机器人相关学术速递[6.22]

访问www.arxivdaily.com获取含摘要速递，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏、发帖等功能！点击阅读原文即可访问

cs.RO机器人相关，共计17篇

【1】 Attention-based Neural Network for Driving Environment Complexity Perception 标题：基于注意力的神经网络在驾驶环境复杂性感知中的应用

作者：Ce Zhang,Azim Eskandarian,Xuelai Du 机构：He is a Ph.D. student at Virginia Tech Autonomous Systems and Intelligent, Machines (ASIM) Lab., predicts the affordance for driving actions (vehicle angle 备注：Accepted by 2021 IEEE Intelligent Transportation Systems Conference 链接：https://arxiv.org/abs/2106.11277 摘要：环境感知对自动驾驶汽车（AV）的安全至关重要。现有的AV感知算法大多没有研究周围环境的复杂度，没有考虑环境复杂度参数。提出了一种新的基于注意的神经网络模型来预测周围驾驶环境的复杂程度。该模型以自然驾驶视频和相应的车辆动力学参数作为输入。它由一个Yolo-v3目标检测算法、一个热图生成算法、基于CNN的特征提取器和基于注意力的特征提取器组成，用于视频和时间序列车辆动力学数据输入以提取特征。该算法的输出是一个环境复杂度参数。利用Berkeley-DeepDrive数据集（BDD数据集）和主观标注的环境复杂度水平对算法进行模型训练和验证。提出的基于注意的网络对周围环境的复杂度进行分类，平均分类准确率达到91.22%。结果表明，该算法能够准确地预测环境复杂度水平，并可用于未来AVs的环境感知研究。 摘要：Environment perception is crucial for autonomous vehicle (AV) safety. Most existing AV perception algorithms have not studied the surrounding environment complexity and failed to include the environment complexity parameter. This paper proposes a novel attention-based neural network model to predict the complexity level of the surrounding driving environment. The proposed model takes naturalistic driving videos and corresponding vehicle dynamics parameters as input. It consists of a Yolo-v3 object detection algorithm, a heat map generation algorithm, CNN-based feature extractors, and attention-based feature extractors for both video and time-series vehicle dynamics data inputs to extract features. The output from the proposed algorithm is a surrounding environment complexity parameter. The Berkeley DeepDrive dataset (BDD Dataset) and subjectively labeled surrounding environment complexity levels are used for model training and validation to evaluate the algorithm. The proposed attention-based network achieves 91.22% average classification accuracy to classify the surrounding environment complexity. It proves that the environment complexity level can be accurately predicted and applied for future AVs' environment perception studies.

【2】 PHYSFRAME: Type Checking Physical Frames of Reference for Robotic Systems 标题：PHYSFRAME：机器人系统的类型检查物理参照系

作者：Sayali Kate,Michael Chinn,Hongjun Choi,Xiangyu Zhang,Sebastian Elbaum 机构：Purdue University, USA, University of Virginia 链接：https://arxiv.org/abs/2106.11266 摘要：机器人系统在操作过程中不断地测量自身的运动和外部世界。这种测量是关于某个参考系，即坐标系。一个非平凡的机器人系统有大量不同的帧，数据必须从一帧到另一帧来回转换。开发人员有责任正确地进行翻译。然而，这是非常具有挑战性和容易出错的，开发者论坛上大量与框架使用相关的问题和问题就证明了这一点。由于任何状态变量都可以与某个框架相关联，所以参考框架可以自然地建模为变量类型。因此，我们开发了一个新的类型系统，可以自动推断变量的框架类型，进而检测任何类型的不一致性和违反框架约定的情况。对一组180个公开的ROS项目的评估表明，我们的系统可以检测到190个不一致，154个真阳性。我们向开发人员报告了52份，到目前为止收到了18份回复，其中15份已修复/确认。我们的技术还发现了45种违反常规的行为。 摘要：A robotic system continuously measures its own motions and the external world during operation. Such measurements are with respect to some frame of reference, i.e., a coordinate system. A nontrivial robotic system has a large number of different frames and data have to be translated back-and-forth from a frame to another. The onus is on the developers to get such translation right. However, this is very challenging and error-prone, evidenced by the large number of questions and issues related to frame uses on developers' forum. Since any state variable can be associated with some frame, reference frames can be naturally modeled as variable types. We hence develop a novel type system that can automatically infer variables' frame types and in turn detect any type inconsistencies and violations of frame conventions. The evaluation on a set of 180 publicly available ROS projects shows that our system can detect 190 inconsistencies with 154 true positives. We reported 52 to developers and received 18 responses so far, with 15 fixed/acknowledged. Our technique also finds 45 violations of common practices.

