机器人相关学术速递[7.12]

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

cs.RO机器人相关，共计14篇

【1】 Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios 标题：密集交通场景下运动规划的学习交互感知诱导策略

作者：Bruno Brito,Achin Agarwal,Javier Alonso-Mora 机构：This work was supported by the Amsterdam Institute for AdvancedMetropolitan Solutions and the Netherlands Organisation for Scientific Re-search (NWO) domain Applied Sciences (Veni 1 59 16), DelftUniversityofTechnology 链接：https://arxiv.org/abs/2107.04538 摘要：密集交通场景下的自主导航对于自主车辆（AVs）来说仍然是一个挑战，因为其他驾驶员的意图是不可直接观察的，AVs必须处理各种各样的驾驶行为。要在密集的交通中机动，AVs必须能够推理其行为如何影响他人（交互模型），并利用此推理安全地在密集的交通中导航。提出了一种新的交通密集场景下基于交互感知的运动规划框架。我们探讨了人类驾驶行为和他们相互作用时的速度变化之间的联系。因此，我们建议通过深度强化学习（RL）学习一种交互感知策略，为基于优化的规划人员提供关于其他车辆协作性的全局指导，通过约束满足确保安全性和运动可行性。学习到的策略可以推理和引导具有交互行为的局部优化规划器在交通拥挤的情况下主动合并，同时在其他车辆不让行的情况下保持安全。我们提出了定性和定量的结果在高度互动的模拟环境（高速公路合并和无保护左转）对两个基线方法，基于学习和优化的方法。结果表明，相对于基于学习和基于优化的基线，我们的方法显著减少了碰撞次数，提高了成功率。 摘要：Autonomous navigation in dense traffic scenarios remains challenging for autonomous vehicles (AVs) because the intentions of other drivers are not directly observable and AVs have to deal with a wide range of driving behaviors. To maneuver through dense traffic, AVs must be able to reason how their actions affect others (interaction model) and exploit this reasoning to navigate through dense traffic safely. This paper presents a novel framework for interaction-aware motion planning in dense traffic scenarios. We explore the connection between human driving behavior and their velocity changes when interacting. Hence, we propose to learn, via deep Reinforcement Learning (RL), an interaction-aware policy providing global guidance about the cooperativeness of other vehicles to an optimization-based planner ensuring safety and kinematic feasibility through constraint satisfaction. The learned policy can reason and guide the local optimization-based planner with interactive behavior to pro-actively merge in dense traffic while remaining safe in case the other vehicles do not yield. We present qualitative and quantitative results in highly interactive simulation environments (highway merging and unprotected left turns) against two baseline approaches, a learning-based and an optimization-based method. The presented results demonstrate that our method significantly reduces the number of collisions and increases the success rate with respect to both learning-based and optimization-based baselines.

【2】 Behavior Self-Organization Supports Task Inference for Continual Robot Learning 标题：行为自组织支持机器人持续学习的任务推理

