机器人相关学术速递[7.6]

cs.RO机器人相关，共计27篇

【1】 Biomimetic Tactile Receptors for 3d-printed Skin 标题：3D打印皮肤的仿生触觉感受器

作者：Nicholas Pestell,Thom Griffith,Nathan F. Lepora 链接：https://arxiv.org/abs/2107.02084 摘要：为了使机器人的触觉与人类的触觉相融合，人工传导应该包括生物上合理的群体密码，类似于自然传入的密码。利用基于真皮-表皮边界的三维打印皮肤仿生触觉传感器，提出了两种新的特征集来模拟缓慢适应和快速适应I型触觉机械感受器功能。通过自然触感研究中的三个经典实验验证了它们的合理性：平板撞击探测适应性和空间调制；空间复杂脊状刺激探测单个传入反应；以及感知光栅方向来探测群体响应。我们的结果显示，人工和自然的传入反应在对边缘和缝隙的敏感性上是一致的；同样，人类和机器人的心理测量功能与光栅定位相匹配。这些发现有助于机器人操作、假肢和触觉的神经生理学。 摘要：For robot touch to converge with the human sense of touch, artificial transduction should involve biologically-plausible population codes analogous to those of natural afferents. Using a biomimetic tactile sensor with 3d-printed skin based on the dermal-epidermal boundary, we propose two novel feature sets to mimic slowly-adapting and rapidly-adapting type-I tactile mechanoreceptor function. Their plausibility is tested with three classic experiments from the study of natural touch: impingement on a flat plate to probe adaptation and spatial modulation; stimulation by spatially-complex ridged stimuli to probe single afferent responses; and perception of grating orientation to probe the population response. Our results show a match between artificial and natural afferent responses in their sensitivity to edges and gaps; likewise, the human and robot psychometric functions match for grating orientation. These findings could benefit robot manipulation, prosthetics and the neurophysiology of touch.

【2】 SCOD: Active Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences 标题：SCOD：基于动作序列感官交换性的具身智能体活动目标检测

作者：Hugo Caselles-Dupré,Michael Garcia-Ortiz,David Filliat 机构：U,IS, ENSTA Paris, Institut Polytechnique de Paris & INRIA Flowers, CitAI, SMCSE, City University of London 备注：Accepted to AAMAS 2021 (Extended Abstract) 链接：https://arxiv.org/abs/2107.02069 摘要：介绍了一种主动的动、不动目标检测方法SCOD。SCOD利用动作序列的交换特性，在一个具有第一人称传感器和多自由度连续运动空间的具体化代理的场景中。SCOD的基础是从同一起点以两个不同的顺序播放一个动作序列，并比较每个序列之后获得的两个最终观察结果。我们在三维真实感机器人装置（iGibson）上的实验证明了SCOD的准确性及其对未知环境和物体的泛化。我们还成功地将SCOD应用于实际机器人，进一步说明了SCOD的泛化特性。利用SCOD，我们的目标是提供一种新的方法来处理在一个天真的具体化代理的上下文中的对象发现问题。我们提供代码和补充视频。 摘要：We introduce SCOD (Sensory Commutativity Object Detection), an active method for movable and immovable object detection. SCOD exploits the commutative properties of action sequences, in the scenario of an embodied agent equipped with first-person sensors and a continuous motor space with multiple degrees of freedom. SCOD is based on playing an action sequence in two different orders from the same starting point and comparing the two final observations obtained after each sequence. Our experiments on 3D realistic robotic setups (iGibson) demonstrate the accuracy of SCOD and its generalization to unseen environments and objects. We also successfully apply SCOD on a real robot to further illustrate its generalization properties. With SCOD, we aim at providing a novel way of approaching the problem of object discovery in the context of a naive embodied agent. We provide code and a supplementary video.

【3】 Using Probabilistic Movement Primitives in Analyzing Human Motion Difference under Transcranial Current Stimulation 标题：概率运动基元在经颅电流刺激下人体运动差异分析中的应用

作者：Honghu Xue,Rebecca Herzog,Till M Berger,Tobias Bäumer,Anne Weissbach,Elmar Rueckert 机构：Institute for Robotics and Cognitive Systems, Institute of Systems Motor Science, Department of Neurology, University of Luebeck, University Medical Center Schleswig-Holstein, Institute of Systems Motor Science, Institute of Neurogenetics 链接：https://arxiv.org/abs/2107.02063 摘要：在人体运动分析等医学任务中，计算机辅助辅助系统以其高效性成为人类专家的首选。然而，传统方法通常基于用户定义的特征，例如运动开始时间、峰值速度、运动矢量或频域分析。这些方法需要仔细的数据后处理或特定的领域知识来实现有意义的特征提取。此外，它们容易产生噪声，手工定义的特征很难用于其他分析。本文提出了一种广泛应用于机器人技能学习的概率运动原语（ProMPs）模型。ProMPs的优点是可以直接从数据中学习特征，并且可以捕获描述轨迹形状的重要特征，可以很容易地扩展到其他任务。不同于以往的研究，分类任务主要是研究，我们应用ProMPs和Kullback-Leibler（KL）发散变量来量化不同经颅电流刺激方法对人体运动的影响。我们向10名参与者展示了初步结果。结果验证了ProMPs是一种鲁棒有效的人体运动特征提取工具。 摘要：In medical tasks such as human motion analysis, computer-aided auxiliary systems have become preferred choice for human experts for its high efficiency. However, conventional approaches are typically based on user-defined features such as movement onset times, peak velocities, motion vectors or frequency domain analyses. Such approaches entail careful data post-processing or specific domain knowledge to achieve a meaningful feature extraction. Besides, they are prone to noise and the manual-defined features could hardly be re-used for other analyses. In this paper, we proposed probabilistic movement primitives (ProMPs), a widely-used approach in robot skill learning, to model human motions. The benefit of ProMPs is that the features are directly learned from the data and ProMPs can capture important features describing the trajectory shape, which can easily be extended to other tasks. Distinct from previous research, where classification tasks are mostly investigated, we applied ProMPs together with a variant of Kullback-Leibler (KL) divergence to quantify the effect of different transcranial current stimulation methods on human motions. We presented an initial result with 10 participants. The results validate ProMPs as a robust and effective feature extractor for human motions.

【4】 6D Object Pose Estimation using Keypoints and Part Affinity Fields 标题：基于关键点和局部亲和场的六维物体位姿估计

作者：Moritz Zappel,Simon Bultmann,Sven Behnke 机构：Autonomous Intelligent Systems, Computer Science Institute VI, University of Bonn, Germany 备注：None 链接：https://arxiv.org/abs/2107.02057 摘要：基于RGB图像的6D目标姿态估计是自主服务机器人与现实世界交互的重要要求。在这项工作中，我们提出了一个两步流水线来估计已知物体的6自由度平移和方向。基于人体姿态估计，采用OpenPose-CNN结构，从输入图像中预测关键点和部分亲和场。然后通过PnP-RANSAC算法从检测到的关键点和模型关键点之间的2D-3D对应关系计算目标姿态。所提出的方法在YCB视频数据集上进行评估，并与文献中的最近的方法相一致，达到了精度。使用PAFs将检测到的关键点组装到对象实例中证明比仅使用热图更有优势。为预测单个对象类的关键点而训练的模型要比为几个类训练的模型表现得好得多。 摘要：The task of 6D object pose estimation from RGB images is an important requirement for autonomous service robots to be able to interact with the real world. In this work, we present a two-step pipeline for estimating the 6 DoF translation and orientation of known objects. Keypoints and Part Affinity Fields (PAFs) are predicted from the input image adopting the OpenPose CNN architecture from human pose estimation. Object poses are then calculated from 2D-3D correspondences between detected and model keypoints via the PnP-RANSAC algorithm. The proposed approach is evaluated on the YCB-Video dataset and achieves accuracy on par with recent methods from the literature. Using PAFs to assemble detected keypoints into object instances proves advantageous over only using heatmaps. Models trained to predict keypoints of a single object class perform significantly better than models trained for several classes.

