2021 IEEE International Conference on Robotics and Automation (ICRA)最新文献_第10页

Adversarially-trained Hierarchical Feature Extractor for Vehicle Re-identification 用于车辆再识别的对抗训练分层特征提取器

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9561632

P. Shyam, Kuk-Jin Yoon, Kyung-soo Kim

{"title":"Adversarially-trained Hierarchical Feature Extractor for Vehicle Re-identification","authors":"P. Shyam, Kuk-Jin Yoon, Kyung-soo Kim","doi":"10.1109/ICRA48506.2021.9561632","DOIUrl":"https://doi.org/10.1109/ICRA48506.2021.9561632","url":null,"abstract":"Vehicle Re-identification (Re-ID) aims to retrieve all instances of query vehicle images present in an image pool. However viewpoint, illumination, and occlusion variations along with subtle differences between two unique images pose a significant challenge towards achieving an effective system. In this paper, we emphasize upon enhancing the performance of visual feature based ReID system by improving feature embedding quality and propose (1) an attention-guided hierarchical feature extractor (HFE) that leverages the structure of a backbone CNN to extract coarse and fine-grained features and (2) to train the proposed network within a hard negative adversarial framework that generates samples exhibiting extreme variations, encouraging the network to extract important distinguishing features across varying scales. To demonstrate the effectiveness of the proposed framework we use VERI-Wild, VRIC and Veri-776 datasets that exhibit extreme intra-class and minute inter-class differences and achieve state-of-the-art (SoTA) performance. Codes related to this paper are publicly available at https://github.com/PS06/VReID.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"225 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133813098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

An Underactuated Gripper based on Car Differentials for Self-Adaptive Grasping with Passive Disturbance Rejection 基于汽车差速器的欠驱动夹持器被动抗扰自适应抓取

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9561725

Qiujie Lu, Jinhong Wang, Zhuang Zhang, Genliang Chen, Hao Wang, Nicolás Rojas

{"title":"An Underactuated Gripper based on Car Differentials for Self-Adaptive Grasping with Passive Disturbance Rejection","authors":"Qiujie Lu, Jinhong Wang, Zhuang Zhang, Genliang Chen, Hao Wang, Nicolás Rojas","doi":"10.1109/ICRA48506.2021.9561725","DOIUrl":"https://doi.org/10.1109/ICRA48506.2021.9561725","url":null,"abstract":"We introduce an underactuated differential-based robot gripper able to perform self-adaptive grasping with passive disturbance rejection. The gripper utilises three car differential systems to achieve self-adaptiveness with a single actuator: a base differential for distributing power from the motor to the fingers, and two independent finger differentials for controlling the proximal and distal joints. Linear and torsional springs are cleverly added to these differentials to allow the return of the fingers and the gripper-object system to equilibrium, thus enabling the gripper rejecting unexpected external forces applied to the fingers after securing a grasp. This novel design provides passive disturbance rejection without implementing complicated control systems and is the main contribution of this paper. Moreover, the differentials allow the gripper to perform not only self-adaptive power grasp but also precision grasp, provide it with a large force transmission efficiency, and facilitate the prediction of grasping position. We analyse the static model of the introduced differential system and evaluate the gripper design via four sets of experiments. Numerical and empirical results clearly demonstrate the viability of the proposed grasper.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133813415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Shaped Policy Search for Evolutionary Strategies using Waypoints* 基于路径点的进化策略形策略搜索*

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9561607

Kiran Lekkala, L. Itti

引用次数: 1

Robot Motion Planning with Human-Like Motion Patterns based on Human Arm Movement Primitive Chains* 基于人臂运动原始链的类人运动模式机器人运动规划*

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9560921

Shiqiu Gong, Jing Zhao, Biyun Xie

引用次数: 2

VelocityNet: Motion-Driven Feature Aggregation for 3D Object Detection in Point Cloud Sequences VelocityNet:用于点云序列中3D物体检测的运动驱动特征聚合

