arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.07709cs.RO
收藏

基于强化学习的自适应环境建模在复杂场景避碰中的应用

Adaptive Environment Modeling Based Reinforcement Learning for Collision Avoidance in Complex Scenes

Harbin Institute of Technology(哈尔滨工业大学);Southern University of Science and Technology(南方科技大学);The University of Hongkong(香港大学)

Shuaijun Wang, Rui Gao, Ruihua Han, Shengduo Chen, Chengyang Li, Qi Hao

摘要:

拥挤场景中机器人导航避碰的主要挑战在于准确的环境建模、快速感知和可靠的运动规划策略。本文提出了一种新的基于自适应环境模型的避碰强化学习(即,AEMCARL)框架的无人驾驶机器人,以实现无碰撞运动在具有挑战性的导航方案。这项工作的新颖性有三个方面:(1)开发用于环境建模的门控循环单元(GRU)分层网络;(2)开发具有注意力模块的自适应感知机制;(3)开发强化学习(RL)框架的自适应奖励函数,以联合训练环境模型、感知功能和运动规划策略。所提出的方法进行了测试与健身房露台模拟器和一组机器人(哈士奇和海龟)在各种拥挤的场景。仿真和实验结果表明,该方法优于基线方法的性能。

英文摘要:

The major challenges of collision avoidance for robot navigation in crowded scenes lie in accurate environment modeling, fast perceptions, and trustworthy motion planning policies. This paper presents a novel adaptive environment model based collision avoidance reinforcement learning (i.e., AEMCARL) framework for an unmanned robot to achieve collision-free motions in challenging navigation scenarios. The novelty of this work is threefold: (1) developing a hierarchical network of gated-recurrent-unit (GRU) for environment modeling; (2) developing an adaptive perception mechanism with an attention module; (3) developing an adaptive reward function for the reinforcement learning (RL) framework to jointly train the environment model, perception function and motion planning policy. The proposed method is tested with the Gym-Gazebo simulator and a group of robots (Husky and Turtlebot) under various crowded scenes. Both simulation and experimental results have demonstrated the superior performance of the proposed method over baseline methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