 备注：12 pages, 13 figures 摘要：机器人因其多功能性和鲁棒性而广泛应用于太空环境。然而，恶劣的重力条件和具有挑战性的地形几何暴露了传统机器人设计的局限性，这些设计往往被迫牺牲一种机动性或操纵能力来实现另一种。在这些环境中，未来的攀岩作业需要小型、紧凑的机器人，能够进行多种移动和操作。我们提出了一种新的机器人概念，称为可达机器人，它通过结合两种现有技术来满足这一需求：伸缩臂和移动操纵。ReachBot利用可伸缩臂的伸缩性和抗拉强度，实现超大的可伸缩工作空间和扳手能力。通过其轻质、紧凑的结构，与传统的刚性连杆铰接臂设计相比，这些吊杆还降低了质量和复杂性。利用这些优势，ReachBot在低重力或需要攀爬的移动操纵任务中表现出色，特别是当锚定点稀疏时。在介绍了ReachBot概念之后，我们讨论了提高稳定性和鲁棒性的建模方法和策略。然后，受灵巧机械手抓取模型的启发，我们开发了一个二维分析模型，用于ReachBot的动力学。接下来，我们介绍了一种用于微重力下平面可达机器人的航路点跟踪控制器。仿真结果表明，该控制器对扰动和建模误差具有鲁棒性。最后，我们简要讨论了在这些最初有希望的结果的基础上，为实现ReachBot的全部潜力而采取的下一步措施。 摘要：Robots are widely deployed in space environments because of their versatility and robustness. However, adverse gravity conditions and challenging terrain geometry expose the limitations of traditional robot designs, which are often forced to sacrifice one of mobility or manipulation capabilities to attain the other. Prospective climbing operations in these environments reveals a need for small, compact robots capable of versatile mobility and manipulation. We propose a novel robotic concept called ReachBot that fills this need by combining two existing technologies: extendable booms and mobile manipulation. ReachBot leverages the reach and tensile strength of extendable booms to achieve an outsized reachable workspace and wrench capability. Through their lightweight, compactable structure, these booms also reduce mass and complexity compared to traditional rigid-link articulated-arm designs. Using these advantages, ReachBot excels in mobile manipulation missions in low gravity or that require climbing, particularly when anchor points are sparse. After introducing the ReachBot concept, we discuss modeling approaches and strategies for increasing stability and robustness. We then develop a 2D analytical model for ReachBot's dynamics inspired by grasp models for dexterous manipulators. Next, we introduce a waypoint-tracking controller for a planar ReachBot in microgravity. Our simulation results demonstrate the controller's robustness to disturbances and modeling error. Finally, we briefly discuss next steps that build on these initially promising results to realize the full potential of ReachBot.

【16】 Hierarchical Skills for Efficient Exploration 标题：有效探索的分层技能 链接：https://arxiv.org/abs/2110.10809

作者：Jonas Gehring,Gabriel Synnaeve,Andreas Krause,Nicolas Usunier 机构：Facebook AI Research, ETH Zürich 备注：To appear in 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 摘要：在强化学习中，预先训练的低水平技能有可能极大地促进探索。然而，在技能设计中，为了在通用性（细粒度控制）和专用性（更快的学习）之间取得适当的平衡，需要对下游任务有先验知识。在以前关于连续控制的工作中，由于移动为导航任务提供了一个合适的先验条件，因此没有明确说明方法对这种权衡的敏感性。在这项工作中，我们分析了低水平策略预训练的权衡，并为两足机器人提供了一套新的多样、稀疏的奖励任务基准。我们提出了一个分层的技能学习框架，以无监督的方式获取不同复杂性的技能，从而缓解了对先验知识的需求。对于下游任务的利用，我们提出了一种三层分层学习算法，可以根据相应任务的需要自动在一般技能和特定技能之间进行权衡。在我们的实验中，我们表明我们的方法有效地进行了这种权衡，并且在端到端分层强化学习和无监督技能发现方面取得了比当前最先进的方法更好的结果。代码和视频可在https://facebookresearch.github.io/hsd3 . 摘要：In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design. In previous work on continuous control, the sensitivity of methods to this trade-off has not been addressed explicitly, as locomotion provides a suitable prior for navigation tasks, which have been of foremost interest. In this work, we analyze this trade-off for low-level policy pre-training with a new benchmark suite of diverse, sparse-reward tasks for bipedal robots. We alleviate the need for prior knowledge by proposing a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner. For utilization on downstream tasks, we present a three-layered hierarchical learning algorithm to automatically trade off between general and specific skills as required by the respective task. In our experiments, we show that our approach performs this trade-off effectively and achieves better results than current state-of-the-art methods for end- to-end hierarchical reinforcement learning and unsupervised skill discovery. Code and videos are available at https://facebookresearch.github.io/hsd3 .

【17】 DVIO: Depth aided visual inertial odometry for RGBD sensors 标题：DVIO：RGBD传感器的深度辅助视觉惯性里程计 链接：https://arxiv.org/abs/2110.10805

