机器人相关学术速递[12.20]

cs.RO机器人相关，共计8篇

【1】 Neuromorphic Camera Denoising using Graph Neural Network-driven Transformers 标题：基于图神经网络驱动Transformer的神经形态摄像机去噪 链接：https://arxiv.org/abs/2112.09685

作者：Yusra Alkendi,Rana Azzam,Abdulla Ayyad,Sajid Javed,Lakmal Seneviratne,Yahya Zweiri 摘要：神经形态视觉是一种受生物启发的技术，它引发了计算机视觉领域的范式转变，并成为众多应用的关键促成因素。这项技术具有显著的优势，包括降低功耗、减少处理需求和提高通信速度。然而，神经形态摄像机受到大量测量噪声的影响。这种噪声会恶化基于神经形态事件的感知和导航算法的性能。在本文中，我们提出了一种新的噪声过滤算法来消除观测场景中不代表真实对数强度变化的事件。我们采用一种图形神经网络（GNN）驱动的变换算法，称为GNN变换，将原始流中的每个活动事件像素分类为真实的对数强度变化或噪声。在GNN中，执行了一个称为EventConv的消息传递框架，以反映事件之间的时空相关性，同时保留其异步性质。我们还介绍了已知物体地面真值标记（KoGTL）方法，用于在各种照明条件下生成事件流的近似地面真值标记。KoGTL用于根据在具有挑战性的光照条件下记录的实验生成标记数据集。这些数据集用于训练和广泛测试我们提出的算法。当在看不见的数据集上测试时，所提出的算法在过滤精度方面比现有方法高12%。此外，还对公开的数据集进行了额外的测试，以证明该算法在存在光照变化和不同运动动力学的情况下的泛化能力。与现有的解决方案相比，定性结果验证了该算法在保留有意义的场景事件的同时消除噪声的优越性。 摘要：Neuromorphic vision is a bio-inspired technology that has triggered a paradigm shift in the computer-vision community and is serving as a key-enabler for a multitude of applications. This technology has offered significant advantages including reduced power consumption, reduced processing needs, and communication speed-ups. However, neuromorphic cameras suffer from significant amounts of measurement noise. This noise deteriorates the performance of neuromorphic event-based perception and navigation algorithms. In this paper, we propose a novel noise filtration algorithm to eliminate events which do not represent real log-intensity variations in the observed scene. We employ a Graph Neural Network (GNN)-driven transformer algorithm, called GNN-Transformer, to classify every active event pixel in the raw stream into real-log intensity variation or noise. Within the GNN, a message-passing framework, called EventConv, is carried out to reflect the spatiotemporal correlation among the events, while preserving their asynchronous nature. We also introduce the Known-object Ground-Truth Labeling (KoGTL) approach for generating approximate ground truth labels of event streams under various illumination conditions. KoGTL is used to generate labeled datasets, from experiments recorded in challenging lighting conditions. These datasets are used to train and extensively test our proposed algorithm. When tested on unseen datasets, the proposed algorithm outperforms existing methods by 12% in terms of filtration accuracy. Additional tests are also conducted on publicly available datasets to demonstrate the generalization capabilities of the proposed algorithm in the presence of illumination variations and different motion dynamics. Compared to existing solutions, qualitative results verified the superior capability of the proposed algorithm to eliminate noise while preserving meaningful scene events.

【2】 An Online Data-Driven Emergency-Response Method for Autonomous Agents in Unforeseen Situations 标题：一种数据驱动的自治Agent在不可预见情况下的在线应急响应方法 链接：https://arxiv.org/abs/2112.09670