作者：Muhammad Burhan Hafez,Stefan Wermter 机构： Department of Informatics, University of Hamburg 备注：Accepted at IROS 2021 链接：https://arxiv.org/abs/2107.04533 摘要：机器人学习的最新进展使机器人越来越善于掌握一组预先定义的任务。另一方面，作为人类，我们有能力在一生中学习越来越多的任务。机器人的持续学习是一个新兴的研究方向，其目标是赋予机器人这种能力。为了随着时间的推移学习新的任务，机器人首先需要推断手头的任务。然而，任务推理在多任务学习文献中却很少受到关注。本文提出了一种机器人控制任务连续学习的新方法。我们的方法通过递增的自组织示范行为来执行行为嵌入的无监督学习。任务推理是通过找到最近的行为嵌入到一个示范的行为，它与环境状态一起作为输入到一个多任务策略训练与强化学习，以优化任务的性能。与以前的方法不同，我们的方法对任务分布不做任何假设，也不需要任务探索来推断任务。实验结果表明，该方法在泛化性能和收敛速度方面优于其他多任务学习方法，特别是在连续学习环境下。 摘要：Recent advances in robot learning have enabled robots to become increasingly better at mastering a predefined set of tasks. On the other hand, as humans, we have the ability to learn a growing set of tasks over our lifetime. Continual robot learning is an emerging research direction with the goal of endowing robots with this ability. In order to learn new tasks over time, the robot first needs to infer the task at hand. Task inference, however, has received little attention in the multi-task learning literature. In this paper, we propose a novel approach to continual learning of robotic control tasks. Our approach performs unsupervised learning of behavior embeddings by incrementally self-organizing demonstrated behaviors. Task inference is made by finding the nearest behavior embedding to a demonstrated behavior, which is used together with the environment state as input to a multi-task policy trained with reinforcement learning to optimize performance over tasks. Unlike previous approaches, our approach makes no assumptions about task distribution and requires no task exploration to infer tasks. We evaluate our approach in experiments with concurrently and sequentially presented tasks and show that it outperforms other multi-task learning approaches in terms of generalization performance and convergence speed, particularly in the continual learning setting.

【3】 BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym 标题：BayesSimIG：基于IsaacGym的自适应域随机化可扩展参数推理

作者：Rika Antonova,Fabio Ramos,Rafael Possas,Dieter Fox 机构：Department of Computer Science, Stanford University, USA, NVIDIA, USA, School of Computer Science, University of Sydney, Australia 链接：https://arxiv.org/abs/2107.04527 摘要：BayesSim是一种基于仿真参数无似然推理的强化学习领域随机化统计技术。本文概述了BayesSimIG：一个提供BayesSim与最近发布的nvidiaisaacgym集成的实现的库。这种组合允许使用端到端GPU加速进行大规模参数推断。推理和仿真都得到了GPU的加速，支持为复杂的机器人任务运行超过10K的并行仿真环境，可以估计超过100个仿真参数。BayesSimIG提供了与张力板的集成，可以轻松地可视化高维后验图像。该图书馆是建立在一个模块化的方式，以支持研究实验与新的方法收集和处理的轨迹，从平行的IsaacGym环境。 摘要：BayesSim is a statistical technique for domain randomization in reinforcement learning based on likelihood-free inference of simulation parameters. This paper outlines BayesSimIG: a library that provides an implementation of BayesSim integrated with the recently released NVIDIA IsaacGym. This combination allows large-scale parameter inference with end-to-end GPU acceleration. Both inference and simulation get GPU speedup, with support for running more than 10K parallel simulation environments for complex robotics tasks that can have more than 100 simulation parameters to estimate. BayesSimIG provides an integration with TensorBoard to easily visualize slices of high-dimensional posteriors. The library is built in a modular way to support research experiments with novel ways to collect and process the trajectories from the parallel IsaacGym environments.

【4】 On the Challenges of Open World Recognitionunder Shifting Visual Domains 标题：论视域转换下开放世界认知面临的挑战

