机器人相关学术速递[11.24]

Update！H5支持摘要折叠，体验更佳！点击阅读原文访问arxivdaily.com，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏等功能！

cs.RO机器人相关，共计8篇

【1】 VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles 标题：Vista 2.0：一个开放的、数据驱动的自主车辆多模态感知和策略学习模拟器 链接：https://arxiv.org/abs/2111.12083

作者：Alexander Amini,Tsun-Hsuan Wang,Igor Gilitschenski,Wilko Schwarting,Zhijian Liu,Song Han,Sertac Karaman,Daniela Rus 机构：edu 2 Department of Computer Science 备注：First two authors contributed equally. Code and project website is available here: this https URL 摘要：仿真有可能改变部署在安全关键场景中的移动代理鲁棒算法的发展。然而，现有模拟引擎的低真实感和缺乏多样的传感器模式仍然是实现这一潜力的关键障碍。在这里，我们介绍VISTA，一个开源的数据驱动模拟器，它集成了多种类型的自动驾驶车辆传感器。VISTA使用高保真、真实世界的数据集，表示和模拟RGB摄像机、3D激光雷达和基于事件的摄像机，实现了在模拟中快速生成新视点，从而丰富了可用于政策学习的数据，这些数据在物理世界中难以捕捉。使用VISTA，我们展示了训练和测试感知能力的能力，以控制每种传感器类型的策略，并通过在全尺寸自动车辆上的部署展示了这种方法的威力。在VISTA中学习到的策略显示出无需修改的模拟到真实的传输，并且比那些只针对真实数据进行训练的策略具有更大的鲁棒性。 摘要：Simulation has the potential to transform the development of robust algorithms for mobile agents deployed in safety-critical scenarios. However, the poor photorealism and lack of diverse sensor modalities of existing simulation engines remain key hurdles towards realizing this potential. Here, we present VISTA, an open source, data-driven simulator that integrates multiple types of sensors for autonomous vehicles. Using high fidelity, real-world datasets, VISTA represents and simulates RGB cameras, 3D LiDAR, and event-based cameras, enabling the rapid generation of novel viewpoints in simulation and thereby enriching the data available for policy learning with corner cases that are difficult to capture in the physical world. Using VISTA, we demonstrate the ability to train and test perception-to-control policies across each of the sensor types and showcase the power of this approach via deployment on a full scale autonomous vehicle. The policies learned in VISTA exhibit sim-to-real transfer without modification and greater robustness than those trained exclusively on real-world data.

【2】 AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition 标题：AdaFusion：用于位置识别的自适应权重的视觉-LiDAR融合 链接：https://arxiv.org/abs/2111.11739

作者：Haowen Lai,Peng Yin,Sebastian Scherer 机构： Carnegie Mellon University 备注：8 pages, 7 figures 摘要：近年来，场所识别在各种环境中的应用越来越多，例如城市道路、大型建筑以及室内和室外场所的混合。然而，由于不同传感器的局限性和环境外观的变化，这项任务仍然具有挑战性。目前的工作只考虑使用单个传感器，或者简单地组合不同的传感器，忽略了不同传感器的重要性随着环境的变化而变化的事实。本文提出了一种自适应加权视觉激光雷达融合方法AdaFusion，用于学习图像和点云特征的权重。因此，根据目前的环境状况，这两种模式的特点有所不同。权值的学习由网络的注意分支实现，然后与多模态特征提取分支融合。此外，为了更好地利用图像和点云之间的潜在关系，我们设计了一种两阶段融合方法，将二维和三维注意力结合起来。我们的工作在两个公共数据集上进行了测试，实验表明自适应权重有助于提高识别精度和系统对不同环境的鲁棒性。 摘要：Recent years have witnessed the increasing application of place recognition in various environments, such as city roads, large buildings, and a mix of indoor and outdoor places. This task, however, still remains challenging due to the limitations of different sensors and the changing appearance of environments. Current works only consider the use of individual sensors, or simply combine different sensors, ignoring the fact that the importance of different sensors varies as the environment changes. In this paper, an adaptive weighting visual-LiDAR fusion method, named AdaFusion, is proposed to learn the weights for both images and point cloud features. Features of these two modalities are thus contributed differently according to the current environmental situation. The learning of weights is achieved by the attention branch of the network, which is then fused with the multi-modality feature extraction branch. Furthermore, to better utilize the potential relationship between images and point clouds, we design a twostage fusion approach to combine the 2D and 3D attention. Our work is tested on two public datasets, and experiments show that the adaptive weights help improve recognition accuracy and system robustness to varying environments.