作者：Glenn Maguire,Nicholas Ketz,Praveen Pilly,Jean-Baptiste Mouret 机构： Inria, CNRS, Universit´e de Lorraine, Center for Human-Machine Collaboration, Information and Systems Sciences Laboratory, HRL Laboratories 摘要：强化学习代理在训练过程中遇到的输入分布中表现良好。然而，在他们接受额外训练之前，他们无法在面对新的发行外事件时做出有效反应。本文提出了一种在线、数据驱动的应急响应方法，旨在为自治代理提供对意外情况作出反应的能力，这些意外情况与它所训练或设计用于解决的情况大不相同。在这种情况下，由于在这些新情况下获得的观察结果不在代理优化处理的输入分布范围内，因此无法期望学习到的策略能够正确执行。所提出的方法通过选择使可变自动编码器的重建误差增加率最小化的操作来设计对不可预见情况的定制响应。使用改进的贝叶斯优化程序，以数据高效的方式（大约30个数据点）在线实现此优化。我们在一个模拟的3D汽车驾驶场景中展示了这种方法的潜力，在该场景中，agent在2秒内设计出一个响应，以避免与训练期间未看到的物体发生碰撞。 摘要：Reinforcement learning agents perform well when presented with inputs within the distribution of those encountered during training. However, they are unable to respond effectively when faced with novel, out-of-distribution events, until they have undergone additional training. This paper presents an online, data-driven, emergency-response method that aims to provide autonomous agents the ability to react to unexpected situations that are very different from those it has been trained or designed to address. In such situations, learned policies cannot be expected to perform appropriately since the observations obtained in these novel situations would fall outside the distribution of inputs that the agent has been optimized to handle. The proposed approach devises a customized response to the unforeseen situation sequentially, by selecting actions that minimize the rate of increase of the reconstruction error from a variational auto-encoder. This optimization is achieved online in a data-efficient manner (on the order of 30 data-points) using a modified Bayesian optimization procedure. We demonstrate the potential of this approach in a simulated 3D car driving scenario, in which the agent devises a response in under 2 seconds to avoid collisions with objects it has not seen during training.

【3】 Autonomous Reinforcement Learning: Formalism and Benchmarking 标题：自主强化学习：形式主义与标杆 链接：https://arxiv.org/abs/2112.09605

作者：Archit Sharma,Kelvin Xu,Nikhil Sardana,Abhishek Gupta,Karol Hausman,Sergey Levine,Chelsea Finn 机构：Stanford University, University of California, Berkeley, MIT, Google Brain 摘要：强化学习（RL）提供了一种通过尝试和错误进行学习的自然主义框架，它既简单有效，又与人类和动物通过经验获得技能的方式相似，因此极具吸引力。然而，真实世界的具体化学习，如人类和动物所执行的学习，处于一个连续的、非情节的世界中，而RL中的常见基准任务是情节性的，在试验之间重新设置环境，为代理提供多次尝试。当尝试采用为情景模拟环境开发的RL算法并在现实平台（如机器人）上运行时，这种差异是一个重大挑战。在本文中，我们旨在通过构建一个自主强化学习（ARL）框架来解决这一差异：强化学习，其中代理不仅通过自己的经验进行学习，而且还与缺乏人类监督的情况相抗衡，以在试验之间重置。我们围绕这个框架引入了一个模拟基准EARL，其中包含了一组多样且具有挑战性的模拟任务，这些任务反映了学习中引入的障碍，而此时只能假设对外部干预的依赖最小。我们表明，随着干预措施的减少，情景学习的标准方法和现有方法都会遇到困难，强调需要开发新的强化学习算法，更加注重自主性。 摘要：Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills through experience. However, real-world embodied learning, such as that performed by humans and animals, is situated in a continual, non-episodic world, whereas common benchmark tasks in RL are episodic, with the environment resetting between trials to provide the agent with multiple attempts. This discrepancy presents a major challenge when attempting to take RL algorithms developed for episodic simulated environments and run them on real-world platforms, such as robots. In this paper, we aim to address this discrepancy by laying out a framework for Autonomous Reinforcement Learning (ARL): reinforcement learning where the agent not only learns through its own experience, but also contends with lack of human supervision to reset between trials. We introduce a simulated benchmark EARL around this framework, containing a set of diverse and challenging simulated tasks reflective of the hurdles introduced to learning when only a minimal reliance on extrinsic intervention can be assumed. We show that standard approaches to episodic RL and existing approaches struggle as interventions are minimized, underscoring the need for developing new algorithms for reinforcement learning with a greater focus on autonomy.

