机器人相关学术速递[12.8]

cs.RO机器人相关，共计16篇

【1】 Causal Imitative Model for Autonomous Driving 标题：自动驾驶的因果模拟模型 链接：https://arxiv.org/abs/2112.03908

作者：Mohammad Reza Samsami,Mohammadhossein Bahari,Saber Salehkaleybar,Alexandre Alahi 机构：Sharif University of Tech., EPFL 摘要：模仿学习是一种利用专家驾驶员演示数据学习自主驾驶策略的强大方法。然而，通过模仿学习训练的驾驶策略忽略了专家演示的因果结构，从而产生了两种不良行为：惯性和碰撞。在本文中，我们提出了因果模拟模型（CIM）来解决惯性和碰撞问题。CIM明确地发现因果模型并利用它来训练策略。具体而言，CIM将输入分解为一组潜在变量，选择因果变量，并通过利用所选变量确定下一个位置。我们的实验表明，我们的方法在惯性和碰撞率方面优于以前的工作。此外，由于利用了因果结构，CIM将输入维度缩减为仅两个维度，因此，可以在几次拍摄设置中适应新环境。代码可在https://github.com/vita-epfl/CIM. 摘要：Imitation learning is a powerful approach for learning autonomous driving policy by leveraging data from expert driver demonstrations. However, driving policies trained via imitation learning that neglect the causal structure of expert demonstrations yield two undesirable behaviors: inertia and collision. In this paper, we propose Causal Imitative Model (CIM) to address inertia and collision problems. CIM explicitly discovers the causal model and utilizes it to train the policy. Specifically, CIM disentangles the input to a set of latent variables, selects the causal variables, and determines the next position by leveraging the selected variables. Our experiments show that our method outperforms previous work in terms of inertia and collision rates. Moreover, thanks to exploiting the causal structure, CIM shrinks the input dimension to only two, hence, can adapt to new environments in a few-shot setting. Code is available at https://github.com/vita-epfl/CIM.

【2】 Policy Search for Model Predictive Control with Application to Agile Drone Flight 标题：模型预测控制策略研究及其在敏捷无人机飞行中的应用 链接：https://arxiv.org/abs/2112.03850

作者：Yunlong Song,Davide Scaramuzza 机构： University of Zurich, and Department of Neuroinformatics, University of Zurich and ETH Zurich 备注：This paper is currently under review TRO 摘要：策略搜索和模型预测控制（MPC）是机器人控制的两种不同模式：策略搜索具有利用经验数据自动学习复杂策略的能力，而MPC可以利用模型和轨迹优化提供最优控制性能。一个开放的研究问题是如何利用和结合这两种方法的优势。在这项工作中，我们通过使用策略搜索为MPC自动选择高层决策变量来提供答案，从而为模型预测控制框架提供了一种新的策略搜索。具体来说，我们将MPC描述为一个参数化控制器，其中难以优化的决策变量表示为高级策略。这样的公式允许以自我监督的方式优化策略。我们通过关注敏捷无人机飞行中的一个具有挑战性的问题来验证这个框架：让四旋翼机通过快速移动的闸门。实验结果表明，该控制器在仿真和实际应用中均具有良好的鲁棒性和实时性。该框架为学习和控制的融合提供了一个新的视角。 摘要：Policy Search and Model Predictive Control~(MPC) are two different paradigms for robot control: policy search has the strength of automatically learning complex policies using experienced data, while MPC can offer optimal control performance using models and trajectory optimization. An open research question is how to leverage and combine the advantages of both approaches. In this work, we provide an answer by using policy search for automatically choosing high-level decision variables for MPC, which leads to a novel policy-search-for-model-predictive-control framework. Specifically, we formulate the MPC as a parameterized controller, where the hard-to-optimize decision variables are represented as high-level policies. Such a formulation allows optimizing policies in a self-supervised fashion. We validate this framework by focusing on a challenging problem in agile drone flight: flying a quadrotor through fast-moving gates. Experiments show that our controller achieves robust and real-time control performance in both simulation and the real world. The proposed framework offers a new perspective for merging learning and control.