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9561644

David Emmerichs, Peter Pinggera, B. Ommer

{"title":"VelocityNet: Motion-Driven Feature Aggregation for 3D Object Detection in Point Cloud Sequences","authors":"David Emmerichs, Peter Pinggera, B. Ommer","doi":"10.1109/ICRA48506.2021.9561644","DOIUrl":"https://doi.org/10.1109/ICRA48506.2021.9561644","url":null,"abstract":"The most successful methods for LiDAR-based 3D object detection use sequences of point clouds in order to exploit the increased data density through temporal aggregation. However, common aggregation methods are rarely able to capture fast-moving objects appropriately. These objects are displaced by large distances between frames and naive approaches are not able to successfully leverage the full amount of information spread across time. Yet, especially in autonomous driving scenarios, fast-moving objects are most crucial to detect as they actively take part in highly dynamic traffic situations. This work presents a novel network architecture called VelocityNet which is explicitly designed to temporally align features according to object motion. Our approach extends traditional 3D convolutions by a motion-driven deformation of the convolution kernels across the temporal dimension. The required motion information can be obtained from various sources, ranging from external computation or complementary sensors to an integrated network branch which is trained jointly with the object detection task. The explicit feature alignment allows the training process to focus on the object detection problem and results in a significant increase in detection performance compared to the popular PointPillars baseline, not only for dynamic but also for static objects. We evaluate our approach on the nuScenes dataset and analyze the main reasons for the observed performance gains.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"318 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115447417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Autonomous Vehicle Motion Planning via Recurrent Spline Optimization 基于循环样条优化的自动驾驶汽车运动规划

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9560867

Wenda Xu, Qian Wang, J. Dolan

{"title":"Autonomous Vehicle Motion Planning via Recurrent Spline Optimization","authors":"Wenda Xu, Qian Wang, J. Dolan","doi":"10.1109/ICRA48506.2021.9560867","DOIUrl":"https://doi.org/10.1109/ICRA48506.2021.9560867","url":null,"abstract":"Trajectory planning in dynamic environments can be decomposed into two sub-problems: 1) planning a path to avoid static obstacles, 2) then planning a speed profile to avoid dynamic obstacles. This is also called path-speed decomposition. In this work, we present a novel approach to solve the first sub-problem, motion planning with static obstacles. From an optimization perspective, motion planning for autonomous vehicles can be viewed as non-convex constrained nonlinear optimization, which requires a good enough initial guess to start and is often sensitive to algorithm parameters. We formulate motion planning as convex spline optimization. The convexity of the formulated problem makes it able to be solved fast and reliably, while guaranteeing a global optimum. We then reorganize the constrained spline optimization into a recurrent formulation, which further reduces the computational time to be linear in the optimization horizon size. The proposed method can be applied to both trajectory generation and motion planning problems. Its effectiveness is demonstrated in challenging scenarios such as tight lane changes and sharp turns.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115753874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Contact-Implicit Trajectory Optimization With Learned Deformable Contacts Using Bilevel Optimization 基于双层优化的学习变形接触隐式轨迹优化

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9561521

Yifan Zhu, Zherong Pan, Kris K. Hauser

引用次数: 9

Dynamic Primitives and Optimal Feedback Control for the Manipulation of Complex Objects 复杂对象操作的动态原语与最优反馈控制

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9561352

Reza Sharif Razavian, Salah Bazzi, Rashida Nayeem, Mohsen Sadeghi, D. Sternad

{"title":"Dynamic Primitives and Optimal Feedback Control for the Manipulation of Complex Objects","authors":"Reza Sharif Razavian, Salah Bazzi, Rashida Nayeem, Mohsen Sadeghi, D. Sternad","doi":"10.1109/ICRA48506.2021.9561352","DOIUrl":"https://doi.org/10.1109/ICRA48506.2021.9561352","url":null,"abstract":"Modern computer algorithms easily beat world champions in chess or Go, but state-of-the-art robots are still outperformed by two-year-old’s in manipulating the pieces, let alone interacting with more complex objects. This work studied human behavior when moving an underactuated object, a cup with a ball rolling inside creating internal dynamics like sloshing coffee in a cup. The objective was to develop a control model that could replicate human behavior. Human movement data were collected for transporting this cup-and-ball system, both with and without external perturbations. The existing models in the human control literature, including maximum smoothness, optimal feedback control with minimum effort, and dynamic primitives with impedance were revisited for this challenging task. As these control models were primarily developed for unconstrained reaching movements, they could replicate human trajectories when transporting a rigid object. However, they fell short when the object introduced complex interaction forces due to its internal dynamics. Therefore, this study extended the framework of dynamic primitives and used an optimal controller to generate a maximally smooth zero-force trajectory for the impedance operator when interacting with perturbations from the object or the environment. Given the challenges that robot control still faces when interacting with complex objects, these findings may inform the development of bio-inspired controllers for robotic manipulation.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124553303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Comparison of predictive controllers for locomotion and balance recovery of quadruped robots 四足机器人运动与平衡恢复预测控制器的比较

