机器人相关学术速递[10.20]

cs.RO机器人相关，共计15篇

【1】 Continuous Control with Action Quantization from Demonstrations 标题：基于演示的动作量化连续控制 链接：https://arxiv.org/abs/2110.10149

作者：Robert Dadashi,Léonard Hussenot,Damien Vincent,Sertan Girgin,Anton Raichuk,Matthieu Geist,Olivier Pietquin 机构：Google Research, Brain Team 摘要：在强化学习（RL）中，与连续动作相反，离散动作会导致不太复杂的探索问题，并立即计算动作值函数的最大值，这是基于动态规划的方法的核心。在本文中，我们提出了一种新的方法：来自演示的动作量化（AQuaDem），通过利用演示的先验知识来学习连续动作空间的离散化。这大大减少了探索问题，因为代理所面临的行动不仅是有限的，而且根据演示者的行为也是合理的。通过离散动作空间，我们可以将任何离散动作深度RL算法应用于连续控制问题。我们在三种不同的设置上评估了所提出的方法：带演示的RL，带播放数据的RL——演示人类在环境中播放，但不解决任何特定任务——以及模仿学习。对于所有三个设置，我们只考虑人的数据，这是比合成数据更具挑战性。我们发现AQuaDem在性能和样本效率方面始终优于最先进的连续控制方法。我们在报纸的网站上提供可视化和视频：https://google-research.github.io/aquadem. 摘要：In Reinforcement Learning (RL), discrete actions, as opposed to continuous actions, result in less complex exploration problems and the immediate computation of the maximum of the action-value function which is central to dynamic programming-based methods. In this paper, we propose a novel method: Action Quantization from Demonstrations (AQuaDem) to learn a discretization of continuous action spaces by leveraging the priors of demonstrations. This dramatically reduces the exploration problem, since the actions faced by the agent not only are in a finite number but also are plausible in light of the demonstrator's behavior. By discretizing the action space we can apply any discrete action deep RL algorithm to the continuous control problem. We evaluate the proposed method on three different setups: RL with demonstrations, RL with play data --demonstrations of a human playing in an environment but not solving any specific task-- and Imitation Learning. For all three setups, we only consider human data, which is more challenging than synthetic data. We found that AQuaDem consistently outperforms state-of-the-art continuous control methods, both in terms of performance and sample efficiency. We provide visualizations and videos in the paper's website: https://google-research.github.io/aquadem.

【2】 Learning-based Fast Path Planning in Complex Environments 标题：复杂环境下基于学习的快速路径规划 链接：https://arxiv.org/abs/2110.10041

作者：Jianbang Liu,Baopu Li,Tingguang Li,Wenzheng Chi,Jiankun Wang,Max Q. -H. Meng 机构： 4School of Mechanical and Electric Engineering, SoochowUniversity 备注：Accepted by ROBIO2021 摘要：在本文中，我们提出了一种新的路径规划算法来实现复杂环境下的快速路径规划。现有的大多数路径规划算法难以在复杂环境下快速找到可行路径，甚至失败。然而，我们提出的框架可以通过使用基于学习的预测模块和基于采样的路径规划模块来克服这一困难。预测模块利用卷积神经网络（CNN）等自动编码器-解码器输出可行路径可能所在的有希望的区域。在这个过程中，我们将环境视为RGB图像输入到我们设计的CNN模块中，并且输出也是RGB图像。不需要额外的计算，因此我们可以保持每秒60帧（FPS）的高处理速度。结合基于采样的路径规划器，我们可以从输出图像中提取一条可行的路径，以便机器人能够从起点跟踪到目标。为了证明该算法的优越性，我们在一系列仿真实验中将其与传统的路径规划算法进行了比较。结果表明，该算法在规划时间、成功率和路径长度等方面都能获得更好的性能。 摘要：In this paper, we present a novel path planning algorithm to achieve fast path planning in complex environments. Most existing path planning algorithms are difficult to quickly find a feasible path in complex environments or even fail. However, our proposed framework can overcome this difficulty by using a learning-based prediction module and a sampling-based path planning module. The prediction module utilizes an auto-encoder-decoder-like convolutional neural network (CNN) to output a promising region where the feasible path probably lies in. In this process, the environment is treated as an RGB image to feed in our designed CNN module, and the output is also an RGB image. No extra computation is required so that we can maintain a high processing speed of 60 frames-per-second (FPS). Incorporated with a sampling-based path planner, we can extract a feasible path from the output image so that the robot can track it from start to goal. To demonstrate the advantage of the proposed algorithm, we compare it with conventional path planning algorithms in a series of simulation experiments. The results reveal that the proposed algorithm can achieve much better performance in terms of planning time, success rate, and path length.

