机器人相关每日论文速递[11.19]

同步公众号(arXiv每日论文速递),欢迎关注,感谢支持哦~


cs.RO 方向,今日共计23篇

【1】 A gamified simulator and physical platform for self-driving algorithm training and validation
标题:用于自驾驶算法训练和验证的游戏化模拟器和物理平台
作者: Joshua E. Siegel, Yongbin Sun
链接:arxiv.org/abs/1911.0775

【2】 Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions
标题:用于改善水下恶劣条件下人-机器人合作的机器视觉
作者: Md Jahidul Islam
链接:arxiv.org/abs/1911.0762

【3】 A Hierarchical Framework to Generate Robust Biped Locomotion Based on Divergent Component of Motion
标题:基于运动发散分量的Biped鲁棒运动生成分层框架
作者: Mohammadreza Kasaei, Artur Pereira
链接:arxiv.org/abs/1911.0750

【4】 Object Finding in Cluttered Scenes Using Interactive Perception
标题:使用交互式感知的杂乱场景中的目标发现
作者: Tonci Novkovic, Juan Nieto
链接:arxiv.org/abs/1911.0748

【5】 Fast 2D Map Matching Based on Area Graphs
标题:基于面积图的快速二维地图匹配
作者: Jiawei Hou, Sören Schwertfeger
备注:8 pages, 42 figures, accepted by Robio 2019
链接:arxiv.org/abs/1911.0743

【6】 Development of MirrorShape: High Fidelity Large-Scale Shape Rendering Framework for Virtual Reality
标题:MirrorShape的开发:面向虚拟现实的高保真大规模图形渲染框架
作者: Aleksey Fedoseev, Dzmitry Tsetserukou
备注:Accepted to the 25th ACM Symposium on Virtual Reality Software and Technology (VRST'19), ACM copyright
链接:arxiv.org/abs/1911.0740

【7】 Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization
标题:基于学习能见度优化的监视规避博弈策略综合
作者: Suda Bharadwaj, Ufuk Topcu
链接:arxiv.org/abs/1911.0739

【8】 Robotic Sculpting with Collision-free Motion Planning in Voxel Space
标题:体素空间中具有无碰撞运动规划的机器人雕塑
作者: Abhinav Jain, Frank Dellaert
链接:arxiv.org/abs/1911.0734

【9】 IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
标题:宜家家具长视距复杂操作任务组装环境
作者: Youngwoon Lee, Joseph J. Lim
链接:arxiv.org/abs/1911.0724

【10】 Optimal Control of a Differentially Flat 2D Spring-Loaded Inverted Pendulum Model
标题:二维微分平坦弹簧倒立摆模型的最优控制
作者: Hua Chen, Wei Zhang
链接:arxiv.org/abs/1911.0716

【11】 Ground and Non-Ground Separation Filter for UAV Lidar Point Cloud
标题:无人机激光雷达点云的地面和非地面分离滤波器
作者: Geesara Prathap, Alexandr Klimchik
链接:arxiv.org/abs/1911.0699

【12】 Design of the First Insect-scale Spinning-wing Robot
标题:首台昆虫鳞片旋翼机器人的设计
作者: Palak Bhushan, Claire Tomlin
备注:6 pages. (under review) submitted to Robotics and Automation Letters 2019
链接:arxiv.org/abs/1911.0694

【13】 Flexoskeleton printing for versatile insect-inspired robots
标题:用于多功能昆虫启发机器人的柔性骨架打印
作者: Mingsong Jiang, Nicholas G. Gravish
链接:arxiv.org/abs/1911.0689

【14】 Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning
标题:基于深度强化学习的自适应主从编队控制和避障
作者: Yanlin Zhou, Dapeng Wu
备注:Accepted IROS 2019 paper with minor revisions
链接:arxiv.org/abs/1911.0688

【15】 The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections
标题:IND数据集:德国十字路口自然主义道路用户轨迹的无人机数据集
作者: Julian Bock, Lutz Eckstein
链接:arxiv.org/abs/1911.0760

【16】 Towards Robust RGB-D Human Mesh Recovery
标题:面向稳健的RGB-D人类网格恢复
作者: Ren Li, Ziyan Wu
链接:arxiv.org/abs/1911.0738

【17】 A Sketch-Based System for Human-Guided Constrained Object Manipulation
标题:一种基于草图的人引导约束对象操作系统
作者: Sina Masnadi, Odest Chadwicke Jenkins
链接:arxiv.org/abs/1911.0734

【18】 Prescribed Performance Distance-Based Formation Control of Multi-Agent Systems (Extended Version)
标题:基于规定性能距离的多智能体系统编队控制(扩展版)
作者: Farhad Mehdifar, Mahdi Baradarannia
链接:arxiv.org/abs/1911.0726

【19】 Learning from Trajectories via Subgoal Discovery
标题:通过子目标发现从轨迹中学习
作者: Sujoy Paul, Amit K. Roy-Chowdhury
备注:NeurIPS 2019 Accepted
链接:arxiv.org/abs/1911.0722

【20】 Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance
标题:软专家指导下不完善演示的强化学习
作者: Mingxuan Jing, Huaping Liu
备注:Accepted to AAAI 2020. Xiaojian Ma and Mingxuan Jing contributed equally to this work
链接:arxiv.org/abs/1911.0710

【21】 Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
标题:强化学习非策略评估的实证研究
作者: Cameron Voloshin, Yisong Yue
链接:arxiv.org/abs/1911.0685

【22】 Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient
标题:深确定性策略梯度中潜在轨迹优化的改进探索
作者: Kevin Sebastian Luck, Jonathan Scholz
备注:Accepted for IROS 2019
链接:arxiv.org/abs/1911.0683

【23】 Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning
标题:数据高效的形态和行为与深度强化学习的共同适应
作者: Kevin Sebastian Luck, Roberto Calandra
备注:Accepted for the Conference on Robot Learning 2019
链接:arxiv.org/abs/1911.0683

机器翻译,仅供参考

发布于 2019-11-19 11:23