【3】 Integrating Imitation Learning with Human Driving Data into Reinforcement Learning to Improve Training Efficiency for Autonomous Driving 标题：将模仿学习与人驾驶数据相结合的强化学习提高自主驾驶训练效率 链接：https://arxiv.org/abs/2111.11673

作者：Heidi Lu 机构：The Harker School, Saratoga Avenue, San Jose, CA 备注：17 pages, 5 figures 摘要：目前用于训练自动驾驶汽车的两种方法是强化学习和模仿学习。本研究通过将监督模仿学习与强化学习相结合，开发了一种新的学习方法和系统方法，使RL训练数据收集过程更加有效。通过结合这两种方法，本研究成功地利用了RL和IL方法的优点。首先，一辆真正的微型机器人汽车被组装起来，并通过模仿学习在6英尺乘9英尺的真实世界轨道上进行训练。在这个过程中，一个手柄控制器被用来通过模仿人类专家驾驶员来控制微型机器人汽车在轨道上行驶，并使用Microsoft AirSim的API手动记录动作。能够生成并收集331个准确的类人奖励训练样本。然后，在Microsoft AirSim模拟器中使用强化学习对一名代理进行6小时的训练，并从模仿学习训练中输入最初的331个奖励数据。经过6小时的训练后，微型机器人车能够在6英尺×9英尺的赛道上自动完成全程，而即使经过30小时的纯RL训练，微型机器人车也无法在赛道上完成全程。新方法减少了80%的训练时间，每小时的平均奖励显著增加。因此，新方法能够节省大量训练时间，并可用于加速自主驾驶中RL的采用，这将有助于在应用于实际场景时产生更高效、更好的长期结果。关键词：强化学习（RL）、模仿学习（IL）、自主驾驶、人类驾驶数据、CNN 摘要：Two current methods used to train autonomous cars are reinforcement learning and imitation learning. This research develops a new learning methodology and systematic approach in both a simulated and a smaller real world environment by integrating supervised imitation learning into reinforcement learning to make the RL training data collection process more effective and efficient. By combining the two methods, the proposed research successfully leverages the advantages of both RL and IL methods. First, a real mini-scale robot car was assembled and trained on a 6 feet by 9 feet real world track using imitation learning. During the process, a handle controller was used to control the mini-scale robot car to drive on the track by imitating a human expert driver and manually recorded the actions using Microsoft AirSim's API. 331 accurate human-like reward training samples were able to be generated and collected. Then, an agent was trained in the Microsoft AirSim simulator using reinforcement learning for 6 hours with the initial 331 reward data inputted from imitation learning training. After a 6-hour training period, the mini-scale robot car was able to successfully drive full laps around the 6 feet by 9 feet track autonomously while the mini-scale robot car was unable to complete one full lap round the track even after 30 hour training pure RL training. With 80% less training time, the new methodology produced significantly more average rewards per hour. Thus, the new methodology was able to save a significant amount of training time and can be used to accelerate the adoption of RL in autonomous driving, which would help produce more efficient and better results in the long run when applied to real life scenarios. Key Words: Reinforcement Learning (RL), Imitation Learning (IL), Autonomous Driving, Human Driving Data, CNN

【4】 PointCrack3D: Crack Detection in Unstructured Environments using a 3D-Point-Cloud-Based Deep Neural Network 标题：PointCrack3D：基于三维点云的深度神经网络在非结构化环境中的裂纹检测 链接：https://arxiv.org/abs/2111.11615