【3】 Hybrid Visual SLAM for Underwater Vehicle Manipulator Systems 标题：水下机器人机械臂系统的混合视觉SLAM 链接：https://arxiv.org/abs/2112.03826

作者：Gideon Billings,Richard Camilli,Matthew Johnson-Roberson 机构： 1Gideon Billings and Matthew Johnson-Roberson are with Department ofNaval Architecture and Marine Engineering, University of Michigan 备注：This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 摘要：本文提出了一种新的水下航行器机械手系统（UVMSs）视觉场景映射方法，特别强调了自然海底环境中的鲁棒映射。以前的水下场景映射方法通常离线处理数据，而现有的实时水下SLAM方法通常侧重于定位而不是映射。我们的方法使用图形优化框架中的GPU加速SIFT特征来构建特征图。地图比例受车载立体摄像头的特征约束，我们通过将腕式鱼眼摄像头的特征融合到地图中，将其扩展到车载摄像头的有限视点之外，从而利用机械手系统的动态定位能力。我们的混合SLAM方法是在哥斯达黎加大陆架边缘自然深海海底环境中用UVMS采集的具有挑战性的图像序列上进行评估的，我们还评估了浅礁调查数据集上的仅立体模式。这些数据集的结果表明，我们的系统具有较高的准确性，适合在不同的自然海底环境中运行。 摘要：This paper presents a novel visual scene mapping method for underwater vehicle manipulator systems (UVMSs), with specific emphasis on robust mapping in natural seafloor environments. Prior methods for underwater scene mapping typically process the data offline, while existing underwater SLAM methods that run in real-time are generally focused on localization and not mapping. Our method uses GPU accelerated SIFT features in a graph optimization framework to build a feature map. The map scale is constrained by features from a vehicle mounted stereo camera, and we exploit the dynamic positioning capability of the manipulator system by fusing features from a wrist mounted fisheye camera into the map to extend it beyond the limited viewpoint of the vehicle mounted cameras. Our hybrid SLAM method is evaluated on challenging image sequences collected with a UVMS in natural deep seafloor environments of the Costa Rican continental shelf margin, and we also evaluate the stereo only mode on a shallow reef survey dataset. Results on these datasets demonstrate the high accuracy of our system and suitability for operating in diverse and natural seafloor environments.

【4】 A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops 标题：一种深度学习驱动的行间作物自主导航算法流水线 链接：https://arxiv.org/abs/2112.03816

作者：Simone Cerrato,Vittorio Mazzia,Francesco Salvetti,Marcello Chiaberge 备注：Submitted to IEEE/ASME Transactions on Mechatronics (TMECH) 摘要：昂贵的传感器和低效的算法管道极大地影响了自主机器的总体成本。然而，负担得起的机器人解决方案对于实际使用至关重要，它们的财务影响构成了在大多数应用领域使用服务机器人的基本要求。其中，精准农业领域的研究人员致力于设计健壮且经济高效的自主平台，以提供真正大规模的有竞争力的解决方案。在本文中，我们为基于行的作物自主导航提供了一个完整的算法管道，专门设计用于处理低范围传感器和季节变化。首先，我们建立了一种稳健的数据驱动方法，为自主机器生成可行的路径，仅使用田间占用栅格地图信息覆盖作物的全部延伸。此外，我们的解决方案利用了深度学习优化技术和数据合成的最新进展，提供了一个经济实惠的解决方案，有效解决了众所周知的全球导航卫星系统因行间植被生长而导致的不可靠性和退化问题。针对计算机生成的环境和真实世界的作物进行的大量实验和模拟表明，我们的方法具有鲁棒性和内在的通用性，这为价格合理且完全自主的机器提供了可能性。 摘要：Expensive sensors and inefficient algorithmic pipelines significantly affect the overall cost of autonomous machines. However, affordable robotic solutions are essential to practical usage, and their financial impact constitutes a fundamental requirement to employ service robotics in most fields of application. Among all, researchers in the precision agriculture domain strive to devise robust and cost-effective autonomous platforms in order to provide genuinely large-scale competitive solutions. In this article, we present a complete algorithmic pipeline for row-based crops autonomous navigation, specifically designed to cope with low-range sensors and seasonal variations. Firstly, we build on a robust data-driven methodology to generate a viable path for the autonomous machine, covering the full extension of the crop with only the occupancy grid map information of the field. Moreover, our solution leverages on latest advancement of deep learning optimization techniques and synthetic generation of data to provide an affordable solution that efficiently tackles the well-known Global Navigation Satellite System unreliability and degradation due to vegetation growing inside rows. Extensive experimentation and simulations against computer-generated environments and real-world crops demonstrated the robustness and intrinsic generalizability of our methodology that opens the possibility of highly affordable and fully autonomous machines.