作者：Dario Fontanel,Fabio Cermelli,Massimiliano Mancini,Barbara Caputo 备注：RAL/ICRA 2021 链接：https://arxiv.org/abs/2107.04461 摘要：在野外工作的机器人视觉系统必须在不受约束的场景中，在不同的环境条件下，同时面对各种语义概念，包括未知的语义概念。为此，最近的工作试图使视觉对象识别方法具有以下能力：i）检测看不见的概念；ii）随着时间的推移，随着新语义类图像的出现，扩展其知识。这种设置被称为开放世界识别（OWR），其目标是生成能够打破初始训练集中存在的语义限制的系统。然而，这种训练集不仅给系统施加了自己的语义限制，而且还施加了环境限制，因为它偏向于某些不一定反映现实世界高度可变性的获取条件。训练和测试分布之间的这种差异称为域转移。本文研究了OWR算法在域转移情况下的有效性，提出了第一个公平评估OWR算法性能的基准设置，包括有域转移和无域转移。然后，我们使用这个基准在各种场景中进行分析，显示当训练和测试分布不同时，现有的OWR算法是如何遭受严重的性能退化的。我们的分析表明，通过将OWR与领域泛化技术相结合，这种退化只得到了轻微的缓解，这表明现有算法的简单即插即用不足以识别未知领域中的新类别和未知类别。我们的研究结果清楚地指出了有待解决的问题和未来的研究方向，这些问题和方向是建立机器人视觉系统在这些具有挑战性但非常真实的条件下能够可靠地工作所需要研究的。代码位于https://github.com/DarioFontanel/OWR-VisualDomains 摘要：Robotic visual systems operating in the wild must act in unconstrained scenarios, under different environmental conditions while facing a variety of semantic concepts, including unknown ones. To this end, recent works tried to empower visual object recognition methods with the capability to i) detect unseen concepts and ii) extended their knowledge over time, as images of new semantic classes arrive. This setting, called Open World Recognition (OWR), has the goal to produce systems capable of breaking the semantic limits present in the initial training set. However, this training set imposes to the system not only its own semantic limits, but also environmental ones, due to its bias toward certain acquisition conditions that do not necessarily reflect the high variability of the real-world. This discrepancy between training and test distribution is called domain-shift. This work investigates whether OWR algorithms are effective under domain-shift, presenting the first benchmark setup for assessing fairly the performances of OWR algorithms, with and without domain-shift. We then use this benchmark to conduct analyses in various scenarios, showing how existing OWR algorithms indeed suffer a severe performance degradation when train and test distributions differ. Our analysis shows that this degradation is only slightly mitigated by coupling OWR with domain generalization techniques, indicating that the mere plug-and-play of existing algorithms is not enough to recognize new and unknown categories in unseen domains. Our results clearly point toward open issues and future research directions, that need to be investigated for building robot visual systems able to function reliably under these challenging yet very real conditions. Code available at https://github.com/DarioFontanel/OWR-VisualDomains

【5】 Aligning an optical interferometer with beam divergence control and continuous action space 标题：利用光束发散控制和连续作用空间对准光学干涉仪

作者：Stepan Makarenko,Dmitry Sorokin,Alexander Ulanov,A. I. Lvovsky 机构：Russian Quantum Center, Moscow, Russia, Moscow Institute of Physics and Technology, Russia, University of Oxford, United Kingdom 备注：12 pages, 5 figures 链接：https://arxiv.org/abs/2107.04457 摘要：强化学习正从模拟环境向物理环境的转变，逐渐走向现实问题的应用。在这项工作中，我们实现了光学马赫-曾德尔干涉仪与共焦望远镜在一个手臂，它控制相应的光束直径和发散度的视觉对齐。我们使用连续动作空间；指数缩放使我们能够处理超过两个数量级范围内的动作。我们的代理只在一个模拟的环境中进行训练。在实验评估中，代理的性能明显优于现有的解决方案和人类专家。 摘要：Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly outperforms an existing solution and a human expert.

【6】 Planning of efficient trajectories in robotized assembly of aerostructures exploiting kinematic redundancy 标题：利用运动学冗余的飞行器机器人装配中的有效轨迹规划