作者：Faris Azhari,Charlotte Sennersten,Michael Milford,Thierry Peynot 机构： Queensland University of Technology (QUT) through theQUT Centre for Robotics and Mining 3 备注：submitted, to be published 摘要：建筑物、天然墙和地下矿山隧道的表面裂缝可能表明严重的结构完整性问题，威胁到结构和环境中人员的安全。及时检测和监测裂缝对于管理这些风险至关重要，特别是如果系统可以通过机器人实现高度自动化。使用深度神经网络的基于视觉的裂纹检测算法已在墙或土木工程隧道等结构化表面显示出前景，但很少有工作涉及岩石悬崖和裸露采矿隧道等高度非结构化环境。为了应对这一挑战，本文提出了一种新的基于三维点云的非结构表面裂纹检测算法PointCrack3D。该方法包括三个关键部分：保持足够裂纹点密度的自适应下采样方法、将每个点分类为裂纹或非裂纹的DNN以及将裂纹点分组为裂纹实例的后处理聚类方法。该方法在一个新的大型天然岩石数据集上进行了实验验证，该数据集包括跨越900 m^2和412条单独裂缝的彩色激光雷达点云。结果表明，总的裂纹检测率为97%，最大宽度超过3 cm的裂纹检测率为100%，显著优于最新技术。此外，为了交叉验证，PointCrack3D应用于在不同位置获取的全新数据集，在训练中根本没有使用，并显示其检测100%的裂纹实例。我们还表征检测性能，裂纹宽度和每个裂纹点的数量之间的关系，提供了一个基础上作出决定的实际部署和未来的研究方向。 摘要：Surface cracks on buildings, natural walls and underground mine tunnels can indicate serious structural integrity issues that threaten the safety of the structure and people in the environment. Timely detection and monitoring of cracks are crucial to managing these risks, especially if the systems can be made highly automated through robots. Vision-based crack detection algorithms using deep neural networks have exhibited promise for structured surfaces such as walls or civil engineering tunnels, but little work has addressed highly unstructured environments such as rock cliffs and bare mining tunnels. To address this challenge, this paper presents PointCrack3D, a new 3D-point-cloud-based crack detection algorithm for unstructured surfaces. The method comprises three key components: an adaptive down-sampling method that maintains sufficient crack point density, a DNN that classifies each point as crack or non-crack, and a post-processing clustering method that groups crack points into crack instances. The method was validated experimentally on a new large natural rock dataset, comprising coloured LIDAR point clouds spanning more than 900 m^2 and 412 individual cracks. Results demonstrate a crack detection rate of 97% overall and 100% for cracks with a maximum width of more than 3 cm, significantly outperforming the state of the art. Furthermore, for cross-validation, PointCrack3D was applied to an entirely new dataset acquired in different locations and not used at all in training and shown to detect 100% of its crack instances. We also characterise the relationship between detection performance, crack width and number of points per crack, providing a foundation upon which to make decisions about both practical deployments and future research directions.

【5】 Tenodesis Grasp Emulator: Kinematic Assessment of Wrist-Driven Orthotic Control 标题：肌腱固定抓取仿真器：手腕驱动矫形器的运动学评价 链接：https://arxiv.org/abs/2111.11524