作者：Abhishek Tyagi,Yangwen Liang,Shuangquan Wang,Dongwoon Bai 机构：SOC R&D, Samsung Semiconductor, Inc. 摘要：在过去几年中，我们观察到移动设备中RGBD传感器的使用量有所增加。这些传感器可以很好地估计摄像机帧的深度图，可用于许多增强现实应用。本文提出了一种新的视觉惯性里程计（VIO）系统，该系统使用来自RGBD传感器和惯性测量单元（IMU）传感器的测量值来估计移动设备的运动状态。由此产生的系统称为深度辅助VIO（DVIO）系统。在这个系统中，我们添加了深度测量作为非线性优化过程的一部分。具体来说，我们提出了使用一维（1D）特征参数化和三维（3D）特征参数化的深度测量方法。此外，我们建议利用深度测量来估计非同步IMU和RGBD传感器之间的时间偏移。最后，我们提出了一种新的基于块的边缘化方法，以加快边缘化过程并保持整个系统的实时性能。实验结果表明，所提出的DVIO系统在轨迹精度和处理时间方面优于其他最先进的VIO系统。 摘要：In past few years we have observed an increase in the usage of RGBD sensors in mobile devices. These sensors provide a good estimate of the depth map for the camera frame, which can be used in numerous augmented reality applications. This paper presents a new visual inertial odometry (VIO) system, which uses measurements from a RGBD sensor and an inertial measurement unit (IMU) sensor for estimating the motion state of the mobile device. The resulting system is called the depth-aided VIO (DVIO) system. In this system we add the depth measurement as part of the nonlinear optimization process. Specifically, we propose methods to use the depth measurement using one-dimensional (1D) feature parameterization as well as three-dimensional (3D) feature parameterization. In addition, we propose to utilize the depth measurement for estimating time offset between the unsynchronized IMU and the RGBD sensors. Last but not least, we propose a novel block-based marginalization approach to speed up the marginalization processes and maintain the real-time performance of the overall system. Experimental results validate that the proposed DVIO system outperforms the other state-of-the-art VIO systems in terms of trajectory accuracy as well as processing time.

【18】 Resilient Time-Varying Formation Tracking for Mobile Robot Networks under Deception Attacks on Positioning 标题：位置欺骗攻击下移动机器人网络的弹性时变队形跟踪 链接：https://arxiv.org/abs/2110.10678

作者：Yen-Chen Liu,Kai-Yuan Liu,Zhuoyuan Song 备注：12 pages, 13 figures 摘要：本文研究了在全球定位欺骗攻击下，移动机器人网络在时变编队跟踪中的弹性控制、分析、恢复和操作。提出了局部和全局跟踪控制算法，以确保移动机器人网络的冗余性，并保持所需的功能以获得更好的恢复能力。利用Lyapunov稳定性分析证明了编队跟踪误差的有界性和网络在各种攻击模式下的稳定性。设计了一个性能指标来比较在有无定位攻击的情况下所提出的编队跟踪算法的效率。随后，提出了一种基于扩展信息滤波器的无通信分散协作定位方法，该方法基于Kullback-Leibler散度识别定位攻击。提出了一种增益调整弹性操作，从战略上综合编队控制和协同定位，以准确、快速地从定位攻击中恢复系统。所提出的方法通过一组四转子进行了数值模拟和实验验证。 摘要：This paper investigates the resilient control, analysis, recovery, and operation of mobile robot networks in time-varying formation tracking under deception attacks on global positioning. Local and global tracking control algorithms are presented to ensure redundancy of the mobile robot network and to retain the desired functionality for better resilience. Lyapunov stability analysis is utilized to show the boundedness of the formation tracking error and the stability of the network under various attack modes. A performance index is designed to compare the efficiency of the proposed formation tracking algorithms in situations with or without positioning attacks. Subsequently, a communication-free decentralized cooperative localization approach based on extended information filters is presented for positioning estimate recovery where the identification of the positioning attacks is based on Kullback-Leibler divergence. A gain-tuning resilient operation is proposed to strategically synthesize the formation control and cooperative localization for accurate and rapid system recovery from positioning attacks. The proposed methods are tested using both numerical simulation and experimental validation with a team of quadrotors.

【19】 CobotAR: Interaction with Robots using Omnidirectionally Projected Image and DNN-based Gesture Recognition 标题：CobotAR：使用全方位投影图像和基于DNN的手势识别与机器人交互 链接：https://arxiv.org/abs/2110.10571

作者：Nazarova Elena,Sautenkov Oleg,Altamirano Cabrera Miguel,Tirado Jonathan,Serpiva Valerii,Rakhmatulin Viktor,Tsetserukou Dzmitry 机构： Skolkovo Institute of Scienceand Technology (Skoltech) 备注：Accepted paper in SMC conference 2021, IEEE copyright 摘要：在过去几年中，一些技术解决方案支持为增强现实（AR）多用户协作创建接口。然而，这些技术需要使用可穿戴设备。我们提出了CobotAR——一种通过基于深度神经网络（DNN）的手势识别实现人机交互（HRI）的新AR技术，该技术不需要用户额外的可穿戴设备。该系统使用户只需双手就能更直观地体验机器人应用程序。CobotAR系统假设AR空间显示由安装在6自由度机器人上的移动投影仪创建。提出的技术提出了一种与机器交互的新方法，通过机器人投影系统和基于DNN的算法实现安全、直观和沉浸式控制。在这项研究中，我们进行了多个参数评估的实验，使用户可以定义新方法的优点和缺点。CobotAR系统的心理需求比无线游戏机少两倍，比教学挂件少16%。 摘要：Several technological solutions supported the creation of interfaces for Augmented Reality (AR) multi-user collaboration in the last years. However, these technologies require the use of wearable devices. We present CobotAR - a new AR technology to achieve the Human-Robot Interaction (HRI) by gesture recognition based on Deep Neural Network (DNN) - without an extra wearable device for the user. The system allows users to have a more intuitive experience with robotic applications using just their hands. The CobotAR system assumes the AR spatial display created by a mobile projector mounted on a 6 DoF robot. The proposed technology suggests a novel way of interaction with machines to achieve safe, intuitive, and immersive control mediated by a robotic projection system and DNN-based algorithm. We conducted the experiment with several parameters assessment during this research, which allows the users to define the positives and negatives of the new approach. The mental demand of CobotAR system is twice less than Wireless Gamepad and by 16\% less than Teach Pendant.