作者：Federica Storiale,Enrico Ferrentino,Pasquale Chiacchio 机构：Department of Computer Engineering, Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Fisciano, SA , Italy 备注：None 链接：https://arxiv.org/abs/2107.04341 摘要：随着时间的推移，航空生产量不断增加，航空装配线逐步采用机器人解决方案，以实现高质量标准、高生产率、灵活性和成本降低。机器人工作单元有时的特点是机器人安装在幻灯片上，以增加机器人的工作空间。幻灯片引入了额外的自由度，使系统在运动上冗余，但此功能很少用于增强性能。本文提出了一种新的弹道规划概念，即利用冗余度来满足附加要求。采用动态规划技术，计算优化轨迹，最小化或最大化性能指标。该用例定义在LABOR（复合材料气动结构的精益机器人化装配与控制）项目中，该项目采用两个安装在直线轴上的协同六轴机器人在机身面板上执行装配操作。考虑到这个工作单元的需要，机器人不必要的运动被最小化以增加安全性，机械刚度被最大化以增加钻井作业期间的稳定性，碰撞被避免，同时关节限制和可用的规划时间被尊重。实验是在一个模拟环境中进行的，在这个环境中，最优轨迹被执行，突出了结果的性能和相对于非优化解决方案的改进。 摘要：Aerospace production volumes have increased over time and robotic solutions have been progressively introduced in the aeronautic assembly lines to achieve high-quality standards, high production rates, flexibility and cost reduction. Robotic workcells are sometimes characterized by robots mounted on slides to increase the robot workspace. The slide introduces an additional degree of freedom, making the system kinematically redundant, but this feature is rarely used to enhance performances. The paper proposes a new concept in trajectory planning, that exploits the redundancy to satisfy additional requirements. A dynamic programming technique is adopted, which computes optimized trajectories, minimizing or maximizing the performance indices of interest. The use case is defined on the LABOR (Lean robotized AssemBly and cOntrol of composite aeRostructures) project which adopts two cooperating six-axis robots mounted on linear axes to perform assembly operations on fuselage panels. Considering the needs of this workcell, unnecessary robot movements are minimized to increase safety, the mechanical stiffness is maximized to increase stability during the drilling operations, collisions are avoided, while joint limits and the available planning time are respected. Experiments are performed in a simulation environment, where the optimal trajectories are executed, highlighting the resulting performances and improvements with respect to non-optimized solutions.

【7】 Score refinement for confidence-based 3D multi-object tracking 标题：基于置信度的三维多目标跟踪分数细化算法

作者：Nuri Benbarka,Jona Schröder,Andreas Zell 机构： University of T¨ubingen 备注：Accepted at IROS 2021 链接：https://arxiv.org/abs/2107.04327 摘要：多目标跟踪是自主导航的一个重要组成部分，它为决策提供了有价值的信息。许多研究者通过滤除逐帧的三维检测来解决三维多目标跟踪问题；然而，他们的重点主要是寻找有用的特征或合适的匹配度量。我们的工作集中在跟踪系统中一个被忽视的部分：分数细化和tracklet终止。我们表明，根据时间一致性操纵分数，同时根据tracklet分数终止tracklet，可以改善跟踪结果。我们通过使用分数更新函数增加匹配的tracklet的分数并减少不匹配的tracklet的分数来实现这一点。与基于计数的方法相比，在不同的数据集上使用不同的检测器和过滤算法时，我们的方法一致地产生更好的AMOTA和MOTA分数。AMOTA评分提高了1.83分，MOTA评分提高了2.96分。我们还使用了我们的方法作为一种后期融合集成方法，它比基于投票的集成方法具有更高的性能。它在nuScenes测试评估中获得了67.6分的AMOTA分数，这与其他最先进的跟踪器相当。代码可在以下网址公开获取：\url{https://github.com/cogsys-tuebingen/CBMOT}. 摘要：Multi-object tracking is a critical component in autonomous navigation, as it provides valuable information for decision-making. Many researchers tackled the 3D multi-object tracking task by filtering out the frame-by-frame 3D detections; however, their focus was mainly on finding useful features or proper matching metrics. Our work focuses on a neglected part of the tracking system: score refinement and tracklet termination. We show that manipulating the scores depending on time consistency while terminating the tracklets depending on the tracklet score improves tracking results. We do this by increasing the matched tracklets' score with score update functions and decreasing the unmatched tracklets' score. Compared to count-based methods, our method consistently produces better AMOTA and MOTA scores when utilizing various detectors and filtering algorithms on different datasets. The improvements in AMOTA score went up to 1.83 and 2.96 in MOTA. We also used our method as a late-fusion ensembling method, and it performed better than voting-based ensemble methods by a solid margin. It achieved an AMOTA score of 67.6 on nuScenes test evaluation, which is comparable to other state-of-the-art trackers. Code is publicly available at: \url{https://github.com/cogsys-tuebingen/CBMOT}.