【3】 A Soft-Rigid Hybrid Gripper with Lateral Compliance and Dexterous In-hand Manipulation 标题：一种侧向柔顺灵巧手部操作的软-刚混合夹持器 链接：https://arxiv.org/abs/2110.10035

作者：Wenpei Zhu,Chenghua Lu,Qule Zheng,Zhonggui Fang,Haichuan Che,Kailuan Tang,Mingchao Zhu,Sicong Liu,Zheng Wang 机构：Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of, Mechanical and Energy Engineering, Southern University of Science and Technology, Guangdong Provincial Key Laboratory of Human Augmentation and Rehabilitation 摘要：软夹持器由于其基于合规性的交互安全性和灵巧性而受到越来越多的关注。混合夹持器（刚性约束增强的软执行器）是软夹持器设计的新趋势。通过软执行器驱动正确的结构部件，它们可以实现良好的抓取适应性和有效载荷，同时也易于用传统运动学建模和控制。然而，现有的工作主要集中在通过简单的平面工作空间实现更高的有效载荷和感知能力，从而导致与传统手爪相比灵活性大大降低。在这项工作中，我们从人类掌指关节（MCP）中汲取灵感，提出了一种新的混合式夹持器设计，具有8块独立的肌肉。结果表明，增加MCP复杂性对于实现混合式手爪的一系列新功能至关重要，包括手部操作、侧向被动顺应性以及新的控制模式。在我们专有的具有视觉引导抓取的双臂机器人平台上制造并测试了一个原型抓取器。使用非常轻的气动波纹管软执行器，夹钳可以抓住超过自身重量25倍的物体，并具有横向柔顺性。使用双臂平台，使用两个混合夹持器演示高度拟人化的灵巧操作，从在刚性杆上拔河到使用手内操作在两个夹持器之间传递软毛巾。与所提出的混合夹持器的新特性和性能规格相匹配，还介绍了基本的建模、驱动、控制和实验验证细节，为实现机器人夹持器的灵活性、强度和柔顺性增强提供了一种有希望的方法。 摘要：Soft grippers are receiving growing attention due to their compliance-based interactive safety and dexterity. Hybrid gripper (soft actuators enhanced by rigid constraints) is a new trend in soft gripper design. With right structural components actuated by soft actuators, they could achieve excellent grasping adaptability and payload, while also being easy to model and control with conventional kinematics. However, existing works were mostly focused on achieving superior payload and perception with simple planar workspaces, resulting in far less dexterity compared with conventional grippers. In this work, we took inspiration from the human Metacarpophalangeal (MCP) joint and proposed a new hybrid gripper design with 8 independent muscles. It was shown that adding the MCP complexity was critical in enabling a range of novel features in the hybrid gripper, including in-hand manipulation, lateral passive compliance, as well as new control modes. A prototype gripper was fabricated and tested on our proprietary dual-arm robot platform with vision guided grasping. With very lightweight pneumatic bellows soft actuators, the gripper could grasp objects over 25 times its own weight with lateral compliance. Using the dual-arm platform, highly anthropomorphic dexterous manipulations were demonstrated using two hybrid grippers, from Tug-of-war on a rigid rod, to passing a soft towel between two grippers using in-hand manipulation. Matching with the novel features and performance specifications of the proposed hybrid gripper, the underlying modeling, actuation, control, and experimental validation details were also presented, offering a promising approach to achieving enhanced dexterity, strength, and compliance in robotic grippers.