【20】 Robust Monocular Localization in Sparse HD Maps Leveraging Multi-Task Uncertainty Estimation 标题：基于多任务不确定性估计的稀疏高清地图鲁棒单目定位 链接：https://arxiv.org/abs/2110.10563

作者：Kürsat Petek,Kshitij Sirohi,Daniel Büscher,Wolfram Burgard 机构： University of Freiburg 摘要：使用低成本传感器设置和稀疏高清地图在密集城市场景中进行稳健定位与当前自主驾驶的进展高度相关，但仍然是一个具有挑战性的研究课题。我们提出了一种新的基于滑动窗口姿态图的单目定位方法，该方法利用预测的不确定性来提高精度和鲁棒性，以应对具有挑战性的场景和每帧故障。为此，我们提出了一个有效的多任务不确定性感知模块，该模块包括语义分割和边界盒检测，以实现稀疏地图中车辆的定位，该地图仅包含车道边界和交通灯。此外，我们还设计了直接由估计的不确定性生成的可微成本图。这为以无关联和不确定性感知的方式最大限度地减少无定形映射元素的重投影损失提供了可能性。对Lyft 5数据集的广泛评估表明，尽管地图稀疏，但我们的方法能够在具有挑战性的城市场景中实现稳健而准确的6D定位 摘要：Robust localization in dense urban scenarios using a low-cost sensor setup and sparse HD maps is highly relevant for the current advances in autonomous driving, but remains a challenging topic in research. We present a novel monocular localization approach based on a sliding-window pose graph that leverages predicted uncertainties for increased precision and robustness against challenging scenarios and per frame failures. To this end, we propose an efficient multi-task uncertainty-aware perception module, which covers semantic segmentation, as well as bounding box detection, to enable the localization of vehicles in sparse maps, containing only lane borders and traffic lights. Further, we design differentiable cost maps that are directly generated from the estimated uncertainties. This opens up the possibility to minimize the reprojection loss of amorphous map elements in an association free and uncertainty-aware manner. Extensive evaluation on the Lyft 5 dataset shows that, despite the sparsity of the map, our approach enables robust and accurate 6D localization in challenging urban scenarios

【21】 Periodic DMP formulation for Quaternion Trajectories 标题：四元数轨道的周期DMP公式 链接：https://arxiv.org/abs/2110.10510

作者：Fares J. Abu-Dakka,Matteo Saveriano,Luka Peternel 备注：2021 20th International Conference on Advanced Robotics (ICAR) 摘要：模仿学习技术已被用作向机器人传授技能的一种方式。其中，动态运动原语（DMPs）作为一种学习和再现复杂离散和周期性技能的有效技术已被广泛应用。虽然DMP已正确制定，用于学习翻译和方向的点对点运动，但周期性DMP缺少学习方向的制定。为了解决这一差距，我们提出了一种新的DMP公式，可以对周期性定向轨迹进行编码。在这个公式中，我们发展了两种方法：基于黎曼度量的投影方法和基于单位四元数的周期DMP。这两种公式都使用单位四元数来表示方向。然而，第一种方法利用黎曼流形的性质在单位球面的切线空间中工作。第二种方法直接编码单位四元数轨迹，同时保证生成的四元数的酉范数。我们在仿真中验证了所提出方法的技术方面。然后，我们在一个真正的机器人上进行实验，以执行日常任务，包括周期性的方向变化（即，表面抛光/擦拭和通过摇动混合液体）。 摘要：Imitation learning techniques have been used as a way to transfer skills to robots. Among them, dynamic movement primitives (DMPs) have been widely exploited as an effective and an efficient technique to learn and reproduce complex discrete and periodic skills. While DMPs have been properly formulated for learning point-to-point movements for both translation and orientation, periodic ones are missing a formulation to learn the orientation. To address this gap, we propose a novel DMP formulation that enables encoding of periodic orientation trajectories. Within this formulation we develop two approaches: Riemannian metric-based projection approach and unit quaternion based periodic DMP. Both formulations exploit unit quaternions to represent the orientation. However, the first exploits the properties of Riemannian manifolds to work in the tangent space of the unit sphere. The second encodes directly the unit quaternion trajectory while guaranteeing the unitary norm of the generated quaternions. We validated the technical aspects of the proposed methods in simulation. Then we performed experiments on a real robot to execute daily tasks that involve periodic orientation changes (i.e., surface polishing/wiping and liquid mixing by shaking).

【22】 A Survey on Deep-Learning Approaches for Vehicle Trajectory Prediction in Autonomous Driving 标题：自动驾驶中车辆轨迹预测的深度学习方法综述 链接：https://arxiv.org/abs/2110.10436

作者：Jianbang Liu,Xinyu Mao,Yuqi Fang,Delong Zhu,Max Q. -H. Meng 机构：hk) 2Yuqi Fang is with the Department of Biomedical Engi-neering, The Chinese University of Hong Kong 备注：Accepted by ROBIO2021 摘要：随着机器学习的快速发展，自主驾驶已经成为一个热点问题，对智能感知和规划系统提出了更高的要求。自动驾驶汽车可以通过精确预测周围车辆的未来轨迹避免交通事故。在这项工作中，我们从表示、建模和学习的角度对现有的基于学习的轨迹预测方法进行了回顾和分类。此外，我们将目标驱动轨迹预测的实现公开于https://github.com/Henry1iu/TNT-Trajectory-Predition，显示其卓越的性能，而保留其原始代码。基于我们所取得的成就，希望对寻求改进弹道预测性能的研究人员有所启示。 摘要：With the rapid development of machine learning, autonomous driving has become a hot issue, making urgent demands for more intelligent perception and planning systems. Self-driving cars can avoid traffic crashes with precisely predicted future trajectories of surrounding vehicles. In this work, we review and categorize existing learning-based trajectory forecasting methods from perspectives of representation, modeling, and learning. Moreover, we make our implementation of Target-driveN Trajectory Prediction publicly available at https://github.com/Henry1iu/TNT-Trajectory-Predition, demonstrating its outstanding performance whereas its original codes are withheld. Enlightenment is expected for researchers seeking to improve trajectory prediction performance based on the achievement we have made.