【3】 Domain and Modality Gaps for LiDAR-based Person Detection on Mobile Robots 标题：基于LiDAR的移动机器人人物检测的域和模态间隙

作者：Dan Jia,Alexander Hermans,Bastian Leibe 机构：Visual Computing Institute, RWTH Aachen 链接：https://arxiv.org/abs/2106.11239 摘要：人体检测是移动机器人在人类居住环境中导航的一项重要任务，而激光雷达传感器由于具有精确的深度测量和大视场的特点，在这项任务中具有广阔的应用前景。本文研究了现有的基于LiDAR的人探测器，特别关注移动机器人场景（如服务机器人或社交机器人），与驾驶场景相比，在移动机器人场景中，人被观察的频率更高，距离更近。我们使用最近发布的JackRabbot数据集和基于3D或2D激光雷达传感器（CenterPoint和DR-SPAAM）的最新探测器进行了一系列实验。这些实验围绕驾驶和移动机器人场景之间的领域差距，以及三维和二维激光雷达传感器之间的模态差距展开。对于领域差距，我们的目的是了解在驱动数据集上预训练的检测器是否能在移动机器人场景中获得良好的性能，目前还没有现成的训练模型。对于模态间隙，我们从性能、运行时间、定位精度、对距离和拥挤度的鲁棒性等多个方面对使用3D或2D激光雷达的探测器进行了比较。我们的实验结果为基于激光雷达的人体检测提供了实用的见解，并为相关的移动机器人设计和应用提供了明智的决策。 摘要：Person detection is a crucial task for mobile robots navigating in human-populated environments and LiDAR sensors are promising for this task, given their accurate depth measurements and large field of view. This paper studies existing LiDAR-based person detectors with a particular focus on mobile robot scenarios (e.g. service robot or social robot), where persons are observed more frequently and in much closer ranges, compared to the driving scenarios. We conduct a series of experiments, using the recently released JackRabbot dataset and the state-of-the-art detectors based on 3D or 2D LiDAR sensors (CenterPoint and DR-SPAAM respectively). These experiments revolve around the domain gap between driving and mobile robot scenarios, as well as the modality gap between 3D and 2D LiDAR sensors. For the domain gap, we aim to understand if detectors pretrained on driving datasets can achieve good performance on the mobile robot scenarios, for which there are currently no trained models readily available. For the modality gap, we compare detectors that use 3D or 2D LiDAR, from various aspects, including performance, runtime, localization accuracy, robustness to range and crowdedness. The results from our experiments provide practical insights into LiDAR-based person detection and facilitate informed decisions for relevant mobile robot designs and applications.

【4】 Come back when you are charged! Self-Organized Charging for Electric Vehicles 标题：充电后再来吧！电动汽车的自组织充电

作者：Benjamin Leiding 机构：Clausthal University of Technology, Institute for Software and Systems Engineering, Clausthal-Zellerfeld, Germany 链接：https://arxiv.org/abs/2106.11025 摘要：不断减少的不可再生燃料储备、日益严重的环境污染和加速的气候变化要求社会重新评估现有的运输概念。随着电动汽车的普及和普及，相应的电池充电设施仍然限制了电动汽车在日常生活中的应用。这对于那些没有选择权在其场所操作充电硬件（如墙盒）的电动汽车车主来说尤其如此。在家里没有壁挂盒的情况下给电动汽车充电是很费时的，因为车主必须开车去充电，在附近等候时给车辆充电，最后开车回家。因此，需要一个方便易用的解决方案来克服这一问题，并激励日常通勤者使用电动汽车。因此，我们建议为（半）自主电动汽车提供一个生态系统和一个服务平台，允许他们利用自己的“空闲”时间，例如在夜间，访问公共和私人充电基础设施，为电池充电，并在车主再次需要汽车之前回家。为此，我们利用机器对一切经济（M2X经济）的概念，为智能机器勾勒出一个分散的生态系统，通过基于区块链的智能合约进行交易、交互和协作，为（半）自主电动汽车提供一个方便的电池充电市场。 摘要：Dwindling nonrenewable fuel reserves, progressing severe environmental pollution, and accelerating climate change require society to reevaluate existing transportation concepts. While electric vehicles (EVs) have become more popular and slowly gain widespread adoption, the corresponding battery charging infrastructures still limits EVs' use in our everyday life. This is especially true for EV owners that do not have the option to operate charging hardware, such as wall boxes, at their premises. Charging an EV without an at-home wall box is time-consuming since the owner has to drive to the charger, charge the vehicle while waiting nearby, and finally drive back home. Thus, a convenient and easy-to-use solution is required to overcome the issue and incentivize EVs for daily commuters. Therefore, we propose an ecosystem and a service platform for (semi-)autonomous electric vehicles that allow them to utilize their "free"-time, e.g., at night, to access public and private charging infrastructure, charge their batteries, and get back home before the owner needs the car again. To do so, we utilize the concept of the Machine-to-Everything Economy (M2X Economy) and outline a decentralized ecosystem for smart machines that transact, interact and collaborate via blockchain-based smart contracts to enable a convenient battery charging marketplace for (semi-)autonomous EVs.