【4】 A controller for reaching and unveiling a partially occluded object of interest with an eye-in-hand robot 标题：用于用手眼机器人到达并揭开部分遮挡的感兴趣对象的控制器 链接：https://arxiv.org/abs/2112.09487

作者：Dimitrios Papageorgiou,Leonidas Koutras,Zoe Doulgeri 机构： Aristotle University of Thessaloniki 摘要：在这项工作中，提出了一种接近和揭示部分遮挡感兴趣对象的控制方案。该控制方案仅基于连接到机器人末端执行器的手持摄像机获得的分类点云。结果表明，所提出的控制器在目标附近逐渐到达目标的每个可见点的邻域。因此，它有可能实现物体的完全揭幕。所提出的控制方案是通过一个UR5e机器人的仿真和实验来评估的，该机器人在一个模拟藤蔓装置上带有一个手持式RealSense摄像头，用于揭幕葡萄茎。 摘要：In this work, a control scheme for approaching and unveiling a partially occluded object of interest is proposed.The control scheme is based only on the classified point cloud obtained by the in-hand camera attached to the robot's end effector. It is shown that the proposed controller reaches in the vicinity of the object progressively unveiling the neighborhood of each visible point of the object of interest. It can therefore potentially achieve the complete unveiling of the object. The proposed control scheme is evaluated through simulations and experiments with a UR5e robot with an in-hand RealSense camera on a mock-up vine setup for unveiling the stem of a grape.

【5】 Visual Learning-based Planning for Continuous High-Dimensional POMDPs 标题：基于可视化学习的连续高维POMDP规划 链接：https://arxiv.org/abs/2112.09456

作者：Sampada Deglurkar,Michael H. Lim,Johnathan Tucker,Zachary N. Sunberg,Aleksandra Faust,Claire J. Tomlin 机构：Department of Electrical Engineering and Computer Sciences, UC Berkeley, Department of Aerospace Engineering Science, CU Boulder, Google Research 摘要：部分可观测马尔可夫决策过程（POMDP）是一个强大的框架，用于捕获涉及状态和转移不确定性的决策问题。然而，目前大多数POMDP规划者无法有效处理他们在现实世界中经常遇到的高维观测（例如机器人领域中的图像观测）。在这项工作中，我们提出了可视化树搜索（VTS），这是一种学习和规划过程，将离线学习的生成模型与在线基于模型的POMDP规划相结合。VTS通过利用一组深度生成观测模型在蒙特卡罗树搜索规划器中预测和评估图像观测的可能性，将离线模型训练和在线规划联系起来。我们证明了VTS对不同的观测噪声具有鲁棒性，并且由于它采用了在线、基于模型的规划，可以适应不同的奖励结构，而无需重新训练。这种新方法在策略规划算法方面优于最新的基线状态，同时显著减少了离线训练时间。 摘要：The Partially Observable Markov Decision Process (POMDP) is a powerful framework for capturing decision-making problems that involve state and transition uncertainty. However, most current POMDP planners cannot effectively handle very high-dimensional observations they often encounter in the real world (e.g. image observations in robotic domains). In this work, we propose Visual Tree Search (VTS), a learning and planning procedure that combines generative models learned offline with online model-based POMDP planning. VTS bridges offline model training and online planning by utilizing a set of deep generative observation models to predict and evaluate the likelihood of image observations in a Monte Carlo tree search planner. We show that VTS is robust to different observation noises and, since it utilizes online, model-based planning, can adapt to different reward structures without the need to re-train. This new approach outperforms a baseline state-of-the-art on-policy planning algorithm while using significantly less offline training time.