【23】 Depth360: Monocular Depth Estimation using Learnable Axisymmetric Camera Model for Spherical Camera Image 标题：Depth360：基于可学习轴对称摄像机模型的球面摄像机图像单目深度估计 链接：https://arxiv.org/abs/2110.10415

作者：Noriaki Hirose,Kosuke Tahara 备注：8 pages, 6 figures, 2 tables 摘要：自监督单目深度估计已被广泛用于从RGB图像估计深度图像和相对姿态。该框架对研究人员很有吸引力，因为深度和姿势网络可以仅从时间序列图像进行训练，而不需要地面真实深度和姿势。在这项工作中，我们估计机器人周围的深度（360度视图）使用时间序列球形摄像机图像，从一个参数未知的摄像机。我们提出了一个可学习的轴对称相机模型，该模型接受带有两个鱼眼相机图像的畸变球形相机图像。此外，我们使用照片真实感模拟器对模型进行训练，生成地面真实深度图像，以提供监督。此外，我们引入了损失函数来提供地板约束，以减少反射地板表面可能产生的瑕疵。我们使用GO-Stanford数据集的球形摄像机图像和KITTI数据集的针孔摄像机图像来证明我们的方法的有效性，以比较我们的方法与基线方法在学习摄像机参数方面的性能。 摘要：Self-supervised monocular depth estimation has been widely investigated to estimate depth images and relative poses from RGB images. This framework is attractive for researchers because the depth and pose networks can be trained from just time sequence images without the need for the ground truth depth and poses. In this work, we estimate the depth around a robot (360 degree view) using time sequence spherical camera images, from a camera whose parameters are unknown. We propose a learnable axisymmetric camera model which accepts distorted spherical camera images with two fisheye camera images. In addition, we trained our models with a photo-realistic simulator to generate ground truth depth images to provide supervision. Moreover, we introduced loss functions to provide floor constraints to reduce artifacts that can result from reflective floor surfaces. We demonstrate the efficacy of our method using the spherical camera images from the GO Stanford dataset and pinhole camera images from the KITTI dataset to compare our method's performance with that of baseline method in learning the camera parameters.

【24】 A Fast Planning Approach for 3D Short Trajectory with a Parallel Framework 标题：一种基于并行框架的三维短轨迹快速规划方法 链接：https://arxiv.org/abs/2110.10376

作者：Han Chen,Shengyang Chen,Peng Lu,Chih-Yung Wen 机构： 1Department of Aeronautical and Aviation Engineering, Hong Kong Poly-technic University, 2Department of Mechanical Engineering, The Hong Kong PolytechnicUniversity, 3Department of Mechanical Engineering, The University of Hong Kong 备注：16 pages 摘要：对于无人机的实际应用而言，在未知环境中完全自主导航的能力是一项关键要求。然而，用较少的计算时间规划较短的路径是矛盾的。为了解决这个问题，本文提出了一个地图规划器和点云规划器并行运行的框架。地图规划器在2D地图上使用改进的跳跃点搜索方法确定初始路径，然后尝试通过考虑可能较短的3D路径来优化路径。点云规划器以高频率执行以生成运动基本体。它使无人机沿着已解决的路径飞行，并避开附近突然出现的障碍物。因此，车辆可以在对入侵障碍物快速反应的同时实现短轨迹。为了验证所提出的方法，我们在具有静态和动态障碍物的未知和复杂环境中进行了完全自主的四旋翼飞行试验。仿真和硬件实验表明，该框架具有良好的综合性能。 摘要：For real applications of unmanned aerial vehicles, the capability of navigating with full autonomy in unknown environments is a crucial requirement. However, planning a shorter path with less computing time is contradictory. To address this problem, we present a framework with the map planner and point cloud planner running in parallel in this paper. The map planner determines the initial path using the improved jump point search method on the 2D map, and then it tries to optimize the path by considering a possible shorter 3D path. The point cloud planner is executed at a high frequency to generate the motion primitives. It makes the drone follow the solved path and avoid the suddenly appearing obstacles nearby. Thus, vehicles can achieve a short trajectory while reacting quickly to the intruding obstacles. We demonstrate fully autonomous quadrotor flight tests in unknown and complex environments with static and dynamic obstacles to validate the proposed method. In simulation and hardware experiments, the proposed framework shows satisfactorily comprehensive performance.

【25】 Real-time Identification and Simultaneous Avoidance of Static and Dynamic Obstacles on Point Cloud for UAVs Navigation 标题：无人机导航中静电和点云动态障碍物的实时识别与同时避障 链接：https://arxiv.org/abs/2110.10360

作者：Han Chen,Peng Lu 机构：Department of Aeronautical and Aviation Engineering, Hong Kong Polytechnic University, Hong Kong, China., Department of Mechanical Engineering, The University of Hong Kong, Hong Kong, China. 备注：12 pages. arXiv admin note: text overlap with arXiv:2105.06622 摘要：在未知情况下，采用有效的飞行策略避免混合障碍物是无人机应用的关键挑战。在本文中，我们介绍了一种更稳健的技术来区分和跟踪动态障碍物和静态障碍物，只需点云输入。然后，为了实现动态避让，我们提出了禁止金字塔方法，通过一种有效的基于采样的迭代方法来求解期望车速。运动原语是通过求解具有期望速度和航路点约束的非线性优化问题生成的。此外，我们还提出了几种技术来处理近距离物体的位置估计误差、可变形物体的误差以及不同子模块之间的时间间隔。该方法已在机载实时运行，并在仿真和硬件测试中得到广泛验证，证明了我们在跟踪鲁棒性、能量消耗和计算时间方面的优势。 摘要：Avoiding hybrid obstacles in unknown scenarios with an efficient flight strategy is a key challenge for unmanned aerial vehicle applications. In this paper, we introduce a more robust technique to distinguish and track dynamic obstacles from static ones with only point cloud input. Then, to achieve dynamic avoidance, we propose the forbidden pyramids method to solve the desired vehicle velocity with an efficient sampling-based method in iteration. The motion primitives are generated by solving a nonlinear optimization problem with the constraint of desired velocity and the waypoint. Furthermore, we present several techniques to deal with the position estimation error for close objects, the error for deformable objects, and the time gap between different submodules. The proposed approach is implemented to run onboard in real-time and validated extensively in simulation and hardware tests, demonstrating our superiority in tracking robustness, energy cost, and calculating time.