【5】 Here's What I've Learned: Asking Questions that Reveal Reward Learning 标题：这就是我所学到的：提出能揭示奖励学习的问题

作者：Soheil Habibian,Ananth Jonnavittula,Dylan P. Losey 机构： Department of Mechanical Engineering 链接：https://arxiv.org/abs/2107.01995 摘要：机器人可以通过提问向人类学习。在这些问题中，机器人展示了几种不同的行为，并询问人类最喜欢的行为。但是机器人应该如何选择要问的问题呢？今天的机器人优化信息的问题，积极探索人类的喜好尽可能有效。但是，尽管从机器人的角度来看，信息丰富的问题是有意义的，但人类旁观者往往发现这些问题武断且具有误导性。本文从人的角度对基于偏好的主动学习进行了形式化描述。我们假设——从人类的角度来看——机器人的问题揭示了机器人有什么和没有学什么。我们的洞察力使机器人能够使用问题，使他们的学习过程对人类操作员透明。我们开发并测试了一个模型，机器人可以利用这个模型将他们提出的问题与这些问题所揭示的信息联系起来。然后，我们引入了一个信息性问题和揭示性问题之间的权衡，这个权衡考虑了人和机器人的观点：一个机器人为了这个权衡而优化，它主动地从人类那里收集信息，同时让人类了解到最新的知识。我们通过模拟、在线调查和面对面用户研究来评估我们的方法。我们的用户研究和结果视频可在以下位置获得：https://youtu.be/tC6y_jHN7Vw. 摘要：Robots can learn from humans by asking questions. In these questions the robot demonstrates a few different behaviors and asks the human for their favorite. But how should robots choose which questions to ask? Today's robots optimize for informative questions that actively probe the human's preferences as efficiently as possible. But while informative questions make sense from the robot's perspective, human onlookers often find them arbitrary and misleading. In this paper we formalize active preference-based learning from the human's perspective. We hypothesize that -- from the human's point-of-view -- the robot's questions reveal what the robot has and has not learned. Our insight enables robots to use questions to make their learning process transparent to the human operator. We develop and test a model that robots can leverage to relate the questions they ask to the information these questions reveal. We then introduce a trade-off between informative and revealing questions that considers both human and robot perspectives: a robot that optimizes for this trade-off actively gathers information from the human while simultaneously keeping the human up to date with what it has learned. We evaluate our approach across simulations, online surveys, and in-person user studies. Videos of our user studies and results are available here: https://youtu.be/tC6y_jHN7Vw.

【6】 Detecting Faults during Automatic Screwdriving: A Dataset and Use Case of Anomaly Detection for Automatic Screwdriving 标题：自动拧紧过程中的故障检测：自动拧紧异常检测的数据集及应用实例

作者：Błażej Leporowski,Daniella Tola,Casper Hansen,Alexandros Iosifidis 机构： Department of Electrical and Computer Engineering, Aarhus University, Technicon ApS, Hobro 链接：https://arxiv.org/abs/2107.01955 摘要：检测制造应用程序中的故障可能很困难，特别是如果每个故障模型都是手工设计的。数据驱动的方法，使用机器学习（ML）来检测故障最近得到了越来越多的关注，其中ML模型可以在一组来自制造过程的数据上进行训练。在本文中，我们提出了一个使用ML模型检测自动螺丝刀操作过程中故障的用例，并介绍了一个新的数据集，其中包含了通用机器人和OnRobot螺丝刀在正常和异常操作过程中的完全监控和注册数据。我们用两个时间序列ML模型说明了如何在自动螺丝刀应用中检测故障。 摘要：Detecting faults in manufacturing applications can be difficult, especially if each fault model is to be engineered by hand. Data-driven approaches, using Machine Learning (ML) for detecting faults have recently gained increasing interest, where a ML model can be trained on a set of data from a manufacturing process. In this paper, we present a use case of using ML models for detecting faults during automated screwdriving operations, and introduce a new dataset containing fully monitored and registered data from a Universal Robot and OnRobot screwdriver during both normal and anomalous operations. We illustrate, with the use of two time-series ML models, how to detect faults in an automated screwdriving application.

【7】 Hybrid and dynamic policy gradient optimization for bipedal robot locomotion 标题：两足机器人运动的混合动态策略梯度优化

作者：Changxin Huang,Jiang Su,Zhihong Zhang,Dong Zhao,Liang Lin 机构：Sun Yat-sen University, DMAI Great China, Zihong Zhang 链接：https://arxiv.org/abs/2107.01908 摘要：由于涉及到复杂的动力学和多准则优化问题，对非静态双足机器人的控制具有挑战性。最近的工作已经证明了深度强化学习（DRL）对模拟和实际实现的两足动物的有效性。在这些方法中，来自不同标准的奖励通常被加起来学习一个单一的价值函数。然而，这可能会导致混合奖励之间的依赖信息丢失，并导致次优策略。在这项工作中，我们提出了一个新的策略梯度强化学习的两足动物的运动，使控制策略可以同时优化多个准则使用一个动态机制。我们提出的方法是使用一个多头的评论家来学习一个单独的价值函数，每个组成部分的奖励函数。这也导致了混合政策的梯度。我们进一步提出了混合策略梯度的动态权重，以优化不同优先级的策略。这种混合动态策略梯度（HDPG）设计使得agent学习效率更高。结果表明，该方法的性能优于一般的奖励方法，并且能够转移到物理机器人上。MuJoCo结果进一步证明了HDPG的有效性和通用性。 摘要：Controlling a non-statically bipedal robot is challenging due to the complex dynamics and multi-criterion optimization involved. Recent works have demonstrated the effectiveness of deep reinforcement learning (DRL) for simulation and physically implemented bipeds. In these methods, the rewards from different criteria are normally summed to learn a single value function. However, this may cause the loss of dependency information between hybrid rewards and lead to a sub-optimal policy. In this work, we propose a novel policy gradient reinforcement learning for biped locomotion, allowing the control policy to be simultaneously optimized by multiple criteria using a dynamic mechanism. Our proposed method applies a multi-head critic to learn a separate value function for each component reward function. This also leads to hybrid policy gradients. We further propose dynamic weight for hybrid policy gradients to optimize the policy with different priorities. This hybrid and dynamic policy gradient (HDPG) design makes the agent learn more efficiently. We showed that the proposed method outperforms summed-up-reward approaches and is able to transfer to physical robots. The MuJoCo results further demonstrate the effectiveness and generalization of our HDPG.

【8】 Online and Offline Robot Programming via Augmented Reality Workspaces 标题：通过增强现实工作空间进行在线和离线机器人编程

作者：Yong Joon Thoo,Jérémy Maceiras,Philip Abbet,Mattia Racca,Hakan Girgin,Sylvain Calinon 机构： the control of a robot via a teachingpendant often requires the robot in question to be removedThe authors are with the Idiap Research Institute 备注：8 pages, 9 figures, submitted to 'IEEE Robotics & Automation Magazine' (RAM), Special Issue on Extended Reality in Robotics 链接：https://arxiv.org/abs/2107.01884 摘要：用于工业机器人的机器人编程方法非常耗时，并且通常要求操作员具有机器人学和编程方面的知识。为了降低与重新编程相关的成本，最近提出了使用增强现实技术的各种接口，以便为用户提供更直观的方法来实时控制机器人并对其进行编程，而无需编写代码。然而，大多数解决方案要求操作员靠近真实机器人的工作空间，这意味着要么将其从生产线移除，要么由于安全隐患关闭整个生产线。我们提出了一种新的增强现实接口，用户可以建立一个虚拟的工作空间模型，该模型可以被保存和重用，以编写新的任务或调整旧的任务，而不必与真实的机器人共存。与以前的界面类似，操作员可以通过操纵虚拟机器人来编程或实时控制机器人。我们评估的直观性和可用性提出的界面与用户研究，其中18名参与者编程机器人机械手的拆卸任务。 摘要：Robot programming methods for industrial robots are time consuming and often require operators to have knowledge in robotics and programming. To reduce costs associated with reprogramming, various interfaces using augmented reality have recently been proposed to provide users with more intuitive means of controlling robots in real-time and programming them without having to code. However, most solutions require the operator to be close to the real robot's workspace which implies either removing it from the production line or shutting down the whole production line due to safety hazards. We propose a novel augmented reality interface providing the users with the ability to model a virtual representation of a workspace which can be saved and reused to program new tasks or adapt old ones without having to be co-located with the real robot. Similar to previous interfaces, the operators then have the ability to program robot tasks or control the robot in real-time by manipulating a virtual robot. We evaluate the intuitiveness and usability of the proposed interface with a user study where 18 participants programmed a robot manipulator for a disassembly task.