【5】 Towards a Framework for Changing-Contact Robot Manipulation 标题：一种变接触机器人操作框架的研究

作者：Saif Sidhik,Mohan Sridharan,Dirk Ruiken 机构： Intelligent Robotics Lab, School of Computer Science, University of Birmingham, UK, Honda Research Institute Europe GmbH, Offenbach am Main, Germany 备注：Submitted to "Autonomous Robots and Multirobot Systems (ARMS) Workshop" at 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021 链接：https://arxiv.org/abs/2106.10969 摘要：许多机器人操作任务都要求机器人与物体和物体表面进行接触和断开接触。当接触发生或断开时，这种变接触机器人操作任务的动力学是不连续的，而在其他地方是连续的。这些不连续性使得很难为任何此类任务构建和使用单一的动力学模型或控制策略。我们提出了一个框架，平滑动力学和控制这种不断变化的接触操纵任务。对于任何给定的目标运动轨迹，该框架逐步改进了对何时发生接触的预测。这一预测和一个将进近速度与撞击力相关联的模型修改了运动序列的速度剖面，使其平滑，并有助于获得所需的撞击力。我们实现这个框架，建立在我们的混合力运动可变阻抗控制器的连续接触任务。我们实验评估了我们的框架在滑动任务的说明性上下文中涉及多种接触变化和不同性质的表面之间的转换。 摘要：Many robot manipulation tasks require the robot to make and break contact with objects and surfaces. The dynamics of such changing-contact robot manipulation tasks are discontinuous when contact is made or broken, and continuous elsewhere. These discontinuities make it difficult to construct and use a single dynamics model or control strategy for any such task. We present a framework for smooth dynamics and control of such changing-contact manipulation tasks. For any given target motion trajectory, the framework incrementally improves its prediction of when contacts will occur. This prediction and a model relating approach velocity to impact force modify the velocity profile of the motion sequence such that it is $C^\infty$ smooth, and help achieve a desired force on impact. We implement this framework by building on our hybrid force-motion variable impedance controller for continuous contact tasks. We experimentally evaluate our framework in the illustrative context of sliding tasks involving multiple contact changes with transitions between surfaces of different properties.

【6】 Investigating the role of educational robotics in formal mathematics education: the case of geometry for 15-year-old students 标题：探讨教育机器人在正规数学教育中的作用：以15岁学生几何为例

作者：Jérôme Brender,Laila El-Hamamsy,Barbara Bruno,Frédérique Chessel-Lazzarotto,Jessica Dehler Zufferey,Francesco Mondada 机构：Bruno,[,−,−,−,], Fr´ed´erique Chessel-Lazzarotto, Jessica Dehler, Center LEARN, Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Switzerland, Mobots Group, Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Switzerland 备注：To appear in the proceedings of the Sixteenth European Conference on Technology Enhanced Learning (2021) 链接：https://arxiv.org/abs/2106.10925 摘要：研究表明，教育机器人（ER）可以提高学生的学习成绩、兴趣、参与度和协作能力。然而，到目前为止，机器人技术在正规教育中的应用还相对较少。除其他原因外，这是由于难以确定教育机器人学习活动与课程所设想的学习成果的一致性，以及它们与教师实践中确立的传统非机器人学习活动的整合。这项工作通过一项准实验研究，采用Thymio机器人和Scratch编程，对两个15岁的学生进行几何教学，共26名参与者，探讨了ER与正规数学教育的整合。本研究提出了三个研究问题：（1）基于内质网的理论讲座应该先于、继承还是取代传统的理论讲座(2） 学生对基于ER的讲座和练习有何看法和参与度(3） 根据学生先前对数学的欣赏程度，研究结果是否有所不同？结果表明，在帮助学生掌握相关理论概念方面，ER活动与传统活动一样有效。在练习课上，机器人活动似乎特别有益：学生们自由选择做包括机器人在内的练习，认为机器人比传统的机器人更有趣、更有用，并表示有兴趣在其他数学课程中引入ER。最后，喜欢和不喜欢数学的学生之间的结果基本一致，表明使用机器人作为一种手段来扩大从事这一学科的学生数量。 摘要：Research has shown that Educational Robotics (ER) enhances student performance, interest, engagement and collaboration. However, until now, the adoption of robotics in formal education has remained relatively scarce. Among other causes, this is due to the difficulty of determining the alignment of educational robotic learning activities with the learning outcomes envisioned by the curriculum, as well as their integration with traditional, non-robotics learning activities that are well established in teachers' practices. This work investigates the integration of ER into formal mathematics education, through a quasi-experimental study employing the Thymio robot and Scratch programming to teach geometry to two classes of 15-year-old students, for a total of 26 participants. Three research questions were addressed: (1) Should an ER-based theoretical lecture precede, succeed or replace a traditional theoretical lecture? (2) What is the students' perception of and engagement in the ER-based lecture and exercises? (3) Do the findings differ according to students' prior appreciation of mathematics? The results suggest that ER activities are as valid as traditional ones in helping students grasp the relevant theoretical concepts. Robotics activities seem particularly beneficial during exercise sessions: students freely chose to do exercises that included the robot, rated them as significantly more interesting and useful than their traditional counterparts, and expressed their interest in introducing ER in other mathematics lectures. Finally, results were generally consistent between the students that like and did not like mathematics, suggesting the use of robotics as a means to broaden the number of students engaged in the discipline.