【26】 Quadrotor Trajectory Tracking with Learned Dynamics: Joint Koopman-based Learning of System Models and Function Dictionaries 标题：具有学习动力学的四旋翼轨迹跟踪：基于联合库普曼的系统模型和函数字典的学习 链接：https://arxiv.org/abs/2110.10341

作者：Carl Folkestad,Skylar X. Wei,Joel W. Burdick 机构： California Institute of Technology 备注：arXiv admin note: text overlap with arXiv:2105.08036 摘要：非线性动力学效应对许多敏捷机器人系统的运行至关重要。基于Koopman的模型学习方法可以在高维提升双线性模型中捕捉这些非线性动力学系统的影响，这些模型适合于最优控制。然而，在模型学习之前使用固定函数字典提升系统状态的标准方法会导致难以实时控制的高维模型。本文提出了一种新的方法，通过将Koopman模型合并到神经网络结构中，联合学习函数字典并从数据中提取双线性模型。利用所学习的模型可以很容易地进行非线性MPC设计。我们在多旋翼无人机上实验实现了这种方法，用于在低空进行敏捷轨迹跟踪，在低空，气动地面效应会影响系统的行为。实验结果表明，基于学习的控制器与基于标称动力学模型的非线性MPC在中等高度下具有相似的性能。然而，我们的基于学习的系统能够可靠地跟踪近地飞行状态下的轨迹，而标称控制器由于我们的方法捕获的未建模动态效应而崩溃。 摘要：Nonlinear dynamical effects are crucial to the operation of many agile robotic systems. Koopman-based model learning methods can capture these nonlinear dynamical system effects in higher dimensional lifted bilinear models that are amenable to optimal control. However, standard methods that lift the system state using a fixed function dictionary before model learning result in high dimensional models that are intractable for real time control. This paper presents a novel method that jointly learns a function dictionary and lifted bilinear model purely from data by incorporating the Koopman model in a neural network architecture. Nonlinear MPC design utilizing the learned model can be performed readily. We experimentally realized this method on a multirotor drone for agile trajectory tracking at low altitudes where the aerodynamic ground effect influences the system's behavior. Experimental results demonstrate that the learning-based controller achieves similar performance as a nonlinear MPC based on a nominal dynamics model in medium altitude. However, our learning-based system can reliably track trajectories in near-ground flight regimes while the nominal controller crashes due to unmodeled dynamical effects that are captured by our method.

【27】 Semantic Sensing and Planning for Human-Robot Collaboration in Uncertain Environments 标题：不确定环境中人-机器人协作的语义感知与规划 链接：https://arxiv.org/abs/2110.10324

作者：Luke Burks,Hunter M. Ray,Jamison McGinley,Sousheel Vunnam,Nisar Ahmed 机构：UniversityofColoradoBoulder, a Na-tional Science Foundation IndustryUniversity Cooperative Research Center(IUCRC) under NSF Award No 摘要：自主机器人可以从人类提供的不确定任务环境和状态的语义表征中获益匪浅。然而，让机器人对这些软数据进行建模、通信和操作的集成策略的开发仍然具有挑战性。本文提出了一个用于人类机器人团队主动语义感知和规划的框架，该框架通过正式结合基于在线采样的POMDP策略、多模态语义交互和贝叶斯数据融合的优点来解决这些差距。这种方法允许人类在不确定的环境中通过绘制和标记环境中的任意地标，机会主义地施加模型结构并扩展语义软数据的范围。搜索移动目标时动态更新环境允许机器人代理主动向人类查询新的和相关的语义数据，从而改善未知环境和目标状态的信念，以改进在线规划。目标搜索仿真表明，与仅基于机器人感知的传统规划相比，拦截所需的时间和信念状态估计有显著改进。人类受试者研究表明，与单独的机器人相比，动态目标捕获率平均翻了一番，在一系列用户特征和交互模式上进行推理。互动视频可在以下网址找到：https://youtu.be/Eh-82ZJ1o4I. 摘要：Autonomous robots can benefit greatly from human-provided semantic characterizations of uncertain task environments and states. However, the development of integrated strategies which let robots model, communicate, and act on such soft data remains challenging. Here, a framework is presented for active semantic sensing and planning in human-robot teams which addresses these gaps by formally combining the benefits of online sampling-based POMDP policies, multi-modal semantic interaction, and Bayesian data fusion. This approach lets humans opportunistically impose model structure and extend the range of semantic soft data in uncertain environments by sketching and labeling arbitrary landmarks across the environment. Dynamic updating of the environment while searching for a mobile target allows robotic agents to actively query humans for novel and relevant semantic data, thereby improving beliefs of unknown environments and target states for improved online planning. Target search simulations show significant improvements in time and belief state estimates required for interception versus conventional planning based solely on robotic sensing. Human subject studies demonstrate a average doubling in dynamic target capture rate compared to the lone robot case, employing reasoning over a range of user characteristics and interaction modalities. Video of interaction can be found at https://youtu.be/Eh-82ZJ1o4I.