【5】 Bridging the Model-Reality Gap with Lipschitz Network Adaptation 标题：用Lipschitz网络自适应弥合模型与现实的鸿沟 链接：https://arxiv.org/abs/2112.03756

作者：Siqi Zhou,Karime Pereida,Wenda Zhao,Angela P. Schoellig 机构： University of Toronto 备注：None 摘要：当机器人冒险进入现实世界时，它们会受到未建模动力学和干扰的影响。传统的基于模型的控制方法在相对静态和已知的操作环境中已被证明是成功的。然而，当机器人的精确模型不可用时，基于模型的设计可能导致次优甚至不安全的行为。在这项工作中，我们提出了一种方法，弥补了模型与现实之间的差距，并使基于模型的方法得以应用，即使存在动态不确定性。特别是，我们提出了一种基于学习的模型参考自适应方法，使可能具有不确定动力学的机器人系统表现为预定义的参考模型。反过来，参考模型可用于基于模型的控制器设计。与典型的模型参考自适应控制方法相比，我们利用神经网络的代表性功能，通过在一种称为Lipschitz网络的特殊类型神经网络的结构设计中编码一个证明Lipschitz条件来捕获高度非线性的动态不确定性并保证稳定性。我们的方法适用于一类一般的非线性仿射控制系统，即使我们对真实机器人系统的先验知识是有限的。我们在飞行倒立摆实验中演示了我们的方法，其中一个现成的四旋翼在悬停或跟踪圆形轨迹时面临平衡倒立摆的挑战。 摘要：As robots venture into the real world, they are subject to unmodeled dynamics and disturbances. Traditional model-based control approaches have been proven successful in relatively static and known operating environments. However, when an accurate model of the robot is not available, model-based design can lead to suboptimal and even unsafe behaviour. In this work, we propose a method that bridges the model-reality gap and enables the application of model-based approaches even if dynamic uncertainties are present. In particular, we present a learning-based model reference adaptation approach that makes a robot system, with possibly uncertain dynamics, behave as a predefined reference model. In turn, the reference model can be used for model-based controller design. In contrast to typical model reference adaptation control approaches, we leverage the representative power of neural networks to capture highly nonlinear dynamics uncertainties and guarantee stability by encoding a certifying Lipschitz condition in the architectural design of a special type of neural network called the Lipschitz network. Our approach applies to a general class of nonlinear control-affine systems even when our prior knowledge about the true robot system is limited. We demonstrate our approach in flying inverted pendulum experiments, where an off-the-shelf quadrotor is challenged to balance an inverted pendulum while hovering or tracking circular trajectories.

【6】 Adaptive Mimic: Deep Reinforcement Learning of Parameterized Bipedal Walking from Infeasible References 标题：自适应模拟：基于不可行解的参数化两足步行的深度强化学习 链接：https://arxiv.org/abs/2112.03735

作者：Chong Zhang,Qi Wu,Liqian Ma,Hongyuan Su 机构：Department of Precision Instrument, Tsinghua University, Beijing, China., Department of Mechanical Engineering, Tsinghua University, Beijing, China., Department of Electronic Engineering, Tsinghua University, Beijing, China. 备注：12pages, 8 figures 摘要：直到最近，通过深度强化学习（DRL）实现了机器人的鲁棒运动。然而，为了有效地学习参数化两足步行，通常需要开发参考文献，将性能限制在参考文献的性能范围内。在本文中，我们建议设计一个自适应的奖励函数，用于模仿学习。鼓励代理在其性能较低时模仿引用，而在达到引用限制时追求高性能。我们进一步证明，只要能够提供先验知识以加快学习过程，开发的参考就可以被低质量的参考所取代，这些低质量的参考是在不费力调整的情况下生成的，并且不可能自己部署。 摘要：Not until recently, robust robot locomotion has been achieved by deep reinforcement learning (DRL). However, for efficient learning of parametrized bipedal walking, developed references are usually required, limiting the performance to that of the references. In this paper, we propose to design an adaptive reward function for imitation learning from the references. The agent is encouraged to mimic the references when its performance is low, while to pursue high performance when it reaches the limit of references. We further demonstrate that developed references can be replaced by low-quality references that are generated without laborious tuning and infeasible to deploy by themselves, as long as they can provide a priori knowledge to expedite the learning process.