作者：Erin Y. Chang,Raghid Mardini,Andrew I. W. McPherson,Yuri Gloumakov,Hannah S. Stuart 机构： University of California Berkeley 备注：7 pages, 11 figures, submitted to International Conference on Robotics and Automation (ICRA) 2022. Video Supplement: this https URL 摘要：腕部驱动矫形器被设计用于帮助C6-7脊髓损伤患者，但是，这种控制策略施加的运动学约束可能会阻碍移动性并导致身体异常运动。本研究使用新型Tenodesis抓取仿真器（一种适配矫形器，用于研究手功能未受损的受试者的Tenodesis抓取）来表征身体补偿。受试者执行一系列抓取和释放任务，以比较正常（测试控制）和受约束的腕部驱动模式，显示受约束的显著补偿。此外，还将电机增强模式与传统的腕部驱动操作进行了比较，以探索混合式人-机器人控制的潜在作用。我们发现，被动腕部驱动模式和电机增强模式在测试的各种任务中扮演不同的角色。因此，我们得出结论，灵活的控制方案可以根据手头的任务改变干预，有可能在未来的工作中减少补偿。 摘要：Wrist-driven orthotics have been designed to assist people with C6-7 spinal cord injury, however, the kinematic constraint imposed by such a control strategy can impede mobility and lead to abnormal body motion. This study characterizes body compensation using the novel Tenodesis Grasp Emulator, an adaptor orthotic that allows for the investigation of tenodesis grasping in subjects with unimpaired hand function. Subjects perform a series of grasp-and-release tasks in order to compare normal (test control) and constrained wrist-driven modes, showing significant compensation as a result of the constraint. A motor-augmented mode is also compared against traditional wrist-driven operation, to explore the potential role of hybrid human-robot control. We find that both the passive wrist-driven and motor-augmented modes fulfill different roles throughout various tasks tested. Thus, we conclude that a flexible control scheme that can alter intervention based on the task at hand holds the potential to reduce compensation in future work.

【6】 Universal Swarm Computing by Nanorobots 标题：基于纳米机器人的通用群计算 链接：https://arxiv.org/abs/2111.11503

作者：Alireza Rowhanimanesh,Mohammad-R Akbarzadeh-T 机构： Department of Electrical Engineering, University of Neyshabur, Neyshabur, Iran., Department of Electrical Engineering, Center of Excellence on Soft Computing and, Intelligent Information Processing, Ferdowsi University of Mashhad, Mashhad, Iran. 摘要：为纳米机器人实现通用计算单元在创建新的和广泛的应用阵列方面非常有希望，特别是在分布式计算领域。然而，由于纳米尺寸设计在计算、感官和感知以及驱动等方面的物理限制，这种实现也是一个具有挑战性的问题。本文提出了一种基于基础代理（BAS）的分布式群体计算新概念来解决这一问题的理论基础。提出的BA是纳米机器人的抽象模型，可以计算一个非常简单的基函数，称为B函数。本文从数学上证明了群BAs具有普适函数逼近性质，能够精确逼近函数。然后通过分析证明，通过简单地调整环境中BAs的浓度，可以很容易地对BAs群进行重新编程，以计算所需的函数。我们进一步提出了一种特定的BAs结构，使其能够执行分布式计算，例如在生物组织和纳米医学的水环境中。该结构的硬件复杂度旨在保持较低，以便通过当今技术更合理地实现。最后，通过仿真实例说明了该方法的性能。 摘要：Realization of universal computing units for nanorobots is highly promising in creating new and wide arrays of applications, particularly in the realm of distributed computation. However, such realization is also a challenging problem due to the physical limitations of nanometer-sized designs such as in computation, sensory and perception as well as actuation. This paper proposes a theoretical foundation for solving this problem based on a novel notion of distributed swarm computing by basis agents (BAs). The proposed BA is an abstract model for nanorobots that can compute a very simple basis function called B-function. It is mathematically shown here that a swarm of BAs has the universal function approximation property and can accurately approximate functions. It is then analytically demonstrated that a swarm of BAs can be easily reprogrammed to compute desired functions simply by adjusting the concentrations of BAs in the environment. We further propose a specific structure for BAs which enable them to perform distributed computing such as in the aqueous environment of living tissues and nanomedicine. The hardware complexity of this structure aims to remain low to be more reasonably realizable by today technology. Finally, the performance of the proposed approach is illustrated by a simulation example.