【28】 Incorporating Rich Social Interactions Into MDPs 标题：将丰富的社交活动整合到MDP中 链接：https://arxiv.org/abs/2110.10298

作者：Ravi Tejwani,Yen-Ling Kuo,Tianmin Shu,Bennett Stankovits,Dan Gutfreund,Joshua B. Tenenbaum,Boris Katz,Andrei Barbu 备注：Submitted to the 39th IEEE Conference on Robotics and Automation (ICRA 2022). Do not distribute 摘要：作为人类，我们所做的很多事情都是与其他代理进行社交，机器人最终也必须具备这一技能。我们证明，源自微观经济学和经济学的丰富的社会互动理论可以通过扩展嵌套MDP形式化，在MDP中，代理对彼此隐藏奖励的任意函数进行推理。这个扩展的社会MDP允许我们编码构成微观社会学基础的五种基本互动：合作、冲突、胁迫、竞争和交流。结果是一个机器人代理能够在新环境中执行社会交互Zero-Shot；和人类一样，它可以以新颖的方式参与社会活动，即使没有一个社会互动的例子。此外，在考虑环境中发生的社会互动时，这些社会MDP的判断与人类的判断密切相关。这种方法通过提供具体的数学定义，既揭示了社会互动的本质，又将丰富的社会互动引入到一个数学框架中，这个数学框架已被证明是机器人学的自然产物，MDP。 摘要：Much of what we do as humans is engage socially with other agents, a skill that robots must also eventually possess. We demonstrate that a rich theory of social interactions originating from microsociology and economics can be formalized by extending a nested MDP where agents reason about arbitrary functions of each other's hidden rewards. This extended Social MDP allows us to encode the five basic interactions that underlie microsociology: cooperation, conflict, coercion, competition, and exchange. The result is a robotic agent capable of executing social interactions zero-shot in new environments; like humans it can engage socially in novel ways even without a single example of that social interaction. Moreover, the judgments of these Social MDPs align closely with those of humans when considering which social interaction is taking place in an environment. This method both sheds light on the nature of social interactions, by providing concrete mathematical definitions, and brings rich social interactions into a mathematical framework that has proven to be natural for robotics, MDPs.

【29】 A Simple Approach to Continual Learning by Transferring Skill Parameters 标题：通过传递技能参数实现持续学习的一种简单方法 链接：https://arxiv.org/abs/2110.10255

作者：K. R. Zentner,Ryan Julian,Ujjwal Puri,Yulun Zhang,Gaurav S. Sukhatme 备注：Submitted to ICRA 2022 摘要：为了在现实世界中成为有效的通用机器，机器人不仅需要将其现有的操作技能适应新的环境，还需要在飞行中获得全新的技能。持续学习的一个巨大前景是，通过利用机器人从先前技能中积累的知识和经验，赋予机器人这种能力。我们重新审视这个问题，考虑一个设置，即机器人仅限于以学习技能策略的形式存储知识和经验。我们表明，存储技能策略、仔细的预训练以及适当选择何时转移这些技能策略足以在机器人操作的环境中建立一个持续的学习者。我们分析在具有挑战性的元世界模拟基准中需要哪些条件来转移技能。通过这一分析，我们引入了一个成对的度量相关技能，它允许我们预测任务之间技能转移的有效性，并使用它来减少课程选择中的持续学习问题。在适当的课程中，我们将展示如何在不忘记的情况下不断获得机器人操作技能，并且使用的样本远远少于从头开始训练它们所需的样本。 摘要：In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-the-fly. A great promise of continual learning is to endow robots with this ability, by using their accumulated knowledge and experience from prior skills. We take a fresh look at this problem, by considering a setting in which the robot is limited to storing that knowledge and experience only in the form of learned skill policies. We show that storing skill policies, careful pre-training, and appropriately choosing when to transfer those skill policies is sufficient to build a continual learner in the context of robotic manipulation. We analyze which conditions are needed to transfer skills in the challenging Meta-World simulation benchmark. Using this analysis, we introduce a pair-wise metric relating skills that allows us to predict the effectiveness of skill transfer between tasks, and use it to reduce the problem of continual learning to curriculum selection. Given an appropriate curriculum, we show how to continually acquire robotic manipulation skills without forgetting, and using far fewer samples than needed to train them from scratch.

【30】 Stochastic Assignment for Deploying Multiple Marsupial Robots 标题：多有袋类机器人部署的随机分配 链接：https://arxiv.org/abs/2110.10237

作者：Chris,Lee,Graeme Best,Geoffrey A. Hollinger 机构：The authors are with the Collaborative Robotics and IntelligentSystems (CoRIS) Institute, Oregon State University 备注：None 摘要：有袋机器人团队由运输和部署多个乘客机器人的运载机器人组成，例如一组运载和部署多个空中机器人的地面机器人，以快速探索复杂环境。我们专门解决规划运载机器人的部署时间和位置的问题，以最好地满足任务目标，同时对不确定的未来观测和奖励进行推理。虽然之前的工作提出了单运载机器人系统的最优多项式时间解决方案，但多运载机器人部署问题从根本上说更难，因为它需要解决多个乘客机器人部署之间的冲突和依赖性。我们提出了一种多载体机器人部署问题的集中式启发式搜索算法，该算法将蒙特卡罗树搜索与基于动态规划的顺序随机分配问题解决方案相结合，作为一种行动选择策略。我们对程序生成的数据和来自DARPA地下挑战城市回路的数据的结果表明，我们的方法的可行性以及与替代算法相比的实质性勘探性能改进。 摘要：Marsupial robot teams consist of carrier robots that transport and deploy multiple passenger robots, such as a team of ground robots that carry and deploy multiple aerial robots, to rapidly explore complex environments. We specifically address the problem of planning the deployment times and locations of the carrier robots to best meet the objectives of a mission while reasoning over uncertain future observations and rewards. While prior work proposed optimal, polynomial-time solutions to single-carrier robot systems, the multiple-carrier robot deployment problem is fundamentally harder as it requires addressing conflicts and dependencies between deployments of multiple passenger robots. We propose a centralized heuristic search algorithm for the multiple-carrier robot deployment problem that combines Monte Carlo Tree Search with a dynamic programming-based solution to the Sequential Stochastic Assignment Problem as a rollout action-selection policy. Our results with both procedurally-generated data and data drawn from the DARPA Subterranean Challenge Urban Circuit show the viability of our approach and substantial exploration performance improvements over alternative algorithms.