【8】 Learning structured approximations of operations research problems 标题：运筹学问题的结构化近似学习

作者：Axel Parmentier 机构：CERMICS, Ecole des Ponts, Marne-la-Vall´ee, France 链接：https://arxiv.org/abs/2107.04323 摘要：利用机器学习和组合优化技术的算法设计是运筹学中一个年轻但蓬勃发展的领域。如果出现趋势，文献仍然没有集中在结合这两种技术的正确方法上，或者应该使用的预测架构上。我们专注于运筹学的问题，没有有效的算法是已知的，但这是经典问题的变种，其中有一个有效的算法存在。在详细阐述最近的贡献，建议使用机器学习预测近似变量的经典问题，我们介绍了概念结构近似的运筹学问题的另一个。我们提供了一个通用的学习算法来适应这些近似。该算法只需要训练集中变量的实例，不像以前的学习算法也需要这些实例的解。利用统计学习理论中的工具，我们证明了估计量的收敛速度，并推导了对该变量算法性能的近似比保证。对文献中的单机调度和随机车辆调度问题的数值实验表明，我们的学习算法与能够获得最优解的算法具有竞争力，从而为所考虑的变量提供了最先进的算法。 摘要：The design of algorithms that leverage machine learning alongside combinatorial optimization techniques is a young but thriving area of operations research. If trends emerge, the literature has still not converged on the proper way of combining these two techniques or on the predictor architectures that should be used. We focus on operations research problems for which no efficient algorithms are known, but that are variants of classic problems for which ones efficient algorithm exist. Elaborating on recent contributions that suggest using a machine learning predictor to approximate the variant by the classic problem, we introduce the notion of structured approximation of an operations research problem by another. We provide a generic learning algorithm to fit these approximations. This algorithm requires only instances of the variant in the training set, unlike previous learning algorithms that also require the solution of these instances. Using tools from statistical learning theory, we prove a result showing the convergence speed of the estimator, and deduce an approximation ratio guarantee on the performance of the algorithm obtained for the variant. Numerical experiments on a single machine scheduling and a stochastic vehicle scheduling problem from the literature show that our learning algorithm is competitive with algorithms that have access to optimal solutions, leading to state-of-the-art algorithms for the variant considered.

【9】 Dynamic Modeling of Bucket-Soil Interactions Using Koopman-DFL Lifting Linearization for Model Predictive Contouring Control of Autonomous Excavators 标题：基于Koopman-DFL提升线性化的斗土相互作用动力学建模自主挖掘机模型预测轮廓控制

作者：Filippos E. Sotiropoulos,H. Harry Asada 机构：edu) arewith the Department of Mechanical Engineering, Massachusetts Institute ofTechnology 链接：https://arxiv.org/abs/2107.04314 摘要：将基于Koopman算子和对偶线性化的提升线性化方法应用于机器人挖掘机的控制。在开挖过程中，铲斗与周围土壤的相互作用是高度非线性和复杂的。在这里，我们建议在高维空间中用一组线性状态方程来表示非线性桶土动力学。通过添加与桶土动力学中涉及的非线性元素相关的变量，扩充了独立状态变量的空间。这些包括土壤作用在铲斗上的非线性阻力和力矩，以及铲斗的有效惯性，随着土壤被捕获到铲斗中而变化。与这些非线性电阻和惯性元件相关的变量被视为附加状态变量，它们的时间演化被表示为另一组线性微分方程。然后将提升线性动态模型应用于模型预测轮廓控制，利用提升空间的线性动态特性，将成本函数最小化为凸优化问题。基于数据驱动的方法，利用土壤动力学模拟器对提升线性模型进行了调整。仿真实验验证了提出的提升线性化方法的有效性。 摘要：A lifting-linearization method based on the Koopman operator and Dual Faceted Linearization is applied to the control of a robotic excavator. In excavation, a bucket interacts with the surrounding soil in a highly nonlinear and complex manner. Here, we propose to represent the nonlinear bucket-soil dynamics with a set of linear state equations in a higher-dimensional space. The space of independent state variables is augmented by adding variables associated with nonlinear elements involved in the bucket-soil dynamics. These include nonlinear resistive forces and moment acting on the bucket from the soil, and the effective inertia of the bucket that varies as the soil is captured into the bucket. Variables associated with these nonlinear resistive and inertia elements are treated as additional state variables, and their time evolution is represented as another set of linear differential equations. The lifted linear dynamic model is then applied to Model Predictive Contouring Control, where a cost functional is minimized as a convex optimization problem thanks to the linear dynamics in the lifted space. The lifted linear model is tuned based on a data-driven method by using a soil dynamics simulator. Simulation experiments verify the effectiveness of the proposed lifting linearization compared to its counterpart.