【7】 On the Importance of Environments in Human-Robot Coordination 标题：论环境在人-机器人协调中的重要性

作者：Matthew C. Fontaine,Ya-Chuan Hsu,Yulun Zhang,Bryon Tjakana,Stefanos Nikolaidis 机构：Department of Computer Science, University of Southern California, Los Angeles, CA, USA 备注：Accepted to Robotics: Science and Systems (RSS) 2021 链接：https://arxiv.org/abs/2106.10853 摘要：当研究机器人与人类协作时，大部分的焦点都集中在机器人策略上，这些策略能够在协作任务中与人类的队友进行流畅的协调。然而，人们很少关注环境对协调行为的影响。为了深入研究导致不同行为的环境，我们提出了一个程序生成环境的框架，这些环境（1）在风格上类似于人类编写的环境，（2）保证人类机器人团队可以解决，（3）在协调措施方面不同。我们通过模拟和在线用户研究，分析了在超调基准域中程序生成的环境。结果表明，即使机器人运行相同的规划算法，环境也会导致不同的涌现行为，并且在协作流畅性指标上存在显著的统计差异。 摘要：When studying robots collaborating with humans, much of the focus has been on robot policies that coordinate fluently with human teammates in collaborative tasks. However, less emphasis has been placed on the effect of the environment on coordination behaviors. To thoroughly explore environments that result in diverse behaviors, we propose a framework for procedural generation of environments that are (1) stylistically similar to human-authored environments, (2) guaranteed to be solvable by the human-robot team, and (3) diverse with respect to coordination measures. We analyze the procedurally generated environments in the Overcooked benchmark domain via simulation and an online user study. Results show that the environments result in qualitatively different emerging behaviors and statistically significant differences in collaborative fluency metrics, even when the robot runs the same planning algorithm.

【8】 Guiding vector fields in Paparazzi autopilot 标题：狗仔队自动驾驶仪中的引导向量场

作者：Hector Garcia de Marina,Murat Bronz,Gautier Hattenberger 机构：Universidad Complutense de Madrid, Madrid, Spain, ´Ecole National de l’Aviation Civile, Toulouse, France 备注：Submitted to IMAV 2021, 5 pages 链接：https://arxiv.org/abs/2106.10680 摘要：这篇文章是一篇关于两种不同的基于向量场的制导系统的技术报告，这两种制导系统可以在Paparazzi中找到，Paparazzi是一种免费的sw/hw自动驾驶仪。引导向量场允许自主车辆跟踪用户数学描述的路径。特别地，我们允许使用隐式函数或参数函数对路径进行两种描述。每个描述都与其对应的引导向量场算法相关联。这两种算法的实现很轻，可以在现代微控制器中运行。我们将介绍它们如何工作的基本理论，用户如何在狗仔队中实现自己的路径，如何利用它们来协调多个车辆，并给出一些实验结果。虽然所提出的方法主要针对固定翼飞机，但该制导方法也适用于旋翼机等其他类型的飞行器。 摘要：This article is a technical report on the two different guidance systems based on vector fields that can be found in Paparazzi, a free sw/hw autopilot. Guiding vector fields allow autonomous vehicles to track paths described by the user mathematically. In particular, we allow two descriptions of the path with an implicit or a parametric function. Each description is associated with its corresponding guiding vector field algorithm. The implementations of the two algorithms are light enough to be run in a modern microcontroller. We will cover the basic theory on how they work, how a user can implement its own paths in Paparazzi, how to exploit them to coordinate multiple vehicles, and we finish with some experimental results. Although the presented implementation is focused on fixed-wing aircraft, the guidance is also applicable to other kinds of aerial vehicles such as rotorcraft.

【9】 Image-guided Breast Biopsy of MRI-visible Lesions with a Hand-mounted Motorised Needle Steering Tool 标题：用手持电动导针工具进行MRI可见病变的影像引导乳腺活检

作者：Marta Lagomarsino,Vincent Groenhuis,Maura Casadio,Marcel K. Welleweerd,Francoise J. Siepel,Stefano Stramigioli 机构： University of Genoa 备注：Submitted to 2021 International Symposium on Medical Robotics (ISMR) 链接：https://arxiv.org/abs/2106.10672 摘要：活检是唯一的诊断程序，准确的组织学确认乳腺癌。当超声定位是不可行的，磁共振成像（MRI）引导活检往往是首选。由于缺乏实时成像信息和乳房的变形，使得在介入前磁共振（MR）图像中精确地将针头对准检测到的肿瘤非常困难。目前的手动磁共振引导活检工作流程是不准确的，并将受益于一项技术，允许实时跟踪和定位的肿瘤病变在针插入。本文提出了一个机器人的设置和软件架构，以协助放射科在定位磁共振检测可疑肿瘤。该方法得益于术前图像的图像融合和术中附着在患者皮肤上的标记物的光学跟踪。手持式活组织检查装置由一个驱动针座构成，以驱动针尖朝向所需的方向。转向指令可由用户输入和计算机引导提供。通过虚拟实验验证了该工作流程。平均而言，可疑乳腺病变的靶点半径小于2.3毫米。结果表明，考虑乳房变形的机器人系统有潜力应对这一临床挑战。 摘要：A biopsy is the only diagnostic procedure for accurate histological confirmation of breast cancer. When sonographic placement is not feasible, a Magnetic Resonance Imaging(MRI)-guided biopsy is often preferred. The lack of real-time imaging information and the deformations of the breast make it challenging to bring the needle precisely towards the tumour detected in pre-interventional Magnetic Resonance (MR) images. The current manual MRI-guided biopsy workflow is inaccurate and would benefit from a technique that allows real-time tracking and localisation of the tumour lesion during needle insertion. This paper proposes a robotic setup and software architecture to assist the radiologist in targeting MR-detected suspicious tumours. The approach benefits from image fusion of preoperative images with intraoperative optical tracking of markers attached to the patient's skin. A hand-mounted biopsy device has been constructed with an actuated needle base to drive the tip toward the desired direction. The steering commands may be provided both by user input and by computer guidance. The workflow is validated through phantom experiments. On average, the suspicious breast lesion is targeted with a radius down to 2.3 mm. The results suggest that robotic systems taking into account breast deformations have the potentials to tackle this clinical challenge.