【31】 Optimal Sequential Stochastic Deployment of Multiple Passenger Robots 标题：多个载客机器人的最优序贯随机部署 链接：https://arxiv.org/abs/2110.10236

作者：Chris,Lee,Graeme Best,Geoffrey A. Hollinger 机构：The authors are with the Collaborative Robotics and IntelligentSystems (CoRIS) Institute, Oregon State University 备注：None 摘要：我们提出了一种在有袋机器人系统中部署乘客机器人的新算法。有袋机器人系统包括一个运载机器人（例如，地面车辆），该运载机器人能力强，任务持续时间长，以及至少一个由运载机器人运输的乘客机器人（例如，短时间的飞行器）。我们通过提出一种算法来优化乘客机器人的部署性能，该算法通过利用环境中感兴趣的特征的先验概率分布信息来推理过度不确定性。我们的算法被描述为一个序列随机分配问题（SSAP）的解。该算法的关键特征是递归关系，定义了一组观察阈值，用于决定何时部署乘客机器人。我们的算法以$O（NR）$时间计算最优策略，其中$N$是部署决策点的数量，$R$是要部署的乘客机器人的数量。我们对DARPA“地下挑战”的真实数据进行了无人机部署探索实验，以测试SSAP算法。我们的结果表明，我们的部署算法优于其他竞争算法，如经典的秘书方法和基线分区方法，并且与离线oracle算法相当。 摘要：We present a new algorithm for deploying passenger robots in marsupial robot systems. A marsupial robot system consists of a carrier robot (e.g., a ground vehicle), which is highly capable and has a long mission duration, and at least one passenger robot (e.g., a short-duration aerial vehicle) transported by the carrier. We optimize the performance of passenger robot deployment by proposing an algorithm that reasons over uncertainty by exploiting information about the prior probability distribution of features of interest in the environment. Our algorithm is formulated as a solution to a sequential stochastic assignment problem (SSAP). The key feature of the algorithm is a recurrence relationship that defines a set of observation thresholds that are used to decide when to deploy passenger robots. Our algorithm computes the optimal policy in $O(NR)$ time, where $N$ is the number of deployment decision points and $R$ is the number of passenger robots to be deployed. We conducted drone deployment exploration experiments on real-world data from the DARPA Subterranean challenge to test the SSAP algorithm. Our results show that our deployment algorithm outperforms other competing algorithms, such as the classic secretary approach and baseline partitioning methods, and is comparable to an offline oracle algorithm.

【32】 CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map 标题：COFI：用于激光雷达定位的从粗到精的ICP在高效、持久的点云地图中的应用 链接：https://arxiv.org/abs/2110.10194

作者：Yecheng Lyu,Xinming Huang,Ziming Zhang 机构： Ziming Zhang are with theDepartment of Electrical and Computer Engineering, Worcester PolytechnicInstitute 备注：8 pages, submitted to ICRA 2022 摘要：近年来，激光雷达里程计和定位技术引起了越来越多的研究兴趣。在现有的工作中，迭代最近点（ICP）由于其精确性和有效性而被广泛使用。然而，由于其非凸性和局部迭代策略，基于ICP的方法容易陷入局部最优，这反过来需要精确的初始化。在本文中，我们提出了CoFi，一种从粗到精的激光雷达定位ICP算法。具体来说，该算法在多体素分辨率下对输入点集进行下采样，并逐步细化从粗点集到细粒度点集的转换。此外，我们提出了一种基于地图的激光雷达定位算法，该算法从激光雷达帧中提取语义特征点，并应用CoFi在有效的点云地图上估计姿态。借助用于激光雷达扫描语义分割的Cylinder3D算法，提出的CoFi定位算法在KITTI里程计基准上展示了最先进的性能，与文献相比有显著改进。 摘要：LiDAR odometry and localization has attracted increasing research interest in recent years. In the existing works, iterative closest point (ICP) is widely used since it is precise and efficient. Due to its non-convexity and its local iterative strategy, however, ICP-based method easily falls into local optima, which in turn calls for a precise initialization. In this paper, we propose CoFi, a Coarse-to-Fine ICP algorithm for LiDAR localization. Specifically, the proposed algorithm down-samples the input point sets under multiple voxel resolution, and gradually refines the transformation from the coarse point sets to the fine-grained point sets. In addition, we propose a map based LiDAR localization algorithm that extracts semantic feature points from the LiDAR frames and apply CoFi to estimate the pose on an efficient point cloud map. With the help of the Cylinder3D algorithm for LiDAR scan semantic segmentation, the proposed CoFi localization algorithm demonstrates the state-of-the-art performance on the KITTI odometry benchmark, with significant improvement over the literature.