【4】 Robust Control of a Multi-Axis Shape Memory Alloy-Driven Soft Manipulator 标题：多轴形状记忆合金驱动软机械手的鲁棒控制 链接：https://arxiv.org/abs/2110.10022

作者：Zach J. Patterson,Andrew P. Sabelhaus,Carmel Majidi 机构： and anIntelligence Community Postdoctoral Research Fellowship through the OakRidge Institute for Sciece and Education (Corresponding author, Department of Mechanical Engineering, CarnegieMellon University 备注：This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 摘要：对于具有先进功能和新颖驱动的设计而言，软机械手的控制仍然是一个挑战。形状记忆合金（SMA）驱动的软机器人存在两个显著的局限性，即多轴、三维运动以及执行器动力学和约束。本文采用鲁棒反馈控制方案解决了这两个问题，并演示了这种类型的软机器人机械手的状态跟踪控制。我们的控制器使用静态梁弯曲模型将软肢近似为LTI系统，同时使用奇异值分解补偿器方法将多轴运动解耦，并使用抗饱和元件实现执行器饱和。我们证明了控制器的稳定性和鲁棒性，鲁棒性旨在说明未建模的动态。我们的实现在软SMA动力肢体的硬件测试中得到验证，显示出较低的跟踪误差，对于未来的多肢机器人具有良好的效果。 摘要：Control of soft robotic manipulators remains a challenge for designs with advanced capabilities and novel actuation. Two significant limitations are multi-axis, three-dimensional motion of soft bodies alongside actuator dynamics and constraints, both of which are present in shape-memory-alloy (SMA)-powered soft robots. This article addresses both concerns with a robust feedback control scheme, demonstrating state tracking control for a soft robot manipulator of this type. Our controller uses a static beam bending model to approximate the soft limb as an LTI system, alongside a singular-value-decomposition compensator approach to decouple the multi-axial motion and an anti-windup element for the actuator saturation. We prove stability and verify robustness of our controller, with robustness intended to account for the unmodeled dynamics. Our implementation is verified in hardware tests of a soft SMA-powered limb, showing low tracking error, with promising results for future multi-limbed robots.

【5】 Watch out for the risky actors: Assessing risk in dynamic environments for safe driving 标题：警惕危险行为者：评估动态环境中的风险以实现安全驾驶 链接：https://arxiv.org/abs/2110.09998

作者：Saurabh Jha,Yan Miao,Zbigniew Kalbarczyk,Ravishankar K. Iyer 机构：University of Illinois at Urbana-Champaign 备注：preprint version 摘要：在由其他参与者组成的动态环境中驾驶本质上是一项危险的任务，因为每个参与者都会影响驾驶决策，并可能显著限制导航和安全计划方面的选择数量。自我参与者所遇到的风险取决于驾驶场景以及与预测驾驶场景中其他参与者未来轨迹相关的不确定性。然而，并非所有物体都具有类似的风险。取决于物体的类型、轨迹、位置以及与这些量相关的不确定性；有些物体的危险性比其他物体高得多。与参与者相关的风险越高，就资源和安全规划而言，必须更加关注该参与者。在本文中，我们提出了一种新的风险度量来计算世界上每个参与者的重要性，并通过一个案例研究来证明其有用性。 摘要：Driving in a dynamic environment that consists of other actors is inherently a risky task as each actor influences the driving decision and may significantly limit the number of choices in terms of navigation and safety plan. The risk encountered by the Ego actor depends on the driving scenario and the uncertainty associated with predicting the future trajectories of the other actors in the driving scenario. However, not all objects pose a similar risk. Depending on the object's type, trajectory, position, and the associated uncertainty with these quantities; some objects pose a much higher risk than others. The higher the risk associated with an actor, the more attention must be directed towards that actor in terms of resources and safety planning. In this paper, we propose a novel risk metric to calculate the importance of each actor in the world and demonstrate its usefulness through a case study.

【6】 Towards Optimal Correlational Object Search 标题：朝向最佳相关对象搜索 链接：https://arxiv.org/abs/2110.09991