【7】 Robust Control of Nanoscale Drug Delivery System in Atherosclerosis: A Mathematical Approach 标题：动脉粥样硬化纳米级给药系统的鲁棒控制：一种数学方法 链接：https://arxiv.org/abs/2111.11499

作者：Alireza Rowhanimanesh,Mohammad-R Akbarzadeh-T 机构： Department of Electrical Engineering, University of Neyshabur, Neyshabur, Iran., Department of Electrical Engineering, Center of Excellence on Soft Computing and Intelligent Information 摘要：本文提出了一种用于治疗动脉粥样硬化的纳米级药物输送系统鲁棒控制的数学方法。首先，引入了一种新的非线性集总模型用于动脉壁内的物质输运，并与原分布参数模型进行了比较，评估了其精度。然后，基于滑模控制的概念，设计了一个智能给药纳米颗粒的抽象模型。与纳米机器人技术上的竞争策略相比，所提出的纳米颗粒携带更简单的硬件穿透动脉内壁，在技术上更可行。最后，根据该集总模型和非线性控制理论，从数学上证明了存在不确定性时整个系统的稳定性。一个著名模型的模拟结果以及与早期基准方法的比较表明，即使管腔中的LDL浓度很高，拟议的纳米级药物输送系统也成功地将药物消耗水平降低了16%，并将内皮、内膜、内弹性层（IEL）中的LDL水平降低了16%和不健康动脉壁的中层分别高达14.6%、50.5%、51.8%和64.4%。 摘要：This paper proposes a mathematical approach for robust control of a nanoscale drug delivery system in treatment of atherosclerosis. First, a new nonlinear lumped model is introduced for mass transport in the arterial wall, and its accuracy is evaluated in comparison with the original distributed-parameter model. Then, based on the notion of sliding-mode control, an abstract model is designed for a smart drug delivery nanoparticle. In contrast to the competing strategies on nanorobotics, the proposed nanoparticles carry simpler hardware to penetrate the interior arterial wall and become more technologically feasible. Finally, from this lumped model and the nonlinear control theory, the overall system's stability is mathematically proven in the presence of uncertainty. Simulation results on a well-known model, and comparisons with earlier benchmark approaches, reveals that even when the LDL concentration in the lumen is high, the proposed nanoscale drug delivery system successfully reduces the drug consumption levels by as much as 16% and the LDL level in the Endothelium, Intima, Internal Elastic Layer (IEL) and Media layers of an unhealthy arterial wall by as much as 14.6%, 50.5%, 51.8%, and 64.4%, respectively.

【8】 Real-time ground filtering algorithm of cloud points acquired using Terrestrial Laser Scanner (TLS) 标题：地面激光扫描仪(TLS)获取云点的实时地面滤波算法 链接：https://arxiv.org/abs/2111.11481

作者：Nelson Diaz,Omar Gallo,Jhon Caceres,Hernan Porras 机构：Department of Computer Science, Universidad de Investigaci´on y Desarrollo, Bucaramanga, Colombia, Department of Civil Engineering, Universidad Industrial de Santander, Bucaramanga 备注：25 pages, 7 figures 摘要：基于点云的三维建模需要地面过滤算法，将地面与非地面对象分离。本研究提出两种地面滤波算法。第一种是基于法向量的。根据计算k近邻的过程，它有两种变体。第二种算法基于将云点转换为体素结构。为了对这两种算法进行评估，根据它们的执行时间、有效性和效率对这两种算法进行了比较。结果表明，基于体素结构的地面滤波算法在执行时间、有效性和效率方面都比法向量地面滤波算法快。 摘要：3D modeling based on point clouds requires ground-filtering algorithms that separate ground from non-ground objects. This study presents two ground filtering algorithms. The first one is based on normal vectors. It has two variants depending on the procedure to compute the k-nearest neighbors. The second algorithm is based on transforming the cloud points into a voxel structure. To evaluate them, the two algorithms are compared according to their execution time, effectiveness and efficiency. Results show that the ground filtering algorithm based on the voxel structure is faster in terms of execution time, effectiveness, and efficiency than the normal vector ground filtering.

机器翻译，仅供参考