【9】 Control of rough terrain vehicles using deep reinforcement learning 标题：基于深度强化学习的崎岖地形车辆控制

作者：Viktor Wiberg,Erik Wallin,Martin Servin,Tomas Nordfjell 机构： Ume˚a University, se† Swedish University of Agricultural Sciences 备注：16 pages, 13 figures 链接：https://arxiv.org/abs/2107.01867 摘要：我们探讨了在人工操作和传统控制方法不足的情况下，使用深度强化控制地形车辆的可能性。这封信提出了一个控制器，感知，计划，并成功地控制一个16吨的林业车辆与两个框架铰接关节，六个车轮，以及他们的积极铰接悬挂横穿崎岖的地形。精心塑造的奖励信号促进了安全、环保和高效驾驶，这导致了前所未有的驾驶技能的出现。我们在虚拟环境中测试所学的技能，包括用高密度激光扫描森林遗址重建的地形。控制器显示处理障碍物、高达27$^\circ$的斜坡和各种自然地形的能力，所有这些都具有有限的车轮打滑、平滑和垂直的横向移动以及智能使用主动悬架。结果表明，与人工操作或传统的控制方法相比，深度强化学习对具有复杂动力学和高维观测数据的车辆具有增强控制的潜力，特别是在崎岖地形下。 摘要：We explore the potential to control terrain vehicles using deep reinforcement in scenarios where human operators and traditional control methods are inadequate. This letter presents a controller that perceives, plans, and successfully controls a 16-tonne forestry vehicle with two frame articulation joints, six wheels, and their actively articulated suspensions to traverse rough terrain. The carefully shaped reward signal promotes safe, environmental, and efficient driving, which leads to the emergence of unprecedented driving skills. We test learned skills in a virtual environment, including terrains reconstructed from high-density laser scans of forest sites. The controller displays the ability to handle obstructing obstacles, slopes up to 27$^\circ$, and a variety of natural terrains, all with limited wheel slip, smooth, and upright traversal with intelligent use of the active suspensions. The results confirm that deep reinforcement learning has the potential to enhance control of vehicles with complex dynamics and high-dimensional observation data compared to human operators or traditional control methods, especially in rough terrain.

【10】 Advanced turning maneuver of a multi-legged robot using pitchfork bifurcation 标题：基于干草叉分叉的多足机器人高级转弯动作

作者：Shinya Aoi,Ryoe Tomatsu,Yuki Yabuuchi,Soichiro Fujiki,Kei Senda,Kazuo Tsuchiya 机构： Dept. of Aeronautics and Astronautics, Graduate School of Engineering, Kyoto University, Kyoto, daigaku-Katsura, Nishikyo-ku, Kyoto ,-, Japan, Dept. of Physiology and Biological Information, School of Medicine, Dokkyo Medical University 链接：https://arxiv.org/abs/2107.01837 摘要：腿型机器人在陆地上有很好的机动性，可以穿越各种各样的环境，因此有可能被部署在各种各样的场景中。然而，在运动过程中，它们很容易摔倒和腿部故障。虽然使用大量的腿可以克服这些问题，但它会使身体变长，导致许多接触腿被限制在地面上以支撑长身体，从而影响机动性。为了提高机器人的运动可操作性，本文研究了引起快速、大幅度运动变化的动态不稳定性，并采用了一种具有柔性体轴的12足机器人。我们以前的工作发现，当机器人的体轴柔度发生变化时，机器人的直线行走会通过Hopf分岔而变得不稳定，从而引起人体的波动。此外，我们开发了一个简单的基于Hopf分岔的控制器，并证明了直线行走不稳定性有利于机器人的转向。在这项研究中，我们新发现，当体轴柔度以不同于我们先前工作的方式改变时，直线行走通过干叉分叉变得不稳定。干叉分叉不仅导致了直线行走的不稳定性，而且导致了向曲线行走的过渡，曲线行走的曲率可以由体轴的柔度来控制。我们开发了一个简单的基于干叉分岔特性的控制器，并证明了该机器人能够执行比以前基于Hopf分岔的控制器更好的转弯动作。本研究提供了一种新的设计原则，可用于多足机器人的机动运动利用固有的动态特性。 摘要：Legged robots have excellent terrestrial mobility for traversing diverse environments and thus have the potential to be deployed in a wide variety of scenarios. However, they are susceptible to falling and leg malfunction during locomotion. Although the use of a large number of legs can overcome these problems, it makes the body long and leads to many contact legs being constrained on the ground to support the long body, which impedes maneuverability. To improve the locomotion maneuverability of the robots, the present study focuses on dynamic instability, which induces rapid and large movement changes, and uses a 12-legged robot with flexible body axis. Our previous work found that the straight walk of the robot becomes unstable through Hopf bifurcation when the body axis flexibility is changed, which induces body undulations. Furthermore, we developed a simple controller based on the Hopf bifurcation and showed that the straight walk instability facilitates the turning of the robot. In this study, we newly found that the straight walk becomes unstable through pitchfork bifurcation when the body-axis flexibility is changed in a different way from that in our previous work. The pitchfork bifurcation not only induces the straight walk instability but also the transition into the curved walk, whose curvature can be controlled by the body-axis flexibility. We developed a simple controller based on the pitchfork-bifurcation characteristics and demonstrated that the robot can perform a turning maneuver superior to the previous controller based on the Hopf bifurcation. This study provides a novel design principle for maneuverable locomotion of many-legged robots using intrinsic dynamic properties.

【11】 GraspME -- Grasp Manifold Estimator 标题：GRAPME--GRAP流形估计器

作者：Janik Hager,Ruben Bauer,Marc Toussaint,Jim Mainprice 机构：Machine Learning and Robotics Lab, IPVS, University of Stuttgart, Germany, Max Planck Institute for Intelligent Systems ; IS-MPI ; T¨ubingenStuttgart, Germany, Technische Universit¨at Berlin ; TUB ; Germany 备注：Accepted to RoMan 2021 链接：https://arxiv.org/abs/2107.01836 摘要：在本文中，我们引入了一个抓取流形估计器（GraspME）来直接检测二维相机图像中物体的抓取启示。为了自主地执行操作任务，机器人必须对周围物体建立这样的可抓取性模型。抓取流形具有提供连续无限多个抓取的优点，这在使用其他抓取表示（例如预定义的抓取点）时不是这种情况。例如，在运动优化中可以利用这个特性，将目标集定义为机器人配置空间中的隐式曲面约束。在这项工作中，我们限制自己的情况下估计可能的末端效应器位置直接从二维相机图像。为此，我们通过一组关键点来定义抓取流形，并使用掩模R-CNN主干在图像中定位它们。使用学习到的特征可以概括到不同的视角，具有潜在噪声的图像和不属于训练集的对象。我们只依赖模拟数据，对简单和复杂的物体进行实验，包括看不见的物体。该框架在GPU上的推理速度为11.5fps，关键点估计的平均精度为94.5%，平均像素距离仅为1.29。这表明，通过边界盒和分割掩模可以很好地估计出目标，并且可以逼近正确的抓取流形的关键点坐标。 摘要：In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images. To perform manipulation tasks autonomously it is crucial for robots to have such graspability models of the surrounding objects. Grasp manifolds have the advantage of providing continuously infinitely many grasps, which is not the case when using other grasp representations such as predefined grasp points. For instance, this property can be leveraged in motion optimization to define goal sets as implicit surface constraints in the robot configuration space. In this work, we restrict ourselves to the case of estimating possible end-effector positions directly from 2D camera images. To this extend, we define grasp manifolds via a set of key points and locate them in images using a Mask R-CNN backbone. Using learned features allows generalizing to different view angles, with potentially noisy images, and objects that were not part of the training set. We rely on simulation data only and perform experiments on simple and complex objects, including unseen ones. Our framework achieves an inference speed of 11.5 fps on a GPU, an average precision for keypoint estimation of 94.5% and a mean pixel distance of only 1.29. This shows that we can estimate the objects very well via bounding boxes and segmentation masks as well as approximate the correct grasp manifold's keypoint coordinates.