【6】 Scenario-Based Safety Assessment Framework for Automated Vehicles 标题：基于情景的自动车辆安全评价框架 链接：https://arxiv.org/abs/2112.09366

作者：J. Ploeg,E. de Gelder,M. Slavík,E. Querner,T. Webster,N. de Boer 机构： Singapore 3 Nanyang Technological University 备注：None 摘要：自动化车辆（AV）有望通过实现灵活的随需应变移动系统，提高交通安全和交通效率。这在新加坡尤其重要，因为新加坡是世界上人口最密集的国家之一，这就是为什么新加坡当局目前正在积极推动AVs的部署。然而，因此，需要一个正式的AV道路批准程序。为此，提出了一个安全评估框架，该框架将标准化功能安全设计方法与基于交通场景的方法相结合。后者涉及使用驾驶数据提取与AV相关的交通场景。基本方法基于将场景分解为基本事件、后续场景参数化以及对场景参数的估计概率密度函数进行采样，以创建测试场景。生成的测试场景随后用于模拟环境中的虚拟测试以及试验场和现实生活中的物理测试。因此，由于基于模拟的方法，拟议的评估管道因此在相对较短的时间内为AV性能提供了统计相关和定量的度量。最终，建议的方法为当局提供了AVs的正式道路批准程序。特别是，建议的方法将支持新加坡陆路运输局对AVs进行道路批准。 摘要：Automated vehicles (AVs) are expected to increase traffic safety and traffic efficiency, among others by enabling flexible mobility-on-demand systems. This is particularly important in Singapore, being one of the world's most densely populated countries, which is why the Singaporean authorities are currently actively facilitating the deployment of AVs. As a consequence, however, the need arises for a formal AV road approval procedure. To this end, a safety assessment framework is proposed, which combines aspects of the standardized functional safety design methodology with a traffic scenario-based approach. The latter involves using driving data to extract AV-relevant traffic scenarios. The underlying approach is based on decomposition of scenarios into elementary events, subsequent scenario parametrization, and sampling of the estimated probability density functions of the scenario parameters to create test scenarios. The resulting test scenarios are subsequently employed for virtual testing in a simulation environment and physical testing on a proving ground and in real life. As a result, the proposed assessment pipeline thus provides statistically relevant and quantitative measures for the AV performance in a relatively short time frame due to the simulation-based approach. Ultimately, the proposed methodology provides authorities with a formal road approval procedure for AVs. In particular, the proposed methodology will support the Singaporean Land Transport Authority for road approval of AVs.

【7】 Automated stability testing of elastic rods with helical centerlines using a robotic system 标题：基于机器人系统的螺旋线弹性杆稳定性自动测试 链接：https://arxiv.org/abs/2112.09208

作者：Dezhong Tong,Andy Borum,M. Khalid Jawed 机构： 1Department of Mechanical & Aerospace Engineering, University of Cal-ifornia, CA 9009 5 2Department of Engineering, Hofstra University 备注：Supplementary video is available at this https URL 摘要：可变形物体力学的实验分析，特别是其稳定性，需要重复测试，并且根据物体形状的复杂性，需要一个可以在物体边界操纵多个自由度的测试装置。受机器人操纵可变形物体最新进展的推动，本文通过构建一种使用机器人系统对细长弹性杆（可变形物体的典型示例）进行自动稳定性测试的方法，解决了这些挑战。我们关注具有螺旋中心线的杆配置，因为螺旋杆的稳定性只能用三个参数来描述，但通过实验确定稳定性需要操纵杆一端的位置和方向，这是不可能使用传统的实验方法，只驱动有限的自由度。利用螺旋杆稳定性的最新几何特征，我们构建并实现了一个操纵方案，以探索稳定螺旋的空间，并使用视觉系统检测该空间内不稳定性的开始。我们的自动测试系统得到的实验结果与螺旋结构中弹性杆的数值模拟结果吻合良好。本文描述的方法为自动化在实验力学领域的发展奠定了基础。 摘要：Experimental analysis of the mechanics of a deformable object, and particularly its stability, requires repetitive testing and, depending on the complexity of the object's shape, a testing setup that can manipulate many degrees of freedom at the object's boundary. Motivated by recent advancements in robotic manipulation of deformable objects, this paper addresses these challenges by constructing a method for automated stability testing of a slender elastic rod -- a canonical example of a deformable object -- using a robotic system. We focus on rod configurations with helical centerlines since the stability of a helical rod can be described using only three parameters, but experimentally determining the stability requires manipulation of both the position and orientation at one end of the rod, which is not possible using traditional experimental methods that only actuate a limited number of degrees of freedom. Using a recent geometric characterization of stability for helical rods, we construct and implement a manipulation scheme to explore the space of stable helices, and we use a vision system to detect the onset of instabilities within this space. The experimental results obtained by our automated testing system show good agreement with numerical simulations of elastic rods in helical configurations. The methods described in this paper lay the groundwork for automation to grow within the field of experimental mechanics.