作者：Kaiyu Zheng,Rohan Chitnis,Yoonchang Sung,George Konidaris,Stefanie Tellex 机构： previous approaches to object†Brown University 备注：10 pages, 4 figures, 3 tables 摘要：在目标搜索的实际应用中，机器人需要在复杂环境中定位目标，同时应对不可靠的传感器，尤其是小的或难以检测的目标。在这样的环境中，相关信息对于有效地规划是很有价值的：当寻找叉子时，机器人可以从定位更容易检测到的冰箱开始，因为叉子可能在附近找到。以前使用相关信息进行对象搜索的方法通常采用特殊或贪婪的搜索策略。在本文中，我们提出了相关对象搜索POMDP（COS-POMDP），它可以用来产生使用相关信息的搜索策略。COS POMDP包含一个基于相关性的观察模型，该模型允许我们避免维持对所有对象的联合信念的指数膨胀，同时保持这种幼稚的指数POMDP公式的最优解。我们提出了一种分层规划算法来扩展实际领域的COS-POMDP。我们使用AI2-THOR（一种真实的家庭环境模拟器）和YOLOv5（一种广泛使用的物体检测器）进行实验。我们的结果表明，特别是对于难以检测的对象，如刷子和遥控器，与忽略相关性的基线以及贪婪的次优视图方法相比，我们的方法提供了最稳健的性能。 摘要：In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-detect objects. In such settings, correlational information can be valuable for planning efficiently: when looking for a fork, the robot could start by locating the easier-to-detect refrigerator, since forks would probably be found nearby. Previous approaches to object search with correlational information typically resort to ad-hoc or greedy search strategies. In this paper, we propose the Correlational Object Search POMDP (COS-POMDP), which can be solved to produce search strategies that use correlational information. COS-POMDPs contain a correlation-based observation model that allows us to avoid the exponential blow-up of maintaining a joint belief about all objects, while preserving the optimal solution to this naive, exponential POMDP formulation. We propose a hierarchical planning algorithm to scale up COS-POMDP for practical domains. We conduct experiments using AI2-THOR, a realistic simulator of household environments, as well as YOLOv5, a widely-used object detector. Our results show that, particularly for hard-to-detect objects, such as scrub brush and remote control, our method offers the most robust performance compared to baselines that ignore correlations as well as a greedy, next-best view approach.

【7】 Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Space 标题：利用自适应力阻抗动作空间学习机器人操作技能 链接：https://arxiv.org/abs/2110.09904

作者：Maximilian Ulmer,Elie Aljalbout,Sascha Schwarz,Sami Haddadin 机构： proprioceptive measurements need to beevaluated in real-time for control and sometimes require an 1Technical University of Munich (TUM) 摘要：智能代理必须能够快速和缓慢地思考，以执行复杂的操作任务。强化学习（RL）在一系列具有挑战性的决策任务中取得了许多有希望的结果。然而，在现实世界的机器人技术中，这些方法仍然很困难，因为它们需要大量昂贵的交互，并且反馈循环缓慢。另一方面，快速仿人自适应控制方法可以优化复杂的机器人交互，但无法集成非结构化任务所需的多模态反馈。在这项工作中，我们建议在分层学习和自适应架构中考虑学习问题，以获得两个方面的最佳效果。该框架由两个部分组成，一个是在多模态观测条件下优化任务策略的慢速强化学习策略，另一个是持续优化机械手运动、稳定性和作用力的快速实时自适应控制策略。我们通过一个我们称之为力量的仿生行动空间来组合这些组件。我们在真实硬件上的一个接触丰富的操作任务上演示了新的动作空间，并在三个模拟操作任务上评估了它的性能。我们的实验表明，AFORCE极大地提高了样品效率，同时降低了能耗，提高了安全性。 摘要：Intelligent agents must be able to think fast and slow to perform elaborate manipulation tasks. Reinforcement Learning (RL) has led to many promising results on a range of challenging decision-making tasks. However, in real-world robotics, these methods still struggle, as they require large amounts of expensive interactions and have slow feedback loops. On the other hand, fast human-like adaptive control methods can optimize complex robotic interactions, yet fail to integrate multimodal feedback needed for unstructured tasks. In this work, we propose to factor the learning problem in a hierarchical learning and adaption architecture to get the best of both worlds. The framework consists of two components, a slow reinforcement learning policy optimizing the task strategy given multimodal observations, and a fast, real-time adaptive control policy continuously optimizing the motion, stability, and effort of the manipulator. We combine these components through a bio-inspired action space that we call AFORCE. We demonstrate the new action space on a contact-rich manipulation task on real hardware and evaluate its performance on three simulated manipulation tasks. Our experiments show that AFORCE drastically improves sample efficiency while reducing energy consumption and improving safety.

