论文标题
学习神经运动计划的障碍物表示
Learning Obstacle Representations for Neural Motion Planning
论文作者
论文摘要
运动计划和避免障碍是机器人应用中的关键挑战。尽管以前的工作成功地为已知环境提供了出色的解决方案，但在新的和动态的环境中基于传感器的运动计划仍然很困难。在这项工作中，我们从学习的角度解决了基于传感器的运动计划。在视觉识别的最新进展中，我们认为学习适当表示运动计划的重要性。我们根据点网架构提出了一个新的障碍物表示，并通过避免障碍的政策共同训练它。我们通过实验性地评估了在充满挑战的环境下进行僵化的身体运动计划的方法，并在准确性和效率方面表现出了艺术状态的显着改善。
Motion planning and obstacle avoidance is a key challenge in robotics applications. While previous work succeeds to provide excellent solutions for known environments, sensor-based motion planning in new and dynamic environments remains difficult. In this work we address sensor-based motion planning from a learning perspective. Motivated by recent advances in visual recognition, we argue the importance of learning appropriate representations for motion planning. We propose a new obstacle representation based on the PointNet architecture and train it jointly with policies for obstacle avoidance. We experimentally evaluate our approach for rigid body motion planning in challenging environments and demonstrate significant improvements of the state of the art in terms of accuracy and efficiency.