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9560976

Thomas Corbères, T. Flayols, Pierre-Alexandre Léziart, Rohan Budhiraja, P. Souéres, Guilhem Saurel, N. Mansard

{"title":"Comparison of predictive controllers for locomotion and balance recovery of quadruped robots","authors":"Thomas Corbères, T. Flayols, Pierre-Alexandre Léziart, Rohan Budhiraja, P. Souéres, Guilhem Saurel, N. Mansard","doi":"10.1109/ICRA48506.2021.9560976","DOIUrl":"https://doi.org/10.1109/ICRA48506.2021.9560976","url":null,"abstract":"As locomotion decisions must be taken by considering the future, most existing quadruped controllers are based on a model predictive controller (MPC) with a reduced model of the dynamics to generate the motion and a whole- body controller to execute it. Yet the simplifying assumptions of the MPC are often chosen ad-hoc or by intuition. In this article, we focus on a set of MPCs and analyze the effect of chosen model reductions on the behavior of the robot. Based on existing formulations, we present additional controllers to better understand the influence of model reductions on the controller capabilities. Finally, we propose a robust predictive controller capable of optimizing the foot placements, gait period, center- of-mass trajectory and ground reaction forces. The behavior of these controllers is statistically evaluated in simulation. This empirical study aims to assess the relative importance of the components of the optimal control problem (variables, costs, dynamics) to be able to take reasoned decisions instead of arbitrarily emphasizing or neglecting some of them. We also provide a qualitative study in simulation and on the real robot Solo-12.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114747965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

DWA-RL: Dynamically Feasible Deep Reinforcement Learning Policy for Robot Navigation among Mobile Obstacles DWA-RL:机器人在移动障碍物中导航的动态可行深度强化学习策略

2021 IEEE International Conference on Robotics and Automation (ICRA) Pub Date : 2021-05-30 DOI: 10.1109/ICRA48506.2021.9561462

Utsav Patel, Nithish Kumar, A. Sathyamoorthy, Dinesh Manocha

{"title":"DWA-RL: Dynamically Feasible Deep Reinforcement Learning Policy for Robot Navigation among Mobile Obstacles","authors":"Utsav Patel, Nithish Kumar, A. Sathyamoorthy, Dinesh Manocha","doi":"10.1109/ICRA48506.2021.9561462","DOIUrl":"https://doi.org/10.1109/ICRA48506.2021.9561462","url":null,"abstract":"We present a novel Deep Reinforcement Learning (DRL) based policy to compute dynamically feasible and spatially aware velocities for a robot navigating among mobile obstacles. Our approach combines the benefits of the Dynamic Window Approach (DWA) in terms of satisfying the robot’s dynamics constraints with state-of-the-art DRL-based navigation methods that can handle moving obstacles and pedestrians well. Our formulation achieves these goals by embedding the environmental obstacles’ motions in a novel low-dimensional observation space. It also uses a novel reward function to positively reinforce velocities that move the robot away from the obstacle’s heading direction leading to significantly lower number of collisions. We evaluate our method in realistic 3-D simulated environments and on a real differential drive robot in challenging dense indoor scenarios with several walking pedestrians. We compare our method with state-of-the-art collision avoidance methods and observe significant improvements in terms of success rate (up to 33% increase), number of dynamics constraint violations (up to 61% decrease), and smoothness. We also conduct ablation studies to highlight the advantages of our observation space formulation, and reward structure.","PeriodicalId":108312,"journal":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114512586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 27