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.
翻译:在拥挤的场景中避免机器人导航碰撞的主要挑战在于精确的环境建模、快速认知和可信赖的运动规划政策,本文件介绍了基于避免碰撞强化学习(即AEMCARL)的新的适应性环境模型框架,目的是让无人驾驶机器人在具有挑战性的导航场景中实现无碰撞动作。这项工作的新颖之处有三:(1) 开发一个环境建模的门锁-经常单位(GRU)的分级网络;(2) 开发一个有关注模块的适应性感知机制;(3) 开发一个强化学习(RL)框架的适应性奖励功能,以联合培训环境模型、认知功能和运动规划政策;与Gym-Gazebo模拟器和一组机器人(Husky和Turtbot)在各种拥挤的场景下测试拟议方法。模拟和实验结果都表明拟议方法优于基线方法。