【8】 A Lightweight, High-Extension, Planar 3-Degree-of-Freedom Manipulator Using Pinched Bistable Tapes 标题：一种采用夹持双稳带的轻量化、高伸缩性平面三自由度机械手 链接：https://arxiv.org/abs/2110.09751

作者：Brian H. Do,O. Godson Osele,Allison M. Okamura 机构：The authors are with the Department of Mechanical Engineering, Stanford University 备注：ICRA 2022 摘要：为了便于在远程和/或受限环境中进行传感和物理交互，与传统的串行链机械手相比，高扩展、轻型机械手更易于运输和到达更远的地方。我们提出了一种新型的平面三自由度机械手，该机械手通过使用一对卷绕双稳态磁带（通常用于自收缩磁带测量）实现低重量和高延伸，这些磁带夹在一起形成可重构旋转关节。夹持作用使胶带变平，产生局部弯曲区域，从而形成旋转接头，通过夹持机构的摩擦驱动运动，可通过电缆张力改变其方向及其在胶带上的位置。我们介绍了该机械手的设计、实现、运动学建模、旋转关节的刚度特性和准静态性能。特别是，我们演示了操纵器在自由空间中到达指定目标、到达具有各种方向的2D目标以及在改变另一个方向的同时保持末端执行器角度或固定弯曲点的能力。这项工作的长期目标是将机械手与无人机集成，以实现更强大的空中操纵能力。 摘要：To facilitate sensing and physical interaction in remote and/or constrained environments, high-extension, lightweight robot manipulators are easier to transport and reach substantially further than traditional serial chain manipulators. We propose a novel planar 3-degree-of-freedom manipulator that achieves low weight and high extension through the use of a pair of spooling bistable tapes, commonly used in self-retracting tape measures, which are pinched together to form a reconfigurable revolute joint. The pinching action flattens the tapes to produce a localized bending region, resulting in a revolute joint that can change its orientation by cable tension and its location on the tapes though friction-driven movement of the pinching mechanism. We present the design, implementation, kinematic modeling, stiffness behavior of the revolute joint, and quasi-static performance of this manipulator. In particular, we demonstrate the ability of the manipulator to reach specified targets in free space, reach a 2D target with various orientations, and maintain an end-effector angle or stationary bending point while changing the other. The long-term goal of this work is to integrate the manipulator with an unmanned aerial vehicle to enable more capable aerial manipulation.

【9】 UAV Path Planning for Optimal Coverage of Areas with Nonuniform Importance 标题：无人机路径规划在非均匀重要性区域最优覆盖中的应用 链接：https://arxiv.org/abs/2110.09745

作者：Gregory Snyder,Sachin Shriwastav,Dylan Morrison-Fogel,Zhuoyuan Song 机构：University of Hawai‘i at M¯anoa, Honolulu, HI 备注：9 pages, 5 figures 摘要：从科学和气象角度来看，难以覆盖具有潜在健康和安全危害的难以接近或困难地形，如火山区，但至关重要。该区域内包含的区域可以为我们提供不同类型的重要信息。我们提出了一种用无人机（UAV）优化覆盖夏威夷火山区的算法。目标区域被分配了非均匀的覆盖重要性分数分布。对于指定的无人机电池容量，优化问题寻求最大化总覆盖面积和累积重要性得分的路径，同时惩罚相同区域的重访。根据可用的功率和覆盖信息地图，无人机离线生成轨迹。最佳轨迹将未使用的电池电量降至最低，同时强制无人机返回其起始位置。该多目标优化问题采用序列二次规划求解。讨论了竞争优化问题的细节以及分析和仿真结果，以证明所提算法的适用性。 摘要：Coverage of an inaccessible or difficult terrain with potential health and safety hazards, such as in a volcanic region, is difficult yet crucial from scientific and meteorological perspectives. Areas contained within this region can provide us with different types of valuable information of varying importance. We present an algorithm to optimally cover a volcanic region in Hawai`i with an unmanned aerial vehicle (UAV). The target region is assigned with a nonuniform coverage importance score distribution. For a specified battery capacity of the UAV, the optimization problem seeks the path that maximizes the total coverage area and the accumulated importance score while penalizing the revisiting of the same area. Trajectories are generated offline for the UAV based on the available power and coverage information map. The optimal trajectory minimizes the unspent battery power while enforcing that the UAV returns to its starting location. This multi-objective optimization problem is solved by using sequential quadratic programming. The details of the competitive optimization problem are discussed along with the analysis and simulation results to demonstrate the applicability of the proposed algorithm.

