论文标题
基于多任务增强学习的基于动态对象跟踪和掌握的移动操作控制
Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping
论文作者
论文摘要
由于机器人系统和非结构化工作环境的高复杂性，敏捷的移动操纵器的敏捷控制是具有挑战性的。用随机轨迹跟踪和抓住动态对象甚至更难。在本文中，提出了一个基于多任务的增强学习的移动操纵控制框架，以实现一般的动态对象跟踪和掌握。选择几种基本的动态轨迹作为任务训练集。为了改善实践中的策略概括，在训练过程中引入了随机噪声和动态随机化。广泛的实验表明，我们经过训练的政策可以适应看不见的随机动态轨迹，其跟踪误差约为0.1m，动态对象的成功率为75 \％抓取成功率。训练有素的政策也可以成功部署在真正的移动操纵器上。
Agile control of mobile manipulator is challenging because of the high complexity coupled by the robotic system and the unstructured working environment. Tracking and grasping a dynamic object with a random trajectory is even harder. In this paper, a multi-task reinforcement learning-based mobile manipulation control framework is proposed to achieve general dynamic object tracking and grasping. Several basic types of dynamic trajectories are chosen as the task training set. To improve the policy generalization in practice, random noise and dynamics randomization are introduced during the training process. Extensive experiments show that our policy trained can adapt to unseen random dynamic trajectories with about 0.1m tracking error and 75\% grasping success rate of dynamic objects. The trained policy can also be successfully deployed on a real mobile manipulator.