【10】 HapFIC: An Adaptive Force/Position Controller for Safe Environment Interaction in Articulated Systems 标题：HapFIC：一种用于铰接系统安全环境交互的力/位置自适应控制器

作者：Carlo Tiseo,Wolfgang Merkt,Keyhan Kouhkiloui Babarahmati,Wouter Wolfslag,Ioannis Havoutis,Sethu Vijayakumar,Michael Mistry 机构： Sethu Vi-jayakumar and Michael Mistry are with the School of Informatics, Wolfgang Merkt and Ioannis Havoutis are with theOxford Robotics Institute, University of Oxford 链接：https://arxiv.org/abs/2106.10648 摘要：触觉相互作用对于动物的动态灵巧性是必不可少的，动物通过本体感觉的力反馈，从阻抗行为无缝切换到导纳行为。然而，这种能力在机器人中的复制是非常具有挑战性的，特别是在处理复杂的交互动力学、分布式接触和接触开关时。当前基于模型的控制器需要精确的交互建模来考虑接触和稳定交互。在本文中，我们提出了一种自适应力/位置控制器，利用分形阻抗控制器的无源性和非线性，利用末端执行器传感器的力反馈信号执行有限搜索算法。该方法计算量小，为将来处理分布式接触问题提供了可能。我们在物理模拟中评估了该结构，并且表明该控制器能够在不违反最大允许目标力或即使对于非常刚性的物体也不会引起数值不稳定性的情况下，鲁棒地控制与不同动力学物体的相互作用。所提出的控制器还可以自主地处理触点切换，可以应用于腿部运动、康复和辅助机器人等多个领域。 摘要：Haptic interaction is essential for the dynamic dexterity of animals, which seamlessly switch from an impedance to an admittance behaviour using the force feedback from their proprioception. However, this ability is extremely challenging to reproduce in robots, especially when dealing with complex interaction dynamics, distributed contacts, and contact switching. Current model-based controllers require accurate interaction modelling to account for contacts and stabilise the interaction. In this manuscript, we propose an adaptive force/position controller that exploits the fractal impedance controller's passivity and non-linearity to execute a finite search algorithm using the force feedback signal from the sensor at the end-effector. The method is computationally inexpensive, opening the possibility to deal with distributed contacts in the future. We evaluated the architecture in physics simulation and showed that the controller can robustly control the interaction with objects of different dynamics without violating the maximum allowable target forces or causing numerical instability even for very rigid objects. The proposed controller can also autonomously deal with contact switching and may find application in multiple fields such as legged locomotion, rehabilitation and assistive robotics.

【11】 Learning Space Partitions for Path Planning 标题：用于路径规划的学习空间划分

作者：Kevin Yang,Tianjun Zhang,Chris Cummins,Brandon Cui,Benoit Steiner,Linnan Wang,Joseph E. Gonzalez,Dan Klein,Yuandong Tian 备注：Under submission to NeurIPS 2021 链接：https://arxiv.org/abs/2106.10544 摘要：路径规划是一个有效地发现高报酬轨迹的问题，通常需要优化高维多模态报酬函数。像CEM和CMA-ES这样的流行方法贪婪地关注搜索空间中有前途的区域，并且可能陷入局部极大值。DOO和VOOT平衡探索和开发，但使用独立于奖励函数的空间划分策略进行优化。最近，LaMCTS在经验上学会了以奖励敏感的方式划分搜索空间进行黑盒优化。在本文中，我们发展了一种新的形式遗憾分析，以确定这种自适应区域划分方案何时以及为什么有效。我们还提出了一种新的路径规划方法PlaLaM，它改进了每个子区域内的函数值估计，并使用了搜索空间的潜在表示。根据经验，PlaLaM在二维导航任务中的性能优于现有的路径规划方法，特别是在存在难以逃逸的局部最优解的情况下，并且当插入带有规划组件（如PETS）的基于模型的RL时显示出优势。这些增益转移到高度多模态的现实世界任务中，在编译器相位排序方面，我们的性能比强基线高出245%，在分子设计方面，我们的性能比强基线高出0.4，在0-1的范围内。 摘要：Path planning, the problem of efficiently discovering high-reward trajectories, often requires optimizing a high-dimensional and multimodal reward function. Popular approaches like CEM and CMA-ES greedily focus on promising regions of the search space and may get trapped in local maxima. DOO and VOOT balance exploration and exploitation, but use space partitioning strategies independent of the reward function to be optimized. Recently, LaMCTS empirically learns to partition the search space in a reward-sensitive manner for black-box optimization. In this paper, we develop a novel formal regret analysis for when and why such an adaptive region partitioning scheme works. We also propose a new path planning method PlaLaM which improves the function value estimation within each sub-region, and uses a latent representation of the search space. Empirically, PlaLaM outperforms existing path planning methods in 2D navigation tasks, especially in the presence of difficult-to-escape local optima, and shows benefits when plugged into model-based RL with planning components such as PETS. These gains transfer to highly multimodal real-world tasks, where we outperform strong baselines in compiler phase ordering by up to 245% and in molecular design by up to 0.4 on properties on a 0-1 scale.