【12】 A System for Traded Control Teleoperation of Manipulation Tasks using Intent Prediction from Hand Gestures 标题：基于手势意图预测的操作任务交换控制遥操作系统

作者：Yoojin Oh,Marc Toussaint,Jim Mainprice 机构：Machine Learning and Robotics Lab, IPVS, University of Stuttgart, Germany, Max Planck Institute for Intelligent Systems ; MPI-IS ; T¨ubingenStuttgart, Germany, Technische Universit¨at Berlin ; TUB ; Germany 备注：Accepted to IEEE-RoMAN 2021 链接：https://arxiv.org/abs/2107.01829 摘要：提出了一种包含机器人感知和手势意图预测的遥操作系统。感知模块识别机器人工作空间中存在的对象，意图预测模块识别用户可能想要抓住的对象。该体系结构允许该方法依赖于交易控制而不是直接控制：我们使用手势来指定连续操作任务的目标对象，然后机器人通过轨迹优化自主生成抓取或回收运动。感知模块依靠基于模型的跟踪器精确跟踪目标的6D姿态，并利用最新的基于学习的目标检测和分割方法，通过自动检测场景中的目标来初始化跟踪器。利用训练好的多层感知器分类器从用户手势中识别目标对象。在介绍了系统的所有组成部分及其经验评估之后，我们给出了将我们的管道与直接交易控制方法（即不使用预测的方法）进行比较的实验结果，这表明使用意图预测可以降低总体任务执行时间。 摘要：This paper presents a teleoperation system that includes robot perception and intent prediction from hand gestures. The perception module identifies the objects present in the robot workspace and the intent prediction module which object the user likely wants to grasp. This architecture allows the approach to rely on traded control instead of direct control: we use hand gestures to specify the goal objects for a sequential manipulation task, the robot then autonomously generates a grasping or a retrieving motion using trajectory optimization. The perception module relies on the model-based tracker to precisely track the 6D pose of the objects and makes use of a state of the art learning-based object detection and segmentation method, to initialize the tracker by automatically detecting objects in the scene. Goal objects are identified from user hand gestures using a trained a multi-layer perceptron classifier. After presenting all the components of the system and their empirical evaluation, we present experimental results comparing our pipeline to a direct traded control approach (i.e., one that does not use prediction) which shows that using intent prediction allows to bring down the overall task execution time.

【13】 Toward Increased Airspace Safety: Quadrotor Guidance for Targeting Aerial Objects 标题：迈向更高的空域安全：瞄准空中目标的四旋翼制导

作者：Anish Bhattacharya 机构：CMU-RI-TR-,-, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA , Thesis Committee:, Sebastian Scherer (Chair), Oliver Kroemer, Azarakhsh Keipour, Submitted in partial fulfillment of the requirements, for the degree of Master of Science. 备注：58 pages, 33 figures, 2 tables. Thesis towards a Master of Science in Robotics, CMU 链接：https://arxiv.org/abs/2107.01733 摘要：随着商用无人机（UAV）市场的蓬勃发展，在受保护或敏感空域发现的小型遥控或自动驾驶飞机越来越多。拆除这些飞机的现有解决方案要么是军用级的，对国内使用来说太具破坏性，要么是由笨重的遥控反无人机车辆组成，这些车辆在备受瞩目的国内案例中被证明是无效的。在这项工作中，我们研究了如何使用四旋翼自动瞄准半静止和移动的空中目标，而事先对目标的飞行特性知之甚少或一无所知。制导和控制命令仅由车载单目摄像机的信息生成。我们从导弹制导方面的文献中得到启发，并论证了一种在四旋翼上实现但不适用于导弹的最优制导方法。文中给出了不同方法的首过命中成功率和追踪持续时间的计算结果。最后，我们介绍了在MBZIRC 2020 Challenge 1比赛中CMU团队的格子图案，展示了在结构化比赛环境中简单视线引导方法的有效性。 摘要：As the market for commercially available unmanned aerial vehicles (UAVs) booms, there is an increasing number of small, teleoperated or autonomous aircraft found in protected or sensitive airspace. Existing solutions for removal of these aircraft are either military-grade and too disruptive for domestic use, or compose of cumbersomely teleoperated counter-UAV vehicles that have proven ineffective in high-profile domestic cases. In this work, we examine the use of a quadrotor for autonomously targeting semi-stationary and moving aerial objects with little or no prior knowledge of the target's flight characteristics. Guidance and control commands are generated with information just from an onboard monocular camera. We draw inspiration from literature in missile guidance, and demonstrate an optimal guidance method implemented on a quadrotor but not usable by missiles. Results are presented for first-pass hit success and pursuit duration with various methods. Finally, we cover the CMU Team Tartan entry in the MBZIRC 2020 Challenge 1 competition, demonstrating the effectiveness of simple line-of-sight guidance methods in a structured competition setting.

【14】 Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces 标题：连续动作空间中机器人先验的低维状态表征学习

作者：Nicolò Botteghi,Khaled Alaa,Mannes Poel,Beril Sirmacek,Christoph Brune,Abeje Mersha,Stefano Stramigioli 机构： JönköpingUniversity 备注：Paper Accepted at IROS2021. 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 链接：https://arxiv.org/abs/2107.01667 摘要：自主机器人需要高度的认知和运动智能才能进入我们的日常生活。在非结构化环境和存在不确定性的情况下，这样的智能度是不容易获得的。强化学习算法已经被证明能够以端到端的方式解决复杂的机器人任务，而不需要任何手工制作的特性或策略。特别是在机器人领域，真实世界数据的成本通常非常高，因此需要实现高样本效率的强化学习解决方案。在本文中，我们提出了一个结合低维状态表示的学习框架，从机器人原始感官读数的高维观察值中学习低维状态表示，并在给定学习状态表示的情况下学习最优策略。我们评估了我们的框架在移动机器人导航的情况下，在连续的状态和行动空间。此外，我们还研究了在存在视觉和深度干扰（如照明变化和移动障碍物）的情况下，如何将在模拟虚拟环境中学习到的知识转移到真实机器人上，而无需进一步的再训练。 摘要：Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain. Reinforcement learning algorithms have proven to be capable of solving complicated robotics tasks in an end-to-end fashion without any need for hand-crafted features or policies. Especially in the context of robotics, in which the cost of real-world data is usually extremely high, reinforcement learning solutions achieving high sample efficiency are needed. In this paper, we propose a framework combining the learning of a low-dimensional state representation, from high-dimensional observations coming from the robot's raw sensory readings, with the learning of the optimal policy, given the learned state representation. We evaluate our framework in the context of mobile robot navigation in the case of continuous state and action spaces. Moreover, we study the problem of transferring what learned in the simulated virtual environment to the real robot without further retraining using real-world data in the presence of visual and depth distractors, such as lighting changes and moving obstacles.