【8】 Intermittent Deployment for Large-Scale Multi-Robot Forage Perception: Data Synthesis, Prediction, and Planning 标题：大规模多机器人牧草感知的间歇部署：数据合成、预测和规划 链接：https://arxiv.org/abs/2112.09203

作者：Jun Liu,Murtaza Rangwala,Kulbir Singh Ahluwalia,Shayan Ghajar,Harnaik Singh Dhami,Pratap Tokekar,Benjamin F. Tracy,Ryan K. Williams 机构： 2The author is with the Department of Agriculture and Biological Engi-neering, University of Illinois, 3The author is with the Department of Crop and Soil Science, Oregon StateUniversity 备注：21 pages, 26 figures, submitted to IEEE Transactions on Automation Science and Engineering 摘要：监测草原的健康和活力对于指导管理决策，优化农业应用中的轮牧至关重要。为了充分利用牧草资源，提高土地生产力，我们需要了解牧场的生长模式，而这在目前的技术水平上是不可能的。在本文中，我们建议部署一组机器人来监测未知牧场环境的演变，以实现上述目标。为了监测这种通常进展缓慢的环境，我们需要设计一种以低成本快速评估大面积环境的战略。因此，我们提出了一个集成的管道，包括数据合成、深度神经网络训练和预测，以及间歇监测牧场的多机器人部署算法。具体地说，我们首先利用ROS Gazebo中的专家信息农业数据和新的数据合成，提出了一种新的神经网络结构来学习环境的时空动态。这些预测有助于我们大规模了解牧场增长模式，并为未来做出适当的监测决策。基于我们的预测，我们设计了一种用于低成本监控的间歇式多机器人部署策略。最后，我们将提出的管道与其他方法进行比较，从数据合成到预测和规划，以验证我们管道的性能。 摘要：Monitoring the health and vigor of grasslands is vital for informing management decisions to optimize rotational grazing in agriculture applications. To take advantage of forage resources and improve land productivity, we require knowledge of pastureland growth patterns that is simply unavailable at state of the art. In this paper, we propose to deploy a team of robots to monitor the evolution of an unknown pastureland environment to fulfill the above goal. To monitor such an environment, which usually evolves slowly, we need to design a strategy for rapid assessment of the environment over large areas at a low cost. Thus, we propose an integrated pipeline comprising of data synthesis, deep neural network training and prediction along with a multi-robot deployment algorithm that monitors pasturelands intermittently. Specifically, using expert-informed agricultural data coupled with novel data synthesis in ROS Gazebo, we first propose a new neural network architecture to learn the spatiotemporal dynamics of the environment. Such predictions help us to understand pastureland growth patterns on large scales and make appropriate monitoring decisions for the future. Based on our predictions, we then design an intermittent multi-robot deployment policy for low-cost monitoring. Finally, we compare the proposed pipeline with other methods, from data synthesis to prediction and planning, to corroborate our pipeline's performance.

机器翻译，仅供参考