【33】 StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects 标题：StructFormer：用于语言引导的新奇物体语义重排的空间结构学习 链接：https://arxiv.org/abs/2110.10189

作者：Weiyu Liu,Chris Paxton,Tucker Hermans,Dieter Fox 机构：Rearrange objects that are smaller than the green glass pan, tower, top, left, west, line, top, left, large, circle, top, right, large, north, Rearrange objects that have the same color as the glass stapler, tower, top, right, west, line, bottom, left, large 摘要：将对象几何组织成语义上有意义的排列遍布于构建的世界。因此，在仓库、办公室和家庭中操作的辅助机器人将从识别和重新排列对象到这些语义有意义结构的能力中获益匪浅。为了发挥作用，这些机器人必须与以前看不见的物体抗衡，并在没有重大编程的情况下接收指令。虽然之前的工作已经研究了识别成对语义关系和顺序操作来改变这些简单关系，但没有一项工作显示出将对象排列成复杂结构（如圆或表格设置）的能力。为了解决这个问题，我们提出了一种新的基于Transformer的神经网络StructFormer，它以当前对象排列的部分视点云和编码所需对象配置的结构化语言命令作为输入。我们通过严格的实验表明，StructFormer使物理机器人能够利用从语言命令推断的多对象关系约束，将新对象重新排列为语义上有意义的结构。 摘要：Geometric organization of objects into semantically meaningful arrangements pervades the built world. As such, assistive robots operating in warehouses, offices, and homes would greatly benefit from the ability to recognize and rearrange objects into these semantically meaningful structures. To be useful, these robots must contend with previously unseen objects and receive instructions without significant programming. While previous works have examined recognizing pairwise semantic relations and sequential manipulation to change these simple relations none have shown the ability to arrange objects into complex structures such as circles or table settings. To address this problem we propose a novel transformer-based neural network, StructFormer, which takes as input a partial-view point cloud of the current object arrangement and a structured language command encoding the desired object configuration. We show through rigorous experiments that StructFormer enables a physical robot to rearrange novel objects into semantically meaningful structures with multi-object relational constraints inferred from the language command.

【34】 Feedback Linearization of Car Dynamics for Racing via Reinforcement Learning 标题：基于强化学习的赛车动力学反馈线性化 链接：https://arxiv.org/abs/2110.10441

作者：Michael Estrada,Sida Li,Xiangyu Cai 机构：Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, US 备注：Final research paper for Berkeley's CS 285 (Deep Reinforcement Learning) in Fall 2020 摘要：通过学习反馈线性化的方法，我们寻求学习一个线性化控制器，以简化控制汽车自主比赛的过程。在手动设计的线性化控制器中，采用软参与者-批评家方法学习解耦矩阵和漂移向量，有效地校正误差。其结果是一个精确线性化控制器，可用于使发展良好的线性系统理论能够设计易于实现且计算要求显著降低的路径规划和跟踪方案。为了演示反馈线性化方法，首先使用反馈线性化学习一个精确结构已知但与初始控制器不同的仿真模型，从而引入误差。我们进一步寻求将此方法应用于一个系统，该系统在专门为赛车动力学建模而设计的健身房环境中引入了更多错误。为此，我们对学习反馈线性化方法进行了扩展；使用监督学习训练的神经网络，将线性化控制器的输出转换为赛车环境所需的输入。报告了我们在实现这些目标方面取得的进展，并讨论了实现这些目标的下一步。 摘要：Through the method of Learning Feedback Linearization, we seek to learn a linearizing controller to simplify the process of controlling a car to race autonomously. A soft actor-critic approach is used to learn a decoupling matrix and drift vector that effectively correct for errors in a hand-designed linearizing controller. The result is an exactly linearizing controller that can be used to enable the well-developed theory of linear systems to design path planning and tracking schemes that are easy to implement and significantly less computationally demanding. To demonstrate the method of feedback linearization, it is first used to learn a simulated model whose exact structure is known, but varied from the initial controller, so as to introduce error. We further seek to apply this method to a system that introduces even more error in the form of a gym environment specifically designed for modeling the dynamics of car racing. To do so, we posit an extension to the method of learning feedback linearization; a neural network that is trained using supervised learning to convert the output of our linearizing controller to the required input for the racing environment. Our progress towards these goals is reported and the next steps in their accomplishment are discussed.

【35】 Theoretical Advances in Current Estimation and Navigation from a Glider-Based Acoustic Doppler Current Profiler (ADCP) 标题：基于滑翔机的声学多普勒海流剖面仪(ADCP)海流估计和导航的理论进展 链接：https://arxiv.org/abs/2110.10199

作者：Jacob Stevens-Haas,Sarah E. Webster,Aleksandr Aravkin 机构：a Department of Applied Mathematics, University of Washington. b Applied Physics Laboratory, arXiv:,.,v, [math.OC] , Oct 备注：Submitted to Journal of Atmospheric and Oceanic Technology. 15 pages main text. 10 pages figures, tables, bibliography, appendices 摘要：我们研究了声学多普勒流速剖面仪（ADCP）对水下滑翔机的测量，以确定滑翔机的位置、速度和地下水流。然而，ADCP并不直接观察感兴趣的数量；相反，他们测量车辆和水柱的相对运动。我们研究了以前应用于这个问题的数学创新的谱系，发现了一个未陈述但不正确的独立性假设。我们重新构造了一种最新的方法，以形成海流和车辆导航的联合概率模型，这使我们能够纠正这一假设并扩展经典的卡尔曼平滑方法。详细的模拟证实了我们计算估计值及其不确定性的方法的有效性。此处开发的联合模型为将来的工作奠定了基础，以纳入约束、范围测量和稳健的统计建模。 摘要：We examine acoustic Doppler current profiler (ADCP) measurements from underwater gliders to determine glider position, glider velocity, and subsurface current. ADCPs, however, do not directly observe the quantities of interest; instead, they measure the relative motion of the vehicle and the water column. We examine the lineage of mathematical innovations that have previously been applied to this problem, discovering an unstated but incorrect assumption of independence. We reframe a recent method to form a joint probability model of current and vehicle navigation, which allows us to correct this assumption and extend the classic Kalman smoothing method. Detailed simulations affirm the efficacy of our approach for computing estimates and their uncertainty. The joint model developed here sets the stage for future work to incorporate constraints, range measurements, and robust statistical modeling.