【12】 Learning to Reach, Swim, Walk and Fly in One Trial: Data-Driven Control with Scarce Data and Side Information 标题：在一次试验中学会伸手、游泳、步行和飞翔：使用稀缺数据和边际信息的数据驱动控制

作者：Franck Djeumou,Ufuk Topcu 机构：Department of Electrical and Computer Engineering, University of Texas at Austin United States, Department of Aerospace Engineering and Engineering Mechanics 备注：Initial submission to CoRL 2021 链接：https://arxiv.org/abs/2106.10533 摘要：针对数据受限的未知动态系统，提出了一种基于学习的控制算法。具体来说，该算法只能从一次正在进行的试验中访问流数据。尽管缺乏数据，我们通过一系列的例子表明，该算法可以提供与经过数百万次环境交互训练的强化学习算法相当的性能。它通过有效地利用动态中各种形式的边信息来降低样本的复杂性，从而实现这种性能。这些旁白信息通常来自基本物理定律和系统的定性性质。更准确地说，该算法近似地解决了编码系统期望行为的最优控制问题。为此，它构造并细化了一个包含动力学未知向量场的微分包含。差分包含，在区间泰勒方法中使用，使系统可能达到的状态集过于近似。理论上，我们建立了一个关于已知动力学情况下近似解的次优性的界。我们证明，试验时间越长或有更多的辅助信息可用，界限就越紧。在高保真F-16飞机模拟器和MuJoCo的环境（如Reacher、swimper和Cheetah）上的实验表明了该算法的有效性。 摘要：We develop a learning-based control algorithm for unknown dynamical systems under very severe data limitations. Specifically, the algorithm has access to streaming data only from a single and ongoing trial. Despite the scarcity of data, we show -- through a series of examples -- that the algorithm can provide performance comparable to reinforcement learning algorithms trained over millions of environment interactions. It accomplishes such performance by effectively leveraging various forms of side information on the dynamics to reduce the sample complexity. Such side information typically comes from elementary laws of physics and qualitative properties of the system. More precisely, the algorithm approximately solves an optimal control problem encoding the system's desired behavior. To this end, it constructs and refines a differential inclusion that contains the unknown vector field of the dynamics. The differential inclusion, used in an interval Taylor-based method, enables to over-approximate the set of states the system may reach. Theoretically, we establish a bound on the suboptimality of the approximate solution with respect to the case of known dynamics. We show that the longer the trial or the more side information is available, the tighter the bound. Empirically, experiments in a high-fidelity F-16 aircraft simulator and MuJoCo's environments such as the Reacher, Swimmer, and Cheetah illustrate the algorithm's effectiveness.

【13】 Grasping Benchmarks: Normalizing for Object Size \& Approximating Hand Workspaces

作者：John Morrow,Nuha Nishat,Joshua Campbell,Ravi Balasubramanian,Cindy Grimm 机构：grimm atOregon State University 备注：Submitted to IROS 2021, waiting for response 链接：https://arxiv.org/abs/2106.10402 摘要：机器人手设计的多样性使得如何测量手的大小和传达它能抓住的物体的大小的标准变得困难。定义一致的工作空间测量将大大有助于机器人抓取研究中的科学交流，因为它将允许研究人员1）定量地交流对象与手的相对大小，2）以人类可读的方式近似手的运动工作空间的功能子空间。本文的目的是指定一个测量程序，定量捕捉手的工作空间大小的精度和权力掌握。这个测量过程使用{\em functional}方法——基于一个假想物体的一般抓取场景——以便使该过程尽可能具有普遍性和可重复性，而不考虑实际的手部设计。这种功能方法允许测量者选择满足一般抓取场景的精确手指配置和接触点，同时确保测量结果在功能上具有可比性。我们在七只手的配置上演示了这些功能测量。GitHub存储库中提供了额外的手测量和说明。 摘要：The varied landscape of robotic hand designs makes it difficult to set a standard for how to measure hand size and to communicate the size of objects it can grasp. Defining consistent workspace measurements would greatly assist scientific communication in robotic grasping research because it would allow researchers to 1) quantitatively communicate an object's relative size to a hand's and 2) approximate a functional subspace of a hand's kinematic workspace in a human-readable way. The goal of this paper is to specify a measurement procedure that quantitatively captures a hand's workspace size for both a precision and power grasp. This measurement procedure uses a {\em functional} approach -- based on a generic grasping scenario of a hypothetical object -- in order to make the procedure as generalizable and repeatable as possible, regardless of the actual hand design. This functional approach lets the measurer choose the exact finger configurations and contact points that satisfy the generic grasping scenario, while ensuring that the measurements are {\em functionally} comparable. We demonstrate these functional measurements on seven hand configurations. Additional hand measurements and instructions are provided in a GitHub Repository.

