Excavation of irregular rigid objects in clutter, such as fragmented rocks and wood blocks, is very challenging due to their complex interaction dynamics and highly variable geometries. In this paper, we adopt reinforcement learning (RL) to tackle this challenge and learn policies to plan for a sequence of excavation trajectories for irregular rigid objects, given point clouds of excavation scenes. Moreover, we separately learn a compact representation of the point cloud on geometric tasks that do not require human labeling. We show that using the representation reduces training time for RL, while achieving similar asymptotic performance compare to an end-to-end RL algorithm. When using a policy trained in simulation directly on a real scene, we show that the policy trained with the representation outperforms end-to-end RL. To our best knowledge, this paper presents the first application of RL to plan a sequence of excavation trajectories of irregular rigid objects in clutter.
Multi-Task Reinforcement Learning of Drone Aerobatics by Exploiting Geometric Symmetries
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);WINDY Lab, School of Engineering, Westlake University(西湖大学工程学院WINDY实验室);School of Automation Science and Electrical Engineering, Beihang University(北航自动化科学与电气工程学院)
Geometric Reinforcement Learning For Robotic Manipulation
Istanbul Technical University(伊斯坦布尔理工大学);University of Trento(特伦托大学);Technical University of Munich(慕尼黑工业大学);Munich Institute of Robotics and Machine Intelligence(慕尼黑机器人与机器智能研究所);Colorado State University(科罗拉多州立大学);Aalto University(阿尔托大学)
DexRepNet: Learning Dexterous Robotic Grasping Network with Geometric and Spatial Hand-Object Representations
College of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院);Key Lab of CS&AUS of Zhejiang Province(浙江省计算机与应用系统安全重点实验室);Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系)
Tactical Reward Shaping: Bypassing Reinforcement Learning with Strategy-Based Goals
ShanghaiTech University(上海科技大学)
深度强化学习(DRL)已经显示出其有前途的能力,可以直接从试错中学习最优策略。然而,如果奖励函数定义的学习目标“不是最佳”,学习可能会受到阻碍。我们证明,通过以一种反直觉但智能的方式设置竞争的目标/目标,而不是通过许多小时的DRL模拟来尝试解决方案,可以快速收敛到一个获胜的策略。ICRA-DJI RoboMaster AI Challenge是一款在部分可观察环境中进行机器人之间合作和竞争的游戏,与Counter-Strike游戏非常相似。与传统的游戏方法不同,奖励是在赢得比赛或击中敌人时给予的,我们的DRL算法在处于几何战略优势时奖励我们的机器人,这隐含地增加了获胜的机会。此外,我们使用深度Q学习(DQL)来生成移动的多智能体路径,通过避免碰撞来改善两个机器人之间的合作。最后,我们实现了一个变种A* 算法与DQL相同的隐式几何目标和比较结果。我们的结论是,一个良好的设定的目标可以提出问题的需要学习算法,与几何为基础的搜索优于DQL在许多数量级。
End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation
A*STAR Institute of High Performance Computing (IHPC)(新加坡科技研究局高性能计算研究所);A*STAR Institute of Information Research (IR)(新加坡科技研究局信息研究所);National University of Singapore (NUS)(新加坡国立大学);Alibaba DAMO Academy(阿里巴巴达摩院)