Autonomous robots would benefit a lot by gaining the ability to manipulate their environment to solve path planning tasks, known as the Navigation Among Movable Obstacle (NAMO) problem. In this paper, we present a deep reinforcement learning approach for solving NAMO locally, near narrow passages. We train parallel agents in physics simulation using an Advantage Actor-Critic based algorithm with a multi-modal neural network. We present an online policy that is able to push obstacles in a non-axial-aligned fashion, react to unexpected obstacle dynamics in real-time, and solve the local NAMO problem. Experimental validation in simulation shows that the presented approach generalises to unseen NAMO problems in unknown environments. We further demonstrate the implementation of the policy on a real quadrupedal robot, showing that the policy can deal with real-world sensor noises and uncertainties in unseen NAMO tasks.

翻译：自主机器人若能具备操纵环境以解决路径规划任务的能力，将获得显著益处，这一能力被称为“可移动障碍物导航”（NAMO）问题。本文提出一种深度强化学习方法，用于在狭窄通道附近局部解决NAMO问题。我们采用基于优势动作-评论家算法与多模态神经网络的物理仿真方法，训练并行智能体。所提出的在线策略能够以非轴向对齐方式推挤障碍物，实时响应意外的障碍物动态变化，并解决局部NAMO问题。仿真实验验证表明，该方法可泛化至未知环境中的未见过NAMO问题。我们进一步在真实四足机器人上部署该策略，证明该策略能够应对真实世界中的传感器噪声与不确定性，完成未知NAMO任务。