【14】 High-level Features for Resource Economy and Fast Learning in Skill Transfer 标题：资源节约型和技能转移学习快速性的高层次特征

作者：Alper Ahmetoglu,Emre Ugur,Minoru Asada,Erhan Oztop 机构：Department of Computer Engineering, Bogazici University, Turkey, OTRISISREC, Osaka University, Osaka, Japan, Department of Computer Science, Ozyegin University, Turkey, (Received , Month ,X; accepted , Month ,X) 链接：https://arxiv.org/abs/2106.10354 摘要：抽象是智能的一个重要方面，它使智能体能够构造有效决策的健壮表示。在过去的十年中，深度网络被证明是有效的，因为它们能够形成越来越复杂的抽象。然而，这些抽象分布在许多神经元上，使得重复使用所学技能的代价高昂。以前的工作要么强制形成抽象，造成设计师的偏见，要么使用大量的神经单元，而没有研究如何获得更有效地捕获源任务的高级特征。为了避免设计师的偏见和不共享的资源使用，我们建议利用神经反应动力学形成紧凑的表达，用于技能转移。为此，我们考虑了基于（1）最大信息压缩原理和（2）抽象事件倾向于产生缓慢变化的信号的概念的两种竞争方法，并将它们应用于任务执行过程中产生的神经信号。具体地说，在我们的模拟实验中，我们对深度网络执行源任务时从最后一个隐藏层采集的信号进行主成分分析（PCA）或慢特征分析（SFA），并在新的目标任务中使用这些特征进行技能转移。我们比较了这些方案的泛化性能与基线的技能转移与全层输出和无转移设置。我们的结果表明，SFA单位是最成功的技能转移。与通常的技能转移相比，SFA和PCA产生的资源更少，由此形成的许多单位显示出反映末端效应器-障碍-目标关系的局部反应。最后，具有最低特征值的SFA单元类似于与高级特征高度相关的符号表示，例如可以被认为是完全符号系统的前兆的关节角。 摘要：Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are proven to be effective due to their ability to form increasingly complex abstractions. However, these abstractions are distributed over many neurons, making the re-use of a learned skill costly. Previous work either enforced formation of abstractions creating a designer bias, or used a large number of neural units without investigating how to obtain high-level features that may more effectively capture the source task. For avoiding designer bias and unsparing resource use, we propose to exploit neural response dynamics to form compact representations to use in skill transfer. For this, we consider two competing methods based on (1) maximum information compression principle and (2) the notion that abstract events tend to generate slowly changing signals, and apply them to the neural signals generated during task execution. To be concrete, in our simulation experiments, we either apply principal component analysis (PCA) or slow feature analysis (SFA) on the signals collected from the last hidden layer of a deep network while it performs a source task, and use these features for skill transfer in a new target task. We compare the generalization performance of these alternatives with the baselines of skill transfer with full layer output and no-transfer settings. Our results show that SFA units are the most successful for skill transfer. SFA as well as PCA, incur less resources compared to usual skill transfer, whereby many units formed show a localized response reflecting end-effector-obstacle-goal relations. Finally, SFA units with lowest eigenvalues resembles symbolic representations that highly correlate with high-level features such as joint angles which might be thought of precursors for fully symbolic systems.

【15】 Exoskeleton-Based Multimodal Action and Movement Recognition: Identifying and Developing the Optimal Boosted Learning Approach 标题：基于外骨骼的多模态动作和动作识别：识别和开发最佳增强学习方法

作者：Nirmalya Thakur,Chia Y. Han 机构： Han 2 1 Department of Electrical Engineering and Computer Science, University of Cincinnati, 2 Department of Electrical Engineering and Computer Science 备注：None 链接：https://arxiv.org/abs/2106.10331 摘要：本文在基于外骨骼的动作和运动识别领域做出了两项科学贡献。首先，提出了一种新的基于机器学习和模式识别的框架，该框架能够检测多种行为和动作——行走、上楼行走、下楼行走、坐、站、卧、站坐、站、坐、站、坐、卧、卧、坐、卧、卧、立，总体准确率为82.63%。其次，对随机林、人工神经网络、决策树、多向决策树、支持向量机、k-NN、梯度增强树、决策树桩、自动MLP、线性回归、向量线性回归、随机树、Na-ive Bayes、Na-ive Bayes（核）等不同的学习方法进行了综合比较研究，线性判别分析、二次判别分析和深度学习应用于该框架。采用AdaBoost算法提高了每种学习方法的性能，并采用交叉验证方法进行训练和测试。结果表明，在增强形式下，k-NN分类器的性能优于所有其他增强学习方法，因此是实现这一目的的最佳学习方法。所呈现和讨论的结果支持了这项工作的重要性，有助于在未来基于物联网的生活环境（如智能家居）中增强老年人基于外骨骼的辅助和独立生活能力。作为一个特定的用例，我们还讨论了我们的研究结果如何与增强混合辅助肢体外骨骼（一种功能强大的下肢外骨骼）的功能相关。 摘要：This paper makes two scientific contributions to the field of exoskeleton-based action and movement recognition. First, it presents a novel machine learning and pattern recognition-based framework that can detect a wide range of actions and movements - walking, walking upstairs, walking downstairs, sitting, standing, lying, stand to sit, sit to stand, sit to lie, lie to sit, stand to lie, and lie to stand, with an overall accuracy of 82.63%. Second, it presents a comprehensive comparative study of different learning approaches - Random Forest, Artificial Neural Network, Decision Tree, Multiway Decision Tree, Support Vector Machine, k-NN, Gradient Boosted Trees, Decision Stump, Auto MLP, Linear Regression, Vector Linear Regression, Random Tree, Na\"ive Bayes, Na\"ive Bayes (Kernel), Linear Discriminant Analysis, Quadratic Discriminant Analysis, and Deep Learning applied to this framework. The performance of each of these learning approaches was boosted by using the AdaBoost algorithm, and the Cross Validation approach was used for training and testing. The results show that in boosted form, the k- NN classifier outperforms all the other boosted learning approaches and is, therefore, the optimal learning method for this purpose. The results presented and discussed uphold the importance of this work to contribute towards augmenting the abilities of exoskeleton-based assisted and independent living of the elderly in the future of Internet of Things-based living environments, such as Smart Homes. As a specific use case, we also discuss how the findings of our work are relevant for augmenting the capabilities of the Hybrid Assistive Limb exoskeleton, a highly functional lower limb exoskeleton.