【10】 Control Lyapunov Functions for Compliant Hybrid Zero Dynamic Walking 标题：柔顺混合零动态行走的控制Lyapunov函数

作者：Jenna Reher,Aaron D. Ames 机构： a significant subset of the bipedal robotics literaturemitigates the complexity of humanoids and bipeds by viewingJenna Reher is with the Department of Mechanical and Civil En-gineering, CaliforniaInstituteofTechnology 备注：Paper in preparation for submission to IEEE Transactions on Robotics (T-RO) 链接：https://arxiv.org/abs/2107.04241 摘要：在动态机器人系统上实现具有形式保证的非线性控制器的能力有可能实现更复杂的机器人行为——然而，实现这些控制器通常具有实际挑战性。为了解决这一问题，本文提出了一种基于混合零动力学和控制Lyapunov函数的欠驱动双足机器人动态双足运动的端到端实现方法。将Cassie的柔顺模型表示为一个混合系统，为轨迹优化框架奠定基础。为了在各个方向上实现不同的行走速度，编制了一个柔顺行走运动库，然后将其参数化，以便在实时控制器中有效使用。综合具有强大理论保证的控制Lyapunov函数，利用步态库，结合逆动力学得到基于优化的二次规划控制器。证明了该控制器能实现稳定的运动；这与理论分析相结合，证明了该控制器对调节和实现的有用特性。该理论框架在Cassie机器人上得到了实际应用，通过基于优化的力矩控制实现了机器人的三维行走。实验突出了机器人在不同速度和地形下的行走，说明了在动态欠驱动机器人系统上，理论上合理的非线性控制器的端到端实现。 摘要：The ability to realize nonlinear controllers with formal guarantees on dynamic robotic systems has the potential to enable more complex robotic behaviors -- yet, realizing these controllers is often practically challenging. To address this challenge, this paper presents the end-to-end realization of dynamic bipedal locomotion on an underactuated bipedal robot via hybrid zero dynamics and control Lyapunov functions. A compliant model of Cassie is represented as a hybrid system to set the stage for a trajectory optimization framework. With the goal of achieving a variety of walking speeds in all directions, a library of compliant walking motions is compiled and then parameterized for efficient use within real-time controllers. Control Lyapunov functions, which have strong theoretic guarantees, are synthesized to leverage the gait library and coupled with inverse dynamics to obtain optimization-based controllers framed as quadratic programs. It is proven that this controller provably achieves stable locomotion; this is coupled with a theoretic analysis demonstrating useful properties of the controller for tuning and implementation. The proposed theoretic framework is practically demonstrated on the Cassie robot, wherein 3D walking is achieved through the use of optimization-based torque control. The experiments highlight robotic walking at different speeds and terrains, illustrating the end-to-end realization of theoretically justified nonlinear controllers on dynamic underactuated robotic systems.