【15】 Unified Identification and Tuning Approach Using Deep Neural Networks For Visual Servoing Applications 标题：视觉伺服应用的深度神经网络统一辨识与整定方法

作者：Oussama Abdul Hay,Mohamad Chehadeh,Abdulla Ayyad,Mohamad Wahbah,Muhammad Humais,Yahya Zweiri 机构： Member, IEEE 链接：https://arxiv.org/abs/2107.01581 摘要：基于视觉的无人机控制技术由于具有低成本的机载传感器和计算机而得到了广泛的应用。调整这些系统以使其正常工作需要广泛的领域特定经验，这限制了新兴应用程序的增长。此外，由于所用模型的复杂性，用目前的先进技术无法获得无人机视觉伺服的性能极限。在本文中，我们提出了一个系统的方法，实时识别和调整视觉伺服系统的基础上，一个新的鲁棒版本的最新的深层神经网络与改进的继电器反馈测试（DNN-MRFT）方法。所提出的鲁棒DNN-MRFT算法可用于多种视觉传感器和估计算法，尽管传感器的噪声水平很高。研究了MRFT对扰动的敏感性，分析了MRFT对辨识和调谐性能的影响。DNN-MRFT能够检测到由于使用较慢的视觉传感器或由于集成了加速计测量而导致的性能变化。实验辨识结果与仿真结果非常吻合，可以用来解释系统行为，预测给定硬件和软件设置的闭环性能极限。最后，我们证明了DNN-MRFT调谐视觉伺服系统抑制外部干扰的能力。与现有的视觉伺服设计方法相比，本文提出的鲁棒辨识方法具有一些优点。 摘要：Vision based control of Unmanned Aerial Vehicles (UAVs) has been adopted by a wide range of applications due to the availability of low-cost on-board sensors and computers. Tuning such systems to work properly requires extensive domain specific experience which limits the growth of emerging applications. Moreover, obtaining performance limits of UAV based visual servoing with the current state-of-the-art is not possible due to the complexity of the models used. In this paper, we present a systematic approach for real-time identification and tuning of visual servoing systems based on a novel robustified version of the recent deep neural networks with the modified relay feedback test (DNN-MRFT) approach. The proposed robust DNN-MRFT algorithm can be used with a multitude of vision sensors and estimation algorithms despite the high levels of sensor's noise. Sensitivity of MRFT to perturbations is investigated and its effect on identification and tuning performance is analyzed. DNN-MRFT was able to detect performance changes due to the use of slower vision sensors, or due to the integration of accelerometer measurements. Experimental identification results were closely matching simulation results, which can be used to explain system behaviour and anticipate the closed loop performance limits given a certain hardware and software setup. Finally, we demonstrate the capability of the DNN-MRFT tuned visual servoing systems to reject external disturbances. Some advantages of the suggested robust identification approach compared to existing visual servoing design approaches are presented.

【16】 Similarity-Aware Fusion Network for 3D Semantic Segmentation 标题：基于相似度感知的三维语义分割融合网络

作者：Linqing Zhao,Jiwen Lu,Jie Zhou 机构： Tsinghua University 备注：Accepted by 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021) 链接：https://arxiv.org/abs/2107.01579 摘要：本文提出了一种基于相似度的融合网络（SAFNet）自适应融合二维图像和三维点云进行三维语义分割。现有的基于融合的方法通过融合来自多个模式的信息来获得显著的性能。然而，它们严重依赖于二维像素和三维点之间的投影对应关系，只能以固定的方式进行信息融合，因此它们的性能很难迁移到更真实的场景中，在这种场景中，采集的数据往往缺乏严格的成对特征进行预测。为了解决这个问题，我们采用了一种后期融合策略，首先学习输入点云和反向投影点云（从2D像素）之间的几何和上下文相似性，并利用它们指导两种模式的融合，以进一步利用互补信息。具体来说，我们使用几何相似模块（GSM）直接比较成对3D邻域的空间坐标分布，使用上下文相似模块（CSM）聚合和比较相应中心点的空间上下文信息。这两个模块可以有效地测量图像特征对预测的帮助程度，使得网络能够自适应地调整两种模式对每个点最终预测的贡献。在ScanNetV2基准上的实验结果表明，SAFNet在各种数据完整性方面显著优于现有的基于融合的方法。 摘要：In this paper, we propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation. Existing fusion-based methods achieve remarkable performances by integrating information from multiple modalities. However, they heavily rely on the correspondence between 2D pixels and 3D points by projection and can only perform the information fusion in a fixed manner, and thus their performances cannot be easily migrated to a more realistic scenario where the collected data often lack strict pair-wise features for prediction. To address this, we employ a late fusion strategy where we first learn the geometric and contextual similarities between the input and back-projected (from 2D pixels) point clouds and utilize them to guide the fusion of two modalities to further exploit complementary information. Specifically, we employ a geometric similarity module (GSM) to directly compare the spatial coordinate distributions of pair-wise 3D neighborhoods, and a contextual similarity module (CSM) to aggregate and compare spatial contextual information of corresponding central points. The two proposed modules can effectively measure how much image features can help predictions, enabling the network to adaptively adjust the contributions of two modalities to the final prediction of each point. Experimental results on the ScanNetV2 benchmark demonstrate that SAFNet significantly outperforms existing state-of-the-art fusion-based approaches across various data integrity.

【17】 Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans 标题：具有潜在计划的杂乱场景抓取的分层策略

作者：Lirui Wang,Yu Xiang,Dieter Fox 机构：University of Washington,NVIDIA 链接：https://arxiv.org/abs/2107.01518 摘要：在杂乱的场景中抓取6D是一个长期存在的机器人操作问题。由于模块化和错误敏感性，开环操作管道可能会失败，而大多数具有原始感知输入的端到端抓取策略尚未扩展到具有障碍的复杂场景。在这项工作中，我们提出了一种新的方法，通过抽样和选择潜在空间的计划来缩小差距。我们的层次结构学习基于部分点云观测的无碰撞目标驱动抓取。我们的方法学习了一个嵌入空间来表示专家抓取计划，以及一个变分自动编码器来在推理时对不同的潜在计划进行采样。此外，我们还训练了一个潜在的计划批评家来进行计划选择，并通过分层强化学习训练了一个选项分类器来切换到实例抓取策略。我们评估和分析了我们的方法，并与仿真中的几种基线进行了比较，证明了潜在规划可以推广到真实世界中的杂乱场景抓取任务。我们的视频和代码可以在https://sites.google.com/view/latent-grasping . 摘要：6D grasping in cluttered scenes is a longstanding robotic manipulation problem. Open-loop manipulation pipelines can fail due to modularity and error sensitivity while most end-to-end grasping policies with raw perception inputs have not yet scaled to complex scenes with obstacles. In this work, we propose a new method to close the gap through sampling and selecting plans in the latent space. Our hierarchical framework learns collision-free target-driven grasping based on partial point cloud observations. Our method learns an embedding space to represent expert grasping plans and a variational autoencoder to sample diverse latent plans at inference time. Furthermore, we train a latent plan critic for plan selection and an option classifier for switching to an instance grasping policy through hierarchical reinforcement learning. We evaluate and analyze our method and compare against several baselines in simulation, and demonstrate that the latent planning can generalize to the real-world cluttered-scene grasping task. Our videos and code can be found at https://sites.google.com/view/latent-grasping .

【18】 Carnegie Mellon Team Tartan: Mission-level Robustness with Rapidly Deployed Autonomous Aerial Vehicles in the MBZIRC 2020 标题：卡内基梅隆大学塔坦团队：MBZIRC 2020中快速部署的自主飞行器的任务级健壮性