【10】 Trajectory Prediction with Linguistic Representations 标题：基于语言表示的弹道预测 链接：https://arxiv.org/abs/2110.09741

作者：Yen-Ling Kuo,Xin Huang,Andrei Barbu,Stephen G. McGill,Boris Katz,John J. Leonard,Guy Rosman 机构： access tothe descriptions of two scenarios enables one to quickly 1Toyota Research Institute 摘要：语言允许人类建立心理模型，解释周围发生的事情，从而做出更准确的长期预测。我们提出了一种新的轨迹预测模型，该模型使用语言中间表示来预测轨迹，并使用带有部分注释标题的轨迹样本进行训练。该模型在没有直接逐字监督的情况下学习每个单词的含义。在推理时，它生成一个轨迹的语言描述，该描述捕获了一个延长的时间间隔内的机动和交互。生成的描述用于优化多个代理的轨迹预测。我们在Argoverse数据集上训练和验证了我们的模型，并在轨迹预测中展示了改进的精度结果。此外，我们的模型更具解释性：它以简单的语言将部分推理呈现为标题，这有助于模型开发，并有助于在部署模型之前建立对模型的信心。 摘要：Language allows humans to build mental models that interpret what is happening around them resulting in more accurate long-term predictions. We present a novel trajectory prediction model that uses linguistic intermediate representations to forecast trajectories, and is trained using trajectory samples with partially annotated captions. The model learns the meaning of each of the words without direct per-word supervision. At inference time, it generates a linguistic description of trajectories which captures maneuvers and interactions over an extended time interval. This generated description is used to refine predictions of the trajectories of multiple agents. We train and validate our model on the Argoverse dataset, and demonstrate improved accuracy results in trajectory prediction. In addition, our model is more interpretable: it presents part of its reasoning in plain language as captions, which can aid model development and can aid in building confidence in the model before deploying it.

【11】 PI(t)D(t) Control and Motion Profiling for Omnidirectional Mobile Robots 标题：全方位移动机器人的PI(T)D(T)控制与运动仿形 链接：https://arxiv.org/abs/2110.09707

作者：Michael Zeng 备注：12 pages, 13 figures 摘要：最近，出现了一种为人类服务的自主移动机器人的趋势，其具有多种应用，包括在人员稀少的医院、酒店或实验室运送用品，或对室内紧急情况做出反应。然而，现有的自主移动机器人（AMR）运动速度慢且效率低，这是人类服务应用扩散的一个基本障碍。本研究开发了一种运动控制体系结构，展示了几种算法在提高速度和效率方面的潜力。其中包括一种新颖的PI（t）D（t）控制器，该控制器将积分和微分增益设置为时间的函数，以及应用于完整运动的运动轮廓。由此产生的性能表明，有可能实现更快、更高效的AMR，从而保持较高的精度和可重复性。希望这项研究可以作为更快运动控制的概念证明，消除进一步使用为人类服务的移动机器人的关键障碍。 摘要：Recently, a trend is emerging toward human-servicing autonomous mobile robots, with diverse applications including delivery of supplies in hospitals, hotels, or labs where personnel are scarce, or reacting to indoor emergencies. However, existing autonomous mobile robot (AMR) motion is slow and inefficient, a foundational barrier to proliferation of human-servicing applications. This research has developed a motion control architecture that demonstrates the potential of several algorithms for increasing speed and efficiency. These include a novel PI(t)D(t) controller that sets integral and derivative gains as functions of time, and motion-profiling applied for holonomic motion. Resulting performance indicates potential for faster, more efficient AMRs, that maintain high levels of accuracy and repeatability. The hope is that this research can serve as a proof of concept for faster motion-control, to remove a key barrier to further use of human-servicing mobile robots.

【12】 Probabilistic Semantic Data Association for Collaborative Human-Robot Sensing 标题：人-机器人协同感知的概率语义数据关联 链接：https://arxiv.org/abs/2110.09621

