arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.05985cs.LGcs.CVcs.RO
收藏

基于视觉的机器人深度强化学习中关系归纳偏差的图神经网络

Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control

Technical University of Munich(慕尼黑工业大学)

Marco Oliva, Soubarna Banik, Josip Josifovski, Alois Knoll

摘要:

最先进的强化学习算法主要从数值状态向量或图像中学习策略。这两种方法通常不考虑任务的结构知识,这在机器人应用中特别普遍,如果利用,可以有益于学习。这项工作引入了一种神经网络架构,该架构结合了关系归纳偏差和视觉反馈,以学习机器人操作的有效位置控制策略。我们推导出一个图形表示模型的机械手的物理结构,并结合机器人的内部状态与低维描述的图像编码网络生成的视觉场景。在此基础上,用强化学习训练的图神经网络预测关节速度来控制机器人。我们进一步介绍了一种不对称的方法,训练图像编码器单独的政策,使用监督学习。实验结果表明,对于一个2自由度的平面机器人在一个几何简单的2D环境中,学习表示的视觉场景可以取代访问的显式坐标的到达目标,而不损害的质量和样本效率的政策。我们进一步展示了该模型的能力,以提高样本效率的6自由度的机器人手臂在视觉上逼真的3D环境。

英文摘要:

State-of-the-art reinforcement learning algorithms predominantly learn a policy from either a numerical state vector or images. Both approaches generally do not take structural knowledge of the task into account, which is especially prevalent in robotic applications and can benefit learning if exploited. This work introduces a neural network architecture that combines relational inductive bias and visual feedback to learn an efficient position control policy for robotic manipulation. We derive a graph representation that models the physical structure of the manipulator and combines the robot's internal state with a low-dimensional description of the visual scene generated by an image encoding network. On this basis, a graph neural network trained with reinforcement learning predicts joint velocities to control the robot. We further introduce an asymmetric approach of training the image encoder separately from the policy using supervised learning. Experimental results demonstrate that, for a 2-DoF planar robot in a geometrically simplistic 2D environment, a learned representation of the visual scene can replace access to the explicit coordinates of the reaching target without compromising on the quality and sample efficiency of the policy. We further show the ability of the model to improve sample efficiency for a 6-DoF robot arm in a visually realistic 3D environment.

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。

↑