作者：Anish Bhattacharya,Akshit Gandhi,Lukas Merkle,Rohan Tiwari,Karun Warrior,Stanley Winata,Andrew Saba,Kevin Zhang,Oliver Kroemer,Sebastian Scherer 机构：Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 备注：28 pages, 26 figures. To appear in Field Robotics, Special Issues on MBZIRC 2020 链接：https://arxiv.org/abs/2107.01507 摘要：机器人系统要在高风险、现实环境中使用，就必须能够快速部署，并且对环境变化、性能不佳的硬件和任务子任务故障具有鲁棒性。机器人通常被设计成考虑单个任务事件序列，在一些关键约束下，复杂的算法降低单个子任务失败率。我们的方法是利用视觉和控制中的通用技术，通过结果监测和恢复策略，在系统基础设施的帮助下，将鲁棒性编码到任务结构中，该系统基础设施允许在时间紧迫和无中心通信的情况下快速部署任务。我们还详细介绍了快速野战机器人开发和测试的经验教训。在美国宾夕法尼亚州匹兹堡的一个室外试验场，以及在2020年的穆罕默德·本·扎耶德国际机器人挑战赛上，通过真实的机器人实验开发和评估了这些系统。所有比赛试验均在完全自主模式下完成，无需RTK-GPS。我们的系统在挑战2中获得第4名，在大挑战中获得第7名，并取得了诸如弹出五个气球（挑战1）、成功拾取和放置一个木块（挑战2）以及使用所有团队的无人机将大部分水自动分配到室外真实火上（挑战3）等成就。 摘要：For robotics systems to be used in high risk, real-world situations, they have to be quickly deployable and robust to environmental changes, under-performing hardware, and mission subtask failures. Robots are often designed to consider a single sequence of mission events, with complex algorithms lowering individual subtask failure rates under some critical constraints. Our approach is to leverage common techniques in vision and control and encode robustness into mission structure through outcome monitoring and recovery strategies, aided by a system infrastructure that allows for quick mission deployments under tight time constraints and no central communication. We also detail lessons in rapid field robotics development and testing. Systems were developed and evaluated through real-robot experiments at an outdoor test site in Pittsburgh, Pennsylvania, USA, as well as in the 2020 Mohamed Bin Zayed International Robotics Challenge. All competition trials were completed in fully autonomous mode without RTK-GPS. Our system led to 4th place in Challenge 2 and 7th place in the Grand Challenge, and achievements like popping five balloons (Challenge 1), successfully picking and placing a block (Challenge 2), and dispensing the most water autonomously with a UAV of all teams onto an outdoor, real fire (Challenge 3).

【19】 Overcoming the Force Limitations of Magnetic Robotic Surgery: Impact-based Tetherless Suturing 标题：克服磁性机器人手术的力限制：基于冲击的无绳缝合

作者：Onder Erin,Xiaolong Liu,Jiawei Ge,Lamar Mair,Yotam Barnoy,Yancy Diaz-Mercado,Axel Krieger 机构：Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD , USA, Weinberg Medical Physics, Inc., North Bethesda, MD , USA, Department of Computer Science, Johns Hopkins University, Baltimore, MD , USA 备注：Journal, 5 figures 链接：https://arxiv.org/abs/2107.01504 摘要：磁性机器人避免了执行器和末端执行器之间的物理连接，从而实现了超微创手术。尽管这样的无线驱动方法在医学应用中非常有利，但在临床相关条件下实际应用中，作用力和微型磁性末端执行器尺寸之间的权衡一直是主要挑战之一。这种权衡对于需要组织内穿透的应用（例如，针入、活检和缝合）至关重要。为了将这种磁性微型末端执行器的力增加到实用水平，我们提出了一种基于冲击力的缝合针，它能够穿透具有3自由度平面自由度（平面定位和平面定向）的体外和离体样本。所提出的优化设计是定制的12g针，可以产生1.16n的穿透力，在没有这种冲击力的情况下，穿透力是相同尺寸磁性针的56倍。通过将快速移动的永磁体包含在受限管状结构的针内，整个针的移动保持缓慢且易于控制。所获得的力在组织穿透极限的范围内，使得针能够穿透组织，从而以遥控方式遵循缝合方法。我们展示了体外针插入培根条和成功缝合纱布网到琼脂凝胶模拟疝气修补程序。 摘要：Magnetic robotics obviate the physical connections between the actuators and end effectors resulting in ultra-minimally invasive surgeries. Even though such a wireless actuation method is highly advantageous in medical applications, the trade-off between the applied force and miniature magnetic end effector dimensions has been one of the main challenges in practical applications in clinically relevant conditions. This trade-off is crucial for applications where in-tissue penetration is required (e.g., needle access, biopsy, and suturing). To increase the forces of such magnetic miniature end effectors to practically useful levels, we propose an impact-force-based suturing needle that is capable of penetrating into in-vitro and ex-vivo samples with 3-DoF planar freedom (planar positioning and in-plane orienting). The proposed optimized design is a custom-built 12 G needle that can generate 1.16 N penetration force which is 56 times stronger than its magnetic counterparts with the same size without such an impact force. By containing the fast-moving permanent magnet within the needle in a confined tubular structure, the movement of the overall needle remains slow and easily controllable. The achieved force is in the range of tissue penetration limits allowing the needle to be able to penetrate through tissues to follow a suturing method in a teleoperated fashion. We demonstrated in-vitro needle penetration into a bacon strip and successful suturing of a gauze mesh onto an agar gel mimicking a hernia repair procedure.

【20】 Examining average and discounted reward optimality criteria in reinforcement learning 标题：强化学习中平均和贴现报酬最优准则的检验

作者：Vektor Dewanto,Marcus Gallagher 机构：School of Information Technology and Electrical Engineering, University of Queensland, Australia 备注：14 pages, 3 figures, 10-page main content 链接：https://arxiv.org/abs/2107.01348 摘要：在强化学习（RL）中，目标是获得一个最优策略，其中最优性准则至关重要。两个主要的最优性标准是平均报酬和折扣报酬，后者通常被认为是前者的近似值。虽然折扣奖励更受欢迎，但在没有折扣的自然概念的环境中应用是有问题的。这促使我们重新审视a）动态规划中最优性标准的发展，b）人工贴现因子的合理性和复杂性，以及c）直接使平均报酬最大化的好处。我们的贡献包括对平均报酬和折扣报酬之间关系的彻底研究，以及对它们在RL中的优缺点的讨论。我们强调平均报酬RL方法具有发展RL中一般无折扣最优准则（Veinott，1969）的成分和机制。 摘要：In reinforcement learning (RL), the goal is to obtain an optimal policy, for which the optimality criterion is fundamentally important. Two major optimality criteria are average and discounted rewards, where the later is typically considered as an approximation to the former. While the discounted reward is more popular, it is problematic to apply in environments that have no natural notion of discounting. This motivates us to revisit a) the progression of optimality criteria in dynamic programming, b) justification for and complication of an artificial discount factor, and c) benefits of directly maximizing the average reward. Our contributions include a thorough examination of the relationship between average and discounted rewards, as well as a discussion of their pros and cons in RL. We emphasize that average-reward RL methods possess the ingredient and mechanism for developing the general discounting-free optimality criterion (Veinott, 1969) in RL.

【21】 Row-sensing Templates: A Generic 3D Sensor-based Approach to Robot Localization with Respect to Orchard Row Centerlines 标题：行感知模板：一种通用的基于3D传感器的果园行中心线机器人定位方法

作者：Zhenghao Fei,Stavros Vougioukas 机构：University of California, Davis, Department of Biological and Agricultural Engineering 链接：https://arxiv.org/abs/2107.01321 摘要：在卫星信号经常被树叶遮挡的情况下，机器人相对于果园行中心线的精确定位是实现自主导航的关键。现有的基于传感器的方法依赖于从图像和点云中提取的各种特征。然而，任何选定的特征都不一致，因为当树木类型、生长阶段、树冠管理实践、季节和天气条件发生变化时，果园行的视觉和几何特征会发生巨大变化。本文提出了一种不依赖特征的定位方法；相反，它依赖于行感应模板的概念，即当传感器位于中心线上的任何位置并与中心线完美对齐时，对果园行中移动的3D传感器的预期观察。首先，只要传感器相对于中心线的真实姿态可用，就可以使用一些测量值来构建模板。然后，在导航过程中，通过粒子滤波最大化模板和感测点云之间的匹配来估计最佳姿态估计（及其置信度）。该方法通过重建模板，可以适应不同的果园和条件。实验在葡萄园进行，并在果园在不同的季节。结果表明，横向平均绝对误差（MAE）小于行宽的3.6%，抽穗MAE小于1.72°。定位是稳健的，因为当缺少少于75%的测量点时，误差不会增加。结果表明，基于模板的定位方法可以为果园的精确定位和鲁棒定位提供一种通用的方法。 摘要：Accurate robot localization relative to orchard row centerlines is essential for autonomous guidance where satellite signals are often obstructed by foliage. Existing sensor-based approaches rely on various features extracted from images and point clouds. However, any selected features are not available consistently, because the visual and geometrical characteristics of orchard rows change drastically when tree types, growth stages, canopy management practices, seasons, and weather conditions change. In this work, we introduce a novel localization method that doesn't rely on features; instead, it relies on the concept of a row-sensing template, which is the expected observation of a 3D sensor traveling in an orchard row, when the sensor is anywhere on the centerline and perfectly aligned with it. First, the template is built using a few measurements, provided that the sensor's true pose with respect to the centerline is available. Then, during navigation, the best pose estimate (and its confidence) is estimated by maximizing the match between the template and the sensed point cloud using particle-filtering. The method can adapt to various orchards and conditions by re-building the template. Experiments were performed in a vineyard, and in an orchard in different seasons. Results showed that the lateral mean absolute error (MAE) was less than 3.6% of the row width, and the heading MAE was less than 1.72 degrees. Localization was robust, as errors didn't increase when less than 75% of measurement points were missing. The results indicate that template-based localization can provide a generic approach for accurate and robust localization in real-world orchards.