【7】 A low-cost wave-solar powered Unmanned Surface Vehicle 标题：一种低成本的波浪太阳能无人水面航行器 链接：https://arxiv.org/abs/2112.03685

作者：Moustafa Elkolali,Ahmed Al-Tawil,Lennard Much,Ryan Schrader,Olivier Masset,Marina Sayols,Andrew Jenkins,Sara Alonso,Alfredo Carella,Alex Alcocer 机构：Department of Mechanical, Electronic and Chemical, Oslo Metropolitan, Oslo, Norway, Electronic Engineering, Department, Universitat, Politècnica de Catalunya, Barcelona, Spain, Engineering, Glasgow, Caledonian University, Scotland, UK, uk, University of Applied, Sciences Kiel 备注：None 摘要：本文介绍了一种低成本的无人水面飞行器（USV）的原型，该飞行器由波浪和太阳能驱动，可用于降低海洋数据采集的成本。目前的原型是一种紧凑型USV，长度为1.2米，可由两人部署和回收。该设计包括一个电动绞车，可用于收回和降低水下装置。设计的几个要素利用了添加剂制造和廉价材料。通过定制开发的web应用程序，可以使用射频（RF）和卫星通信控制车辆。通过使用先前研究工作和先进材料的推荐，水面和水下装置在阻力、升力、重量和价格方面都进行了优化。USV可通过测量溶解氧、盐度、温度和pH值等参数用于水质监测。 摘要：This paper presents a prototype of a low-cost Unmanned Surface Vehicle (USV) that is operated by wave and solar energy which can be used to minimize the cost of ocean data collection. The current prototype is a compact USV, with a length of 1.2m that can be deployed and recovered by two persons. The design includes an electrically operated winch that can be used to retract and lower the underwater unit. Several elements of the design make use of additive manufacturing and inexpensive materials. The vehicle can be controlled using radio frequency (RF) and a satellite communication, through a custom developed web application. Both the surface and underwater units were optimized with regard to drag, lift, weight, and price by using recommendation of previous research work and advanced materials. The USV could be used in water condition monitoring by measuring several parameters, such as dissolved oxygen, salinity, temperature, and pH.

【8】 Soft Robots Modeling: a Literature Unwinding 标题：软体机器人建模：一种文献解说 链接：https://arxiv.org/abs/2112.03645

作者：Costanza Armanini,Conor Messer,Anup Teejo Mathew,Frédéric Boyer,Christian Duriez,Federico Renda 机构： Khalifa University of Science andTechnology 摘要：机器人学界已经看到，用于软机器人学设备建模的理论工具的复杂性水平呈指数级增长。人们提出了不同的解决方案来克服与软机器人建模相关的困难，通常利用其他科学学科，如连续介质力学和计算机图形学。这些理论基础往往被认为是理所当然的，这导致了一个复杂的文献，因此，从来没有一个完整的审查主题。在这种情况下，本文的目标是双重的。强调了与不同建模技术系列相关的共同理论根源，采用了统一的语言，便于分析其主要联系和差异。因此，自然会列出这些方法，并最终提供对该领域主要工作的完整、不纠结的审查。 摘要：The robotics community has seen an exponential growth in the level of complexity of the theoretical tools presented for the modeling of soft robotics devices. Different solutions have been presented to overcome the difficulties related to the modeling of soft robots, often leveraging on other scientific disciplines, such as continuum mechanics and computer graphics. These theoretical foundations are often taken for granted and this lead to an intricate literature that, consequently, has never been the subject of a complete review. Withing this scenario, the objective of the presented paper is twofold. The common theoretical roots that relate the different families of modeling techniques are highlighted, employing a unifying language that ease the analysis of their main connections and differences. Thus, the listing of the approaches naturally follows and a complete, untangled, review of the main works on the field is finally provided.

【9】 PRM path smoothening by circular arc fillet method for mobile robot navigation 标题：用于移动机器人导航的圆弧圆角法PRM路径平滑 链接：https://arxiv.org/abs/2112.03604