【11】 Probabilistic Trajectory Prediction with Structural Constraints 标题：考虑结构约束的概率弹道预测

作者：Weiming Zhi,Lionel Ott,Fabio Ramos 机构： 1 School of Computer Science, the University of Sydney 备注：To appear at IROS 2021 链接：https://arxiv.org/abs/2107.04193 摘要：这项工作解决了预测环境中动态物体运动轨迹的问题。在预测运动模式方面的最新进展通常依赖于机器学习技术从观察到的轨迹推断运动模式，而没有直接结合已知规则的机制。我们提出了一个结合概率学习和约束轨迹优化的新框架。我们的框架的学习组件提供了一个分布在未来的运动轨迹的条件下观察过去的坐标。然后将该分布作为约束优化问题的先验条件，该约束优化问题对轨迹分布施加机会约束。这将导致符合约束的轨迹分布非常类似于先前的。特别地，我们的研究集中在碰撞约束上，使得外推的未来轨迹分布符合环境结构。我们在真实世界和模拟数据集上实证证明了我们的框架学习运动数据的复杂概率运动轨迹的能力，同时直接强制约束以提高通用性，产生更健壮和更高质量的轨迹分布。 摘要：This work addresses the problem of predicting the motion trajectories of dynamic objects in the environment. Recent advances in predicting motion patterns often rely on machine learning techniques to extrapolate motion patterns from observed trajectories, with no mechanism to directly incorporate known rules. We propose a novel framework, which combines probabilistic learning and constrained trajectory optimisation. The learning component of our framework provides a distribution over future motion trajectories conditioned on observed past coordinates. This distribution is then used as a prior to a constrained optimisation problem which enforces chance constraints on the trajectory distribution. This results in constraint-compliant trajectory distributions which closely resemble the prior. In particular, we focus our investigation on collision constraints, such that extrapolated future trajectory distributions conform to the environment structure. We empirically demonstrate on real-world and simulated datasets the ability of our framework to learn complex probabilistic motion trajectories for motion data, while directly enforcing constraints to improve generalisability, producing more robust and higher quality trajectory distributions.

【12】 Semantic Feature Matching for Robust Mapping in Agriculture 标题：面向农业稳健制图的语义特征匹配

作者：Mohamad Qadri,George Kantor 机构：and USDA NIFA CPS 20 20-670 2 1- 3 1 5 3 1Mohamad Qadri and George Kantor are with The Robotics Institute, Carnegie Mellon University 备注：6 pages, 8 figures 链接：https://arxiv.org/abs/2107.04178 摘要：视觉同步定位与制图（SLAM）系统是农业机器人的重要组成部分，它可以实现农业领域的自主导航和精确三维地图的构建。然而，缺乏纹理、光照条件的变化以及环境中结构的缺乏对依赖传统特征提取和匹配算法（如ORB或SIFT）的视觉SLAM系统提出了挑战。本文提出了1）一种对象级特征关联算法，利用农业领域机器人导航的结构特点，实现了三维重建的鲁棒生成，2）一个对象级SLAM系统，它利用基于深度学习的对象检测和分割算法的最新进展来检测和分割作为SLAM标志的环境中的语义对象。我们在一个高粱地的立体图像数据集上测试了我们的SLAM系统。我们展示了我们基于对象的特征关联算法，使我们能够映射平均78%的高粱范围。相比之下，与传统的视觉特征，我们实现了38%的平均映射距离。我们还比较了我们的系统与ORB-SLAM2，一个最先进的视觉SLAM算法。 摘要：Visual Simultaneous Localization and Mapping (SLAM) systems are an essential component in agricultural robotics that enable autonomous navigation and the construction of accurate 3D maps of agricultural fields. However, lack of texture, varying illumination conditions, and lack of structure in the environment pose a challenge for Visual-SLAM systems that rely on traditional feature extraction and matching algorithms such as ORB or SIFT. This paper proposes 1) an object-level feature association algorithm that enables the creation of 3D reconstructions robustly by taking advantage of the structure in robotic navigation in agricultural fields, and 2) An object-level SLAM system that utilizes recent advances in deep learning-based object detection and segmentation algorithms to detect and segment semantic objects in the environment used as landmarks for SLAM. We test our SLAM system on a stereo image dataset of a sorghum field. We show that our object-based feature association algorithm enables us to map 78% of a sorghum range on average. In contrast, with traditional visual features, we achieve an average mapped distance of 38%. We also compare our system against ORB-SLAM2, a state-of-the-art visual SLAM algorithm.