【22】 Towards safe human-to-robot handovers of unknown containers 标题：走向未知集装箱人到机器人的安全交接

作者：Yik Lung Pang,Alessio Xompero,Changjae Oh,Andrea Cavallaro 机构： Queen Mary University of London 备注：Camera-ready version. Paper accepted to RO-MAN 2021. 8 pages, 8 figures, 1 table 链接：https://arxiv.org/abs/2107.01309 摘要：对于未知物体的人-机器人安全切换，需要精确估计手的姿势和物体的属性，如形状、轨迹和重量。准确估计这些属性需要使用扫描的三维对象模型或昂贵的设备，如运动捕捉系统和标记，或两者兼而有之。然而，用机器人测试切换算法可能会对人类造成危险，当物体是一个装有液体的开放容器时，也可能会对机器人造成危险。在这篇论文中，我们提出了一个真实到模拟的框架来开发安全的人与机器人之间的切换，通过对未知杯子或酒杯的物理特性的估计，以及从人类操纵容器的视频中对人手的估计。我们在模拟中完成了切换，并且我们估计了一个区域，该区域没有被手持容器的人的手遮挡。我们还量化了仿真中人和物体的安全性。我们使用在移交前操纵的容器的公开记录来验证该框架，并且在使用一系列感知算法的噪声估计时显示移交的安全性。 摘要：Safe human-to-robot handovers of unknown objects require accurate estimation of hand poses and object properties, such as shape, trajectory, and weight. Accurately estimating these properties requires the use of scanned 3D object models or expensive equipment, such as motion capture systems and markers, or both. However, testing handover algorithms with robots may be dangerous for the human and, when the object is an open container with liquids, for the robot. In this paper, we propose a real-to-simulation framework to develop safe human-to-robot handovers with estimations of the physical properties of unknown cups or drinking glasses and estimations of the human hands from videos of a human manipulating the container. We complete the handover in simulation, and we estimate a region that is not occluded by the hand of the human holding the container. We also quantify the safeness of the human and object in simulation. We validate the framework using public recordings of containers manipulated before a handover and show the safeness of the handover when using noisy estimates from a range of perceptual algorithms.

【23】 Breaking Barriers in Robotic Soft Tissue Surgery: Conditional Autonomous Intestinal Anastomosis 标题：机器人软组织手术中突破障碍的条件自主肠吻合术

作者：H. Saeidi,J. D. Opfermann,M. Kam,S. Wei,S. Leonard,M. H. Hsieh,J. U. Kang,A. Krieger 机构：Affiliations, Department of Mechanical Engineering, Johns Hopkins University; Baltimore, MD, Laboratory for Computational Sensing and Robotics, Johns Hopkins University;, Baltimore, MD , USA. 链接：https://arxiv.org/abs/2107.01288 摘要：自主机器人手术有潜力提供有效性，安全性和一致性独立于个体外科医生的技能和经验。非结构化和可变形环境下的自主软组织手术尤其具有挑战性，因为它需要复杂的成像、组织跟踪和手术计划技术，以及通过高度适应性的控制策略精确执行。在腹腔镜手术中，软组织手术更具挑战性，因为在运动和视觉限制下需要高的可操作性和可重复性。我们展示了第一个机器人腹腔镜软组织手术，其自主水平为3/5，允许操作者在自主生成的手术计划中进行选择，同时机器人独立执行各种任务。我们还展示了第一个在猪模型上通过肠吻合的在体自主机器人腹腔镜手术。我们比较了所开发系统、手动腹腔镜手术和机器人辅助手术（RAS）之间的标准，包括针位校正、缝线间距、缝线咬合大小、完成时间、管腔通畅度和漏压。离体实验结果表明，我们的系统在一致性和准确性方面优于专家外科医生和RAS技术，并使活体猪的吻合质量显著提高。这些结果表明，手术机器人表现出高度的自主性，有可能提高一致性，病人的结果，并获得一个标准的手术技术。 摘要：Autonomous robotic surgery has the potential to provide efficacy, safety, and consistency independent of individual surgeons skill and experience. Autonomous soft-tissue surgery in unstructured and deformable environments is especially challenging as it necessitates intricate imaging, tissue tracking and surgical planning techniques, as well as a precise execution via highly adaptable control strategies. In the laparoscopic setting, soft-tissue surgery is even more challenging due to the need for high maneuverability and repeatability under motion and vision constraints. We demonstrate the first robotic laparoscopic soft tissue surgery with a level of autonomy of 3 out of 5, which allows the operator to select among autonomously generated surgical plans while the robot executes a wide range of tasks independently. We also demonstrate the first in vivo autonomous robotic laparoscopic surgery via intestinal anastomosis on porcine models. We compared the criteria including needle placement corrections, suture spacing, suture bite size, completion time, lumen patency, and leak pressure between the developed system, manual laparoscopic surgery, and robot-assisted surgery (RAS). The ex vivo results indicate that our system outperforms expert surgeons and RAS techniques in terms of consistency and accuracy, and it leads to a remarkable anastomosis quality in living pigs. These results demonstrate that surgical robots exhibiting high levels of autonomy have the potential to improve consistency, patient outcomes, and access to a standard surgical technique.

【24】 Prescient teleoperation of humanoid robots 标题：仿人机器人的先知式遥操作

作者：Luigi Penco,Jean-Baptiste Mouret,Serena Ivaldi 机构： Inria Nancy – Grand Est, CNRS, Universit´e de Lorraine, France 备注：Video: this https URL 链接：https://arxiv.org/abs/2107.01281 摘要：仿人机器人可以是多功能和直观的人类化身，可以在不可接近的地方进行远程操作：机器人可以在远程位置再现配备了可穿戴运动捕捉设备的操作员的动作，同时向操作员发送视觉反馈。虽然在将人类运动转移到仿人机器人（“重定目标”）方面取得了实质性进展，妨碍此类系统在实际应用中部署的一个主要问题是，人的输入和机器人的反馈之间存在通信延迟：即使几百毫秒的延迟也会不可逆转地干扰操作员，更不用说几秒钟了。为了克服这些延迟，我们引入了一个系统，在该系统中，仿人机器人在实际接收到命令之前执行命令，因此视觉反馈似乎与操作员同步，而机器人在过去执行命令。为了做到这一点，机器人通过查询机器学习模型来不断预测未来的命令，该模型根据过去的轨迹进行训练，并以最后收到的命令为条件。在我们的实验中，一个操作者能够成功地控制一个仿人机器人（32个自由度），在几个全身操作任务中，包括到达不同的目标，捡起，在不同的位置放置一个盒子，随机延迟长达2秒。 摘要：Humanoid robots could be versatile and intuitive human avatars that operate remotely in inaccessible places: the robot could reproduce in the remote location the movements of an operator equipped with a wearable motion capture device while sending visual feedback to the operator. While substantial progress has been made on transferring ("retargeting") human motions to humanoid robots, a major problem preventing the deployment of such systems in real applications is the presence of communication delays between the human input and the feedback from the robot: even a few hundred milliseconds of delay can irreversibly disturb the operator, let alone a few seconds. To overcome these delays, we introduce a system in which a humanoid robot executes commands before it actually receives them, so that the visual feedback appears to be synchronized to the operator, whereas the robot executed the commands in the past. To do so, the robot continuously predicts future commands by querying a machine learning model that is trained on past trajectories and conditioned on the last received commands. In our experiments, an operator was able to successfully control a humanoid robot (32 degrees of freedom) with stochastic delays up to 2 seconds in several whole-body manipulation tasks, including reaching different targets, picking up, and placing a box at distinct locations.