作者：Shohei Wakayama,Nisar Ahmed 机构： University of Colorado Boulder 备注：15 pages, 14 figures 摘要：在协作的人类-机器人语义感知问题中，例如在科学探索中，机器人可能会过度信任人类伙伴提供的信息，从而导致次优状态估计和较差的团队绩效。当人类不能被视为神谕者时，机器人需要更新状态信念，以正确解释人类语义观察和导致这些观察的实际世界状态之间可能存在的差异。这项工作制定了在一般环境下严格在线计算语义可能性的概率语义数据关联（PSDA）概率的策略，这与之前的工作不同，之前的工作为特定环境开发了朴素或启发式近似。新的PSDA方法被纳入混合贝叶斯数据融合方案，该方案使用高斯混合先验值作为对象状态，使用softmax函数作为语义人体传感器观察概率，并在合作多目标搜索任务的蒙特卡罗模拟中进行了演示，该模拟具有一系列相关的人类感知特征（如误检率）。结果表明，当语义人类传感器数据包含用于自主目标搜索和定位的重要目标参考模糊度时，PSDA可以在广泛的条件下稳健地估计观测关联概率。 摘要：In collaborative human-robot semantic sensing problems, e.g. for scientific exploration, robots could potentially overtrust information given by a human partner, resulting in suboptimal state estimation and poor team performance. When humans cannot be treated as oracles, robots need to update state beliefs to correctly account for possible discrepancies between human semantic observations and the actual world states which lead to those observations. This work develops strategies for rigorous online calculation of probabilistic semantic data association (PSDA) probabilities for semantic likelihoods in general settings, unlike previous work which developed naive or heuristic approximations for specific settings. The new PSDA method is incorporated into a hybrid Bayesian data fusion scheme which uses Gaussian mixture priors for object states and softmax functions for semantic human sensor observation likelihoods, and is demonstrated in Monte Carlo simulations of collaborative multi-object search missions featuring a range of relevant human sensing characteristics (e.g. false detection rate). It is shown that PSDA leads to robust estimation of observation association probabilities under a wide range of conditions whenever semantic human sensor data contain significant target reference ambiguities for autonomous object search and localization.

【13】 Active Tapping via Gaussian Process for Efficient Unknown Object Surface Reconstruction 标题：基于高斯过程的主动抽头高效未知物体表面重建 链接：https://arxiv.org/abs/2110.09593

作者：Su Sun,Byung-Cheol Min 机构： Department of Computer and In-formation Technology, Purdue University 摘要：物体表面重构为机器人抓取、物体识别和物体操纵带来了本质的好处。当通过攻丝测量未知物体的表面分布时，最大的挑战是在没有物体区域先验知识的情况下高效准确地选择攻丝位置。在给定的搜索范围内，我们提出了一种主动探索的方法，能够高效、智能地引导攻丝学习物体表面，而无需穷尽和不必要的非表面攻丝。我们分析了我们的方法在探测范围大于物体的物体表面建模中的性能，使用配备有末端攻丝工具的机器人手臂执行攻丝运动。实验结果表明，该方法成功地对未知物体的表面进行了建模，与现有技术相比，在所有抽头中，所需抽头的比例提高了59%。 摘要：Object surface reconstruction brings essential benefits to robot grasping, object recognition, and object manipulation. When measuring the surface distribution of an unknown object by tapping, the greatest challenge is to select tapping positions efficiently and accurately without prior knowledge of object region. Given a searching range, we propose an active exploration method, to efficiently and intelligently guide the tapping to learn the object surface without exhaustive and unnecessary off-surface tapping. We analyze the performance of our approach in modeling object surfaces within an exploration range larger than the object using a robot arm equipped with an end-of-arm tapping tool to execute tapping motions. Experimental results show that the approach successfully models the surface of unknown objects with a relative 59% improvement in the proportion of necessary taps among all taps compared with state-of-art performance.

【14】 Set-based State Estimation with Probabilistic Consistency Guarantee under Epistemic Uncertainty 标题：认知不确定性下具有概率一致性保证的基于集合的状态估计 链接：https://arxiv.org/abs/2110.09584