作者：Meral Kılıçarslan Ouach,Tolga Eren,Evrencan Özcan 机构：Department of Electrical-Electronical Engineering, Kırıkkale University, Kırıkkale Turkey, Department of Industrial Engineering, Kırıkkale University, Kırıkkale Turkey 备注：22 pages, 18 figures, 6 tables 摘要：运动规划和导航，特别是对于在复杂导航环境中运行的移动机器人，自机器人技术诞生以来一直是一个核心问题。解决这一问题的一种启发式方法是构建基于图形的表示（路径），以捕获配置空间的连通性。概率路线图是机器人界为导航移动机器人路径规划构建路径的常用方法。在本研究中，在障碍物存在的情况下，从PRM获得路径后，提出了一种基于圆弧圆角的路径平滑方法用于移动机器人路径规划。该方法分两步运行；第一个是在障碍物存在环境中生成从初始状态到目标状态之一之间的最短路径，其中PRM用于通过连接中间节点来构造直线路径。第二步是平滑由节点存在引起的每个角点。使用圆弧圆角平滑拐角，确保移动机器人的转弯平滑。该方法已在不同PRM特征下进行了仿真和测试。实验结果表明，所构造的路径不仅提供了平滑的转弯；机器人在躲避障碍物的同时，完成任务也更短更快。 摘要：Motion planning and navigation, especially for mobile robots operating in complex navigational environments, has been a central problem since robotics started. A heuristic way to address it is the construction of a graph-based representation (a path) capturing the connectivity of the configuration space. Probabilistic Roadmap is a commonly used method by the robotics community to build a path for navigational mobile robot path planning. In this study, path smoothening by arc fillets is proposed for mobile robot path planning after obtaining the path from PRM in the presence of the obstacle. The proposed method runs in two steps; the first one is generating the shortest path between the initial state to one of the goal states in the obstacle presence environment, wherein the PRM is used to construct a straight-lined path by connecting the intermediate nodes. The second step is smoothening every corner caused by node presence. Smoothening the corners with arc fillets ensures smooth turns for the mobile robots. The suggested method has been simulated and tested with different PRM features. Experiment results show that the constructed path is not just providing smooth turning; it is also shorter and quicker to finish for a robot while avoiding obstacles.

【10】 Pragmatic Implementation of Reinforcement Algorithms For Path Finding On Raspberry Pi 标题：树莓猪寻路增强算法的实用化实现 链接：https://arxiv.org/abs/2112.03577

作者：Serena Raju,Sherin Shibu,Riya Mol Raji,Joel Thomas 机构：Computer Department, Fr. C. Rodrigues Institute of Technology, Navi Mumbai, India 备注：5 pages, 7 figures 摘要：本文介绍了一个利用强化学习算法进行路径规划和避免碰撞的室内自主配送系统的实际实现。所提出的系统是一种经济高效的方法，用于帮助树莓Pi控制的四轮驱动非完整机器人映射网格。该方法计算并导航从源关键点到目标关键点的最短路径，以执行所需的交付。Q学习和Deep-Q学习用于在避免与静态障碍物碰撞的同时寻找最优路径。这项工作定义了一种在机器人上部署这两种算法的方法。本文还提出了一种新的算法，将一系列方向解码为特定动作空间中的精确运动。描述了按照上述要求调度该系统所遵循的程序，从而为室内自动运载车辆提供了概念证明。 摘要：In this paper, pragmatic implementation of an indoor autonomous delivery system that exploits Reinforcement Learning algorithms for path planning and collision avoidance is audited. The proposed system is a cost-efficient approach that is implemented to facilitate a Raspberry Pi controlled four-wheel-drive non-holonomic robot map a grid. This approach computes and navigates the shortest path from a source key point to a destination key point to carry out the desired delivery. Q learning and Deep-Q learning are used to find the optimal path while avoiding collision with static obstacles. This work defines an approach to deploy these two algorithms on a robot. A novel algorithm to decode an array of directions into accurate movements in a certain action space is also proposed. The procedure followed to dispatch this system with the said requirements is described, ergo presenting our proof of concept for indoor autonomous delivery vehicles.

【11】 MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance 标题：MESA：用于安全适配和容错的离线Meta-RL 链接：https://arxiv.org/abs/2112.03575