【25】 Targeted Muscle Effort Distribution with Exercise Robots: Trajectory and Resistance Effects 标题：运动机器人的靶向肌肉力量分布：轨迹和阻力效应

作者：Humberto De las Casas,Santino Bianco,Hanz Richter 机构：Mechanical Engineering Department, Cleveland State University, Cleveland, OH , USA. 链接：https://arxiv.org/abs/2107.01280 摘要：这项工作的目的是将肌肉力量分布与机器人运动和康复机器的轨迹和阻力设置相关联。用肌电图传感器（EMG）测量代表每一块肌肉参与训练活动的肌肉力量分布，并将其定义为个体活动除以总肌肉群活动。一个四自由度机器人和它的阻抗控制系统被用来创建先进的运动协议，用户被要求按照机器的中立路径和阻力的路径。在这项工作中，机器人建立了一个零努力的圆形路径，并要求被试遵循一个椭圆形的轨迹。控制系统在偏离中性点路径和受试者施加的扭矩之间产生用户定义的刚度。实验中使用的轨迹和阻力设置是椭圆的方向和刚度参数。这些参数的多种组合被用来测量它们对肌肉力量分布的影响。人工神经网络（ANN）使用部分数据来训练模型。然后，利用其余数据对模型的精度进行了评价。结果表明，随着时间的推移，模型的精度是如何损失的。这些结果表明长期估计肌肉动力学的复杂性，表明存在可能与疲劳相关的时变动力学。 摘要：The objective of this work is to relate muscle effort distributions to the trajectory and resistance settings of a robotic exercise and rehabilitation machine. Muscular effort distribution, representing the participation of each muscle in the training activity, was measured with electromyography sensors (EMG) and defined as the individual activation divided by the total muscle group activation. A four degrees-of-freedom robot and its impedance control system are used to create advanced exercise protocols whereby the user is asked to follow a path against the machine's neutral path and resistance. In this work, the robot establishes a zero-effort circular path, and the subject is asked to follow an elliptical trajectory. The control system produces a user-defined stiffness between the deviations from the neutral path and the torque applied by the subject. The trajectory and resistance settings used in the experiments were the orientation of the ellipse and a stiffness parameter. Multiple combinations of these parameters were used to measure their effects on the muscle effort distribution. An artificial neural network (ANN) used part of the data for training the model. Then, the accuracy of the model was evaluated using the rest of the data. The results show how the precision of the model is lost over time. These outcomes show the complexity of the muscle dynamics for long-term estimations suggesting the existence of time-varying dynamics possibly associated with fatigue.

【26】 Accelerating Kinodynamic RRT* Through Dimensionality Reduction 标题：通过降维加速运动动力学RRT*

作者：Dongliang Zheng,Panagiotis Tsiotras 机构： which is a non-trivial undertakingThis work has been supported by NSF awards IIS- 16 176 30 and IIS- 200869 5 1Dongliang Zheng is with School of Aerospace Engineering 链接：https://arxiv.org/abs/2107.01259 摘要：基于采样的运动规划算法，如RRT*以其快速找到初始解然后渐近收敛到最优解的能力而闻名。然而，对于高维规划问题，特别是采样空间不仅是配置空间，而且是全状态空间的动态系统，收敛速度会很慢。本文在kinodynamic RRT*[1]中引入部分终态自由（PFF）最优控制器的思想来降低采样空间的维数。提出的加速Kino-RRT*算法不需要对整个状态空间进行采样，只对部分状态空间进行采样，其余状态由PFF最优控制器选择。为了降低算法的计算复杂度，我们还提出了对RRT*树中所有边的最佳到达时间进行延迟和间歇更新的方法。我们用4维和10维状态空间线性系统对该算法进行了测试，结果表明Kino-RRT*算法比kinodynamic-RRT*算法收敛速度快得多。 摘要：Sampling-based motion planning algorithms such as RRT* are well-known for their ability to quickly find an initial solution and then converge to the optimal solution asymptotically. However, the convergence rate can be slow for highdimensional planning problems, particularly for dynamical systems where the sampling space is not just the configuration space but the full state space. In this paper, we introduce the idea of using a partial-final-state-free (PFF) optimal controller in kinodynamic RRT* [1] to reduce the dimensionality of the sampling space. Instead of sampling the full state space, the proposed accelerated kinodynamic RRT*, called Kino-RRT*, only samples part of the state space, while the rest of the states are selected by the PFF optimal controller. We also propose a delayed and intermittent update of the optimal arrival time of all the edges in the RRT* tree to decrease the computation complexity of the algorithm. We tested the proposed algorithm using 4-D and 10-D state-space linear systems and showed that Kino-RRT* converges much faster than the kinodynamic RRT* algorithm.

【27】 Third Party Risk Modelling and Assessment for Safe UAV Path Planning in Metropolitan Environments 标题：大城市环境下无人机安全航迹规划的第三方风险建模与评估

作者：Bizhao Pang,Xinting Hu,Wei Dai,Kin Huat Low 机构：a School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore , Singapore, b School of Air Traffic Management, Civil Aviation University of China, Tianjin , China 链接：https://arxiv.org/abs/2107.01834 摘要：先进空中交通（AAM）在城市环境中的各种应用促进了我们的日常生活和公共服务。路径规划问题是自主实现这些应用的关键问题之一，研究的主要目标是使旅行距离、飞行时间和能量消耗最小化。然而，空空导弹在大都市地区的运行带来了安全和社会问题。因为大多数空空导弹飞机是无人机（UAV），它们可能无法运行，从而对公众造成死亡风险、财产损失风险和社会影响（噪音和隐私）。为了定量地评估这些风险并在规划阶段减轻风险，本文提出了一种综合风险评估模型，并提出了一种混合算法来解决基于风险的三维路径规划问题。综合风险评估方法考虑了无人机撞击地面人员和车辆的概率和严重度模型。通过引入引力模型，对人口密度和交通密度进行了更精细的估计，使风险评估更为准确。首先将基于风险的三维路径规划问题描述为一个特殊的最小费用流问题。在此基础上，提出了一种混合分布估计算法（EDA）和基于风险的a*（称为EDA-RA*）算法。为了提高计算效率，将k-means聚类方法引入EDA-RA*算法中，提供全局和局部搜索的启发式信息，形成了EDA算法和基于风险的快速A*算法。实例分析结果表明，该风险评估模型能够捕捉高风险区域，生成的风险地图能够实现城市复杂环境下无人机的安全路径规划。 摘要：Various applications of advanced air mobility (AAM) in urban environments facilitate our daily life and public services. As one of the key issues of realizing these applications autonomously, path planning problem has been studied with main objectives on minimizing travel distance, flight time and energy cost. However, AAM operations in metropolitan areas bring safety and society issues. Because most of AAM aircraft are unmanned aerial vehicles (UAVs) and they may fail to operate resulting in fatality risk, property damage risk and societal impacts (noise and privacy) to the public. To quantitatively assess these risks and mitigate them in planning phase, this paper proposes an integrated risk assessment model and develops a hybrid algorithm to solve the risk-based 3D path planning problem. The integrated risk assessment method considers probability and severity models of UAV impact ground people and vehicle. By introducing gravity model, the population density and traffic density are estimated in a finer scale, which enables more accurate risk assessment. The 3D risk-based path planning problem is first formulated as a special minimum cost flow problem. Then, a hybrid estimation of distribution algorithm (EDA) and risk-based A* (named as EDA-RA*) algorithm is proposed to solve the problem. To improve computational efficiency, k-means clustering method is incorporated into EDA-RA* to provide both global and local search heuristic information, which formed the EDA and fast risk-based A* algorithm we call EDA-FRA*. Case study results show that the risk assessment model can capture high risk areas and the generated risk map enables safe UAV path planning in urban complex environments.