【13】 Excavation Learning for Rigid Objects in Clutter 标题：杂波中刚性物体的挖掘学习

作者：Qingkai Lu,Liangjun Zhang 备注：Accepted to IEEE Robotics and Automation Letters (RA-L) 2021 链接：https://arxiv.org/abs/2107.04171 摘要：对于坚硬或致密的材料，特别是不规则的刚性物体，由于物体的几何和物理性质变化较大，且在开挖过程中阻力较大，因此自主开挖具有很大的挑战性。本文提出了一种新的基于学习的杂波中刚性目标挖掘规划方法。我们的方法包括一个预测挖掘成功率的卷积神经网络和一个利用学习的预测模型规划高质量挖掘轨迹的基于抽样的优化方法。为了减少挖掘学习的sim2real间隔，我们提出了一种基于体素的挖掘场景表示方法。我们在模拟和真实世界中进行挖掘实验，以评估基于学习的挖掘规划者。我们进一步比较了两种启发式基线挖掘规划者和一种数据驱动场景无关规划者。实验结果表明，该方法能够在杂波环境下对刚性目标进行高质量的挖掘，比基线方法有较大的优势。据我们所知，我们的工作提出了第一个基于学习的挖掘计划混乱和不规则的刚性物体。 摘要：Autonomous excavation for hard or compact materials, especially irregular rigid objects, is challenging due to high variance of geometric and physical properties of objects, and large resistive force during excavation. In this paper, we propose a novel learning-based excavation planning method for rigid objects in clutter. Our method consists of a convolutional neural network to predict the excavation success and a sampling-based optimization method for planning high-quality excavation trajectories leveraging the learned prediction model. To reduce the sim2real gap for excavation learning, we propose a voxel-based representation of the excavation scene. We perform excavation experiments in both simulation and real world to evaluate the learning-based excavation planners. We further compare with two heuristic baseline excavation planners and one data-driven scene-independent planner. The experimental results show that our method can plan high-quality excavations for rigid objects in clutter and outperforms the baseline methods by large margins. As far as we know, our work presents the first learning-based excavation planner for cluttered and irregular rigid objects.

【14】 Distributed formation control for manipulator end-effectors 标题：机械手末端执行器的分布式编队控制

作者：Haiwen Wu,Bayu Jayawardhana,Hector Garcia de Marina,Dabo Xu 备注：arXiv admin note: text overlap with arXiv:2103.14595 链接：https://arxiv.org/abs/2107.04141 摘要：我们提出了三类分布式编队控制器，用于实现和保持机械手末端执行器的二维/三维编队形状，以应对由于模型参数可用而产生的不同情况。针对系统参数完全已知的机器人，提出了一种分布式队形控制器。通过在末端执行器之间分配虚拟弹簧和在关节处添加阻尼项来实现编队控制目标，这为所提出的解决方案提供了清晰的物理解释。随后，我们将其推广到机械手运动学和系统参数未知的情况。分别引入一个额外的积分器和一个自适应估计器用于重力补偿和稳定。以平面机械手和七自由度仿人机械臂为例进行了仿真，验证了该方法的有效性。 摘要：We present three classes of distributed formation controllers for achieving and maintaining the 2D/3D formation shape of manipulator end-effectors to cope with different scenarios due to availability of modeling parameters. We firstly present a distributed formation controller for manipulators whose system parameters are perfectly known. The formation control objective is achieved by assigning virtual springs between end-effectors and by adding damping terms at joints, which provides a clear physical interpretation of the proposed solution. Subsequently, we extend it to the case where manipulator kinematic and system parameters are not exactly known. An extra integrator and an adaptive estimator are introduced for gravitational compensation and stabilization, respectively. Simulation results with planar manipulators and with seven degree-of-freedom humanoid manipulator arms are presented to illustrate the effectiveness of the proposed approach.