【16】 Sample Efficient Social Navigation Using Inverse Reinforcement Learning 标题：基于逆向强化学习的样本高效社交导航

作者：Bobak H. Baghi,Gregory Dudek 机构： Baghi and 2Gregory Dudek are with the School ofComputer Science, McGill University, 3 480 Rue University 链接：https://arxiv.org/abs/2106.10318 摘要：在本文中，我们提出了一个算法，以有效地学习社会兼容的导航政策，从观察人类的轨迹。当移动机器人开始在社交空间中居住和交通时，它们必须考虑到社交线索，并以一种顺应社会的方式行事。我们专注于从例子中学习这些线索。我们描述了一种基于逆强化学习的算法，该算法在不知道人的具体行为的情况下，从人的轨迹观察中学习。我们通过利用重放缓冲区的概念（在许多非策略强化学习方法中发现）来消除与逆强化学习相关的额外样本复杂性，从而提高了我们方法的样本效率。我们通过使用公开的行人运动数据集训练代理来评估我们的方法，并将其与相关方法进行比较。结果表明，该方法在降低训练时间和样本复杂度的同时，具有更好的性能。 摘要：In this paper, we present an algorithm to efficiently learn socially-compliant navigation policies from observations of human trajectories. As mobile robots come to inhabit and traffic social spaces, they must account for social cues and behave in a socially compliant manner. We focus on learning such cues from examples. We describe an inverse reinforcement learning based algorithm which learns from human trajectory observations without knowing their specific actions. We increase the sample-efficiency of our approach over alternative methods by leveraging the notion of a replay buffer (found in many off-policy reinforcement learning methods) to eliminate the additional sample complexity associated with inverse reinforcement learning. We evaluate our method by training agents using publicly available pedestrian motion data sets and compare it to related methods. We show that our approach yields better performance while also decreasing training time and sample complexity.

【17】 Verifying Safe Transitions between Dynamic Motion Primitives on Legged Robots 标题：验证腿式机器人动态运动基元之间的安全过渡

作者：Wyatt Ubellacker,Noel Csomay-Shanklin,Tamas G. Molnar,Aaron D. Ames 机构：Authors are with the Department of Control and Dynamical Sys-tems and the Department of Mechanical and Civil Engineering, Cal-ifornia Institute of Technology 链接：https://arxiv.org/abs/2106.10310 摘要：功能自治系统通常通过使用由离散的原始行为和这些行为之间的转换组成的状态机来实现复杂的任务。这种体系结构在准静态和动态独立系统中得到了广泛的研究。然而，这一概念在动力系统中的应用相对较少，尽管我们对单个动力学原语行为（我们称之为“运动原语”）进行了广泛的研究。本文在安全的背景下，形式化了一个确定运动原语之间转换的动态感知条件的过程。结果被构造成一个“运动原语图”，可以被标准的图搜索和规划算法遍历以实现功能自治。为了演示这个框架，在四足机器人上通过实验实现了动态运动原语（包括站立、行走和跳跃）以及这些行为之间的转换。 摘要：Functional autonomous systems often realize complex tasks by utilizing state machines comprised of discrete primitive behaviors and transitions between these behaviors. This architecture has been widely studied in the context of quasi-static and dynamics-independent systems. However, applications of this concept to dynamical systems are relatively sparse, despite extensive research on individual dynamic primitive behaviors, which we refer to as "motion primitives." This paper formalizes a process to determine dynamic-state aware conditions for transitions between motion primitives in the context of safety. The result is framed as a "motion primitive graph" that can be traversed by standard graph search and planning algorithms to realize functional autonomy. To demonstrate this framework, dynamic motion primitives -- including standing up, walking, and jumping -- and the transitions between these behaviors are experimentally realized on a quadrupedal robot.