作者：Michael Luo,Ashwin Balakrishna,Brijen Thananjeyan,Suraj Nair,Julian Ibarz,Jie Tan,Chelsea Finn,Ion Stoica,Ken Goldberg 备注：None 摘要：安全探索对于在风险敏感环境中使用强化学习（RL）至关重要。最近的工作学习了风险度量，它度量违反约束的概率，然后可用于实现安全。然而，学习此类风险度量需要与环境进行大量交互，从而导致学习过程中过度违反约束。此外，这些措施不容易转移到新的环境中。我们将安全探索视为离线meta-RL问题，其目标是利用一系列环境中的安全和不安全行为示例，以快速将学到的风险度量适应具有以前未发现动态的新环境。然后，我们提出了安全适应元学习（MESA），一种元学习方法，一种安全RL的风险度量方法。跨5个连续控制域的模拟实验表明，MESA可以利用一系列不同环境中的脱机数据，在保持任务性能的同时，将看不见环境中的约束冲突减少多达2倍。看见https://tinyurl.com/safe-meta-rl 代码和补充资料。 摘要：Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However, learning such risk measures requires significant interaction with the environment, resulting in excessive constraint violations during learning. Furthermore, these measures are not easily transferable to new environments. We cast safe exploration as an offline meta-RL problem, where the objective is to leverage examples of safe and unsafe behavior across a range of environments to quickly adapt learned risk measures to a new environment with previously unseen dynamics. We then propose MEta-learning for Safe Adaptation (MESA), an approach for meta-learning a risk measure for safe RL. Simulation experiments across 5 continuous control domains suggest that MESA can leverage offline data from a range of different environments to reduce constraint violations in unseen environments by up to a factor of 2 while maintaining task performance. See https://tinyurl.com/safe-meta-rl for code and supplementary material.

【12】 Combining optimal control and learning for autonomous aerial navigation in novel indoor environments 标题：新型室内环境下自主空中导航的最优控制与学习相结合 链接：https://arxiv.org/abs/2112.03554

作者：Kevin Lin,Brian Huo,Megan Hu 机构：University of California, Berkeley 摘要：本报告提出了一种新型室内封闭环境中微型飞行器（MAV）自主导航的组合最优控制和感知框架，完全依赖于车载传感器数据。我们使用来自模拟器的特权信息在3D空间中生成最佳航路点，以便我们的感知系统学会模仿。经过训练的基于学习的感知模块能够单独从传感器数据（RGB+IMU）生成类似的避障航路点。我们在iGibson仿真环境中演示了该框架在新场景中的有效性。 摘要：This report proposes a combined optimal control and perception framework for Micro Aerial Vehicle (MAV) autonomous navigation in novel indoor enclosed environments, relying exclusively on on-board sensor data. We use privileged information from a simulator to generate optimal waypoints in 3D space for our perception system learns to imitate. The trained learning based perception module in turn is able to generate similar obstacle avoiding waypoints from sensor data (RGB + IMU) alone. We demonstrate the efficacy of the framework across novel scenes in the iGibson simulation environment.

【13】 Socially acceptable route planning and trajectory behavior analysis of personal mobility device for mobility management with improved sensing 标题：社会可接受的路径规划和轨迹行为分析改进感知的个人移动设备用于移动管理的路径规划和轨迹行为分析 链接：https://arxiv.org/abs/2112.03526

作者：Sumit Mishra,Praveen Kumar Rajendran,Dongsoo Har 机构： The Robotics Program, Department of Electrical Engineering, Korea Advanced Institute of, Division of Future Vehicle, Department of Electrical Engineering, Korea Advanced Institute, of Science and Technology, Daejeon, Republic of Korea 备注：12 pages, 6 figures, Accepted by "The 9th International Conference on Robot Intelligence Technology and Applications, RiTA 2021" 摘要：在城市中，随着行人和个人移动设备（PMD）使用的共享空间越来越受欢迎，需要实用的社会可接受的路径规划和导航管理政策。因此，我们提出了一个社会接受的全球路线规划者，并评估由此产生的全球路线的易读性。我们提出的选择全局路线的方法避免了街道穿过共享空间和主要路线，并具有较高的密集使用概率。实验研究表明，在最优超参数下，平均增加10%的路由长度，可以有效地找到社会可接受的路由。这有助于PMD达到目标，同时采取社会可接受且安全的路线，尽量减少不同PMD和行人的互动。当PMD与共享空间中的行人和其他类型的PMD交互时，mi-cro移动模拟对于可接受和安全的导航策略具有主要用途。社会力模型是最先进的行人模拟模型，用于捕捉行人行为的随机运动。带校准的社会力模型可以模拟行人混合导航方案中PMDs的所需行为。在校准模型的基础上，对共享空间链路和门结构进行仿真，以帮助制定与确定等待和停止时间相关的策略。此外，如果GPS传感器的分辨率为0.2 m或更小，则基于模拟PMDs与行人专用区ans的相互作用，可以获得分辨率更高的位置数据。这将有助于建立更好的模型，从而制定更好的微观流动政策。 摘要：In urban cities, with increasing acceptability of shared spaces used by pedestrians and personal mobility devices (PMDs), there is need for pragmatic socially ac-ceptable path planning and navigation management policies. Hence, we propose a socially acceptable global route planner and assess the legibility of the resulting global route. Our approach proposed for choosing global route avoids streets penetrating shared spaces and main routes with high probability of dense usage. The experimental study shows that socially acceptable routes can be effectively found with an average of 10 % increment of route length with optimal hyperpa-rameters. This helps PMDs to reach the goal while taking a socially acceptable and safe route with minimal interaction of different PMDs and pedestrians. When PMDs interact with pedestrians and other types of PMDs in shared spaces, mi-cro-mobility simulations are of prime usage for acceptable and safe navigation policy. Social force models being state of the art for pedestrian simulation are cal-ibrated for capturing random movements of pedestrian behavior. Social force model with calibration can imitate the required behavior of PMDs in a pedestrian mix navigation scheme. Based on calibrated models, simulations on shared space links and gate structures are performed to assist policies related to deciding wait-ing and stopping time. Also, based on simulated PMDs interaction with pedestri-ans, location data with finer resolution can be obtained if the resolution of GPS sensor is 0.2 m or less. This will help in formalizing better modelling and hence better micro-mobility policies.

