Deep Reinforcement Learning for Robot Collision Avoidance With Self-State-Attention and Sensor Fusion
Deep Reinforcement Learning for Robot Collision Avoidance With Self-State-Attention and Sensor Fusion
复制标题
通过自状态注意和传感器融合实现机器人防撞的深度强化学习
DOI：
--
复制
发表时间：
2022
影响因子：
5.2
通讯作者：
Yong
中科院分区：
文献类型：
--
作者：
Yiheng Han;I. Zhan;Wang Zhao;Jia;Ziyang Zhang;Yaoyuan Wang;Yong
3D LiDAR传感器可以提供环境的3D点云，广泛应用于汽车导航；而2D LiDAR传感器只能提供2D扫平面的点云，只能用于高度较小的机器人导航，例如拖地机器人。在这封信中，我们提出了一种简单而有效的深度强化学习（DRL）方法以及我们的自状态注意单元，并给出了一种解决方案，可以使用低成本设备（即2D LiDAR传感器和单目相机）来导航一米高的高移动机器人。总体流程是：（1）借助 2D LiDAR 传感器数据（即固定高度平面上的点云）推断 RGB 图像的密集深度信息，（2）进一步将密集深度图过滤为 2D 最小深度数据并与 2D LiDAR 数据融合，以及（3）利用 DRL 模块和我们的自状态注意单元来解决可以处理部分准确数据的部分可观察序列决策问题。我们提出了一种新颖的机器人导航DRL训练方案，提出了一种简洁有效的自状态注意单元，并证明应用该单元可以代替多阶段训练，取得更好的结果和泛化能力。对模拟数据和真实机器人的实验表明，我们的方法只需使用低成本的 2D LiDAR 传感器和单目摄像头即可有效避免碰撞。
3D LiDAR sensors can provide 3D point clouds of the environment, and are widely used in automobile navigation; while 2D LiDAR sensors can only provide point cloud in a 2D sweeping plane, and then are only used for navigating robots of small height, e.g., floor mopping robots. In this letter, we propose a simple yet effective deep reinforcement learning (DRL) method with our self-state-attention unit and give a solution that can use low-cost devices (i.e., a 2D LiDAR sensor and a monocular camera) to navigate a tall mobile robot of one meter height. The overrall pipeline is that we (1) infer the dense depth information of RGB images with the aid of the 2D LiDAR sensor data (i.e., point clouds in a plane with fixed height), (2) further filter the dense depth map into a 2D minimal depth data and fuse with 2D LiDAR data, and (3) make use of DRL module with our self-state-attention unit to a partially observable sequential decision making problem that can deal with partially accurate data. We present a novel DRL training scheme for robot navigation, proposing a concise and effective self-state-attention unit and proving that applying this unit can replace multi-stage training, achieve better results and generalization capability. Experiments on both simulated data and a real robot show that our method can perform efficient collision avoidance only using low-cost 2D LiDAR sensor and monocular camera.