作者：Shen Li,Theodoros Stouraitis,Michael Gienger,Sethu Vijayakumar,Julie A. Shah 机构：UniversityofEdinburgh 摘要：一致性状态估计具有挑战性，尤其是在学习（非线性）动态和观测模型产生的认知不确定性下。在这项工作中，我们开发了一种基于集合的估计算法，该算法产生了除任意不确定性外，还考虑学习模型中认知不确定性的区域性状态估计。我们的算法保证了概率一致性，即真实状态总是以高概率的zonotopes为界。在学习（非线性）模型的情况下，我们正式地将基于集合的方法与相应的概率方法（GP-EKF）联系起来。特别是，当忽略线性化误差和任意不确定性，简化了认知不确定性时，我们的基于集合的方法将简化为其概率对应方法。我们的方法的改进一致性在模拟摆域和真实世界的机器人辅助穿衣域中都得到了实证证明，其中机器人利用其末端执行器处的力测量来估计人类手臂的配置。 摘要：Consistent state estimation is challenging, especially under the epistemic uncertainties arising from learned (nonlinear) dynamic and observation models. In this work, we develop a set-based estimation algorithm, that produces zonotopic state estimates that respect the epistemic uncertainties in the learned models, in addition to the aleatoric uncertainties. Our algorithm guarantees probabilistic consistency, in the sense that the true state is always bounded by the zonotopes, with a high probability. We formally relate our set-based approach with the corresponding probabilistic approach (GP-EKF) in the case of learned (nonlinear) models. In particular, when linearization errors and aleatoric uncertainties are omitted, and epistemic uncertainties are simplified, our set-based approach reduces to its probabilistic counterpart. Our method's improved consistency is empirically demonstrated in both a simulated pendulum domain and a real-world robot-assisted dressing domain, where the robot estimates the configuration of the human arm utilizing the force measurements at its end effector.

【15】 Improving GNSS Positioning using Neural Network-based Corrections 标题：基于神经网络改正的GNSS定位改进 链接：https://arxiv.org/abs/2110.09581

作者：Ashwin V. Kanhere,Shubh Gupta,Akshay Shetty,Grace Gao 机构：BIOGRAPHY, an M.S. in Aerospace Engineering from the University of Illinois at Urbana-Champaign in , and a B.Tech in Aerospace, Engineering from the Indian Institute of Technology Bombay, Mumbai in ,. His research interests are in reliable navigation 备注：13 pages, 6 figures, submitted to ION GNSS+ 2021 摘要：深度神经网络（DNN）具有利用数据建模复杂误差的能力，是在存在多径和非视线误差的情况下进行全球导航卫星系统（GNSS）定位的一种很有前途的工具。然而，为全球导航卫星系统定位开发DNN带来了各种挑战，例如1）全球范围内测量值和位置值的巨大变化导致数值调节不良，2）由于卫星能见度的变化导致测量数据集内的数量和顺序变化，以及3）对可用数据的过度拟合。在这项工作中，我们解决了上述挑战，并提出了一种将基于DNN的修正应用于初始位置猜测的GNSS定位方法。我们的DNN学习使用伪距残差集和卫星视线向量作为输入输出位置校正。这些输入和输出值的有限变化改善了DNN的数值调节。我们设计了DNN体系结构，通过利用基于集合的深度学习方法的最新进展，将来自可用GNSS测量值的信息结合起来，这些测量值在数量和顺序上都有所不同。此外，我们提出了一种数据增强策略，通过对初始位置猜测进行随机化来减少DNN中的过度拟合。我们首先进行了模拟，并显示了在应用基于DNN的校正时初始定位误差的改善。在此之后，我们证明了我们的方法在真实数据上优于WLS基线。我们的实现可在github.com/Stanford-NavLab/deep_gnss上获得。 摘要：Deep Neural Networks (DNNs) are a promising tool for Global Navigation Satellite System (GNSS) positioning in the presence of multipath and non-line-of-sight errors, owing to their ability to model complex errors using data. However, developing a DNN for GNSS positioning presents various challenges, such as 1) poor numerical conditioning caused by large variations in measurements and position values across the globe, 2) varying number and order within the set of measurements due to changing satellite visibility, and 3) overfitting to available data. In this work, we address the aforementioned challenges and propose an approach for GNSS positioning by applying DNN-based corrections to an initial position guess. Our DNN learns to output the position correction using the set of pseudorange residuals and satellite line-of-sight vectors as inputs. The limited variation in these input and output values improves the numerical conditioning for our DNN. We design our DNN architecture to combine information from the available GNSS measurements, which vary both in number and order, by leveraging recent advancements in set-based deep learning methods. Furthermore, we present a data augmentation strategy for reducing overfitting in the DNN by randomizing the initial position guesses. We first perform simulations and show an improvement in the initial positioning error when our DNN-based corrections are applied. After this, we demonstrate that our approach outperforms a WLS baseline on real-world data. Our implementation is available at github.com/Stanford-NavLab/deep_gnss.

机器翻译，仅供参考