【14】 Control Parameters Considered Harmful: Detecting Range Specification Bugs in Drone Configuration Modules via Learning-Guided Search 标题：被认为有害的控制参数：通过学习引导搜索检测无人机配置模块中的距离规范错误 链接：https://arxiv.org/abs/2112.03511

作者：Ruidong Han,Chao Yang,Siqi Ma,JiangFeng Ma,Cong Sun,Juanru Li,Elisa Bertino 机构：State Key Lab. for Integrated Service, Networks, Xidian University, Xian, China, The University of New South Wales, Canberra, Sydney, Australia, Shanghai Jiao Tong University, Shanghai, China, Purdue University, West Lafayette, USA 备注：Accepted to ICSE2022 Technical Track 摘要：为了支持各种任务和处理不同的飞行环境，无人机控制程序通常提供可配置的控制参数。但是，这种灵活性会引入漏洞。最近发现了一个此类漏洞，称为范围规范漏洞。该漏洞源于这样一个事实，即即使每个单独的参数接收到建议值范围内的值，参数值的某些组合可能会影响无人机的物理稳定性。在本文中，我们开发了一个新的学习引导搜索系统，以找到这样的组合，我们称之为不正确的配置。我们的系统采用元启发式搜索算法变异配置，以检测配置参数，这些参数的值将无人机推向不稳定的物理状态。为了指导突变，我们的系统利用机器学习预测器作为适应度评估器。最后，通过多目标优化，我们的系统根据变异搜索结果返回可行范围。因为在我们的系统中，突变是由预测器引导的，所以评估参数配置不需要实际/模拟执行。因此，我们的系统支持全面而高效地检测错误配置。我们已经对我们的系统进行了实验评估。评估结果表明，系统成功报告了潜在的错误配置，其中85%以上导致实际物理状态不稳定。 摘要：In order to support a variety of missions and deal with different flight environments, drone control programs typically provide configurable control parameters. However, such a flexibility introduces vulnerabilities. One such vulnerability, referred to as range specification bugs, has been recently identified. The vulnerability originates from the fact that even though each individual parameter receives a value in the recommended value range, certain combinations of parameter values may affect the drone physical stability. In this paper we develop a novel learning-guided search system to find such combinations, that we refer to as incorrect configurations. Our system applies metaheuristic search algorithms mutating configurations to detect the configuration parameters that have values driving the drone to unstable physical states. To guide the mutations, our system leverages a machine learning predictor as the fitness evaluator. Finally, by utilizing multi-objective optimization, our system returns the feasible ranges based on the mutation search results. Because in our system the mutations are guided by a predictor, evaluating the parameter configurations does not require realistic/simulation executions. Therefore, our system supports a comprehensive and yet efficient detection of incorrect configurations. We have carried out an experimental evaluation of our system. The evaluation results show that the system successfully reports potentially incorrect configurations, of which over 85% lead to actual unstable physical states.

【15】 Guided Imitation of Task and Motion Planning 标题：任务和运动规划的引导式仿真 链接：https://arxiv.org/abs/2112.03386

作者：Michael James McDonald,Dylan Hadfield-Menell 机构：Massachusetts Institute of Technology 备注：16 pages, 6 figures, 2 tables, submitted to Conference on Robot Learning 2021, to be published in Proceedings of Machine Learning Research 摘要：虽然现代政策优化方法可以从感官数据中进行复杂的操作，但它们在时间范围和多个子目标的问题上仍存在困难。另一方面，任务和运动规划（TAMP）方法可以扩展到很长的范围，但它们的计算成本很高，需要精确跟踪世界状态。我们提出了一种利用这两种方法的优点的方法：我们训练策略来模拟TAMP解算器的输出。这产生了一个前馈策略，可以从感官数据完成多步骤任务。首先，我们构建了一个异步分布式TAMP解算器，该解算器能够以足够快的速度生成用于模拟学习的监控数据。然后，我们提出了一个分层策略架构，允许我们使用部分训练的控制策略来加速TAMP求解器。在具有7自由度关节控制的机器人操作任务中，部分训练的策略将规划所需的时间减少了2.6倍。在这些任务中，我们可以了解到一个策略，该策略88%的时间从对象姿势观测中解决RoboSite 4对象拾取位置任务，以及一个策略，该策略79%的时间从RGB图像中解决RoboDesk 9目标基准（9个不同任务的平均值）。 摘要：While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long horizons but they are computationally expensive and need to precisely track world state. We propose a method that draws on the strength of both methods: we train a policy to imitate a TAMP solver's output. This produces a feed-forward policy that can accomplish multi-step tasks from sensory data. First, we build an asynchronous distributed TAMP solver that can produce supervision data fast enough for imitation learning. Then, we propose a hierarchical policy architecture that lets us use partially trained control policies to speed up the TAMP solver. In robotic manipulation tasks with 7-DoF joint control, the partially trained policies reduce the time needed for planning by a factor of up to 2.6. Among these tasks, we can learn a policy that solves the RoboSuite 4-object pick-place task 88% of the time from object pose observations and a policy that solves the RoboDesk 9-goal benchmark 79% of the time from RGB images (averaged across the 9 disparate tasks).

【16】 Self-Supervised Camera Self-Calibration from Video 标题：基于视频的自监督摄像机自标定 链接：https://arxiv.org/abs/2112.03325

作者：Jiading Fang,Igor Vasiljevic,Vitor Guizilini,Rares Ambrus,Greg Shakhnarovich,Adrien Gaidon,Matthew R. Walter 机构：Rares, Ambrus 摘要：摄像机校准是机器人技术和计算机视觉算法的一个组成部分，这些算法试图从视觉输入流推断场景的几何特性。在实践中，校准是一个费力的过程，需要专门的数据收集和仔细调整。每当摄像机参数发生变化时，必须重复该过程，这对于移动机器人和自动驾驶车辆来说是经常发生的。相比之下，自监督深度和自我运动估计方法可以通过推断优化视图合成目标的每帧投影模型绕过显式校准。在本文中，我们扩展了这种方法，从野外的原始视频中显式地校准了大范围的摄像机。我们提出了一种学习算法，使用一个有效的通用相机模型族来回归每个序列的校准参数。我们的程序实现了具有亚像素重投影误差的自校准结果，优于其他基于学习的方法。我们在各种各样的相机几何体上验证了我们的方法，包括透视、鱼眼和折反射。最后，我们表明，我们的方法改进了深度估计的下游任务，在EuRoC数据集上实现了最先进的结果，计算效率高于当代方法。 摘要：Camera calibration is integral to robotics and computer vision algorithms that seek to infer geometric properties of the scene from visual input streams. In practice, calibration is a laborious procedure requiring specialized data collection and careful tuning. This process must be repeated whenever the parameters of the camera change, which can be a frequent occurrence for mobile robots and autonomous vehicles. In contrast, self-supervised depth and ego-motion estimation approaches can bypass explicit calibration by inferring per-frame projection models that optimize a view synthesis objective. In this paper, we extend this approach to explicitly calibrate a wide range of cameras from raw videos in the wild. We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models. Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods. We validate our approach on a wide variety of camera geometries, including perspective, fisheye, and catadioptric. Finally, we show that our approach leads to improvements in the downstream task of depth estimation, achieving state-of-the-art results on the EuRoC dataset with greater computational efficiency than contemporary methods.

机器翻译，仅供参考