论文标题
机器人桌通过加固学习和全身轨迹优化擦拭
Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization
论文作者
论文摘要
我们提出了一个框架，以使多功能辅助移动机器人自主擦拭桌子以清洁溢出物和面包屑。这个问题具有挑战性，因为它需要计划擦拭动作，同时通过高维视觉观察来推理不确定的碎屑和溢出物的潜在动态。同时，我们必须保证限制满意度以在非结构化的杂乱环境中实现安全部署。为了解决这个问题，我们首先提出了一个随机微分方程，以模拟碎屑和溢出动力学以及用机器人刮水器吸收。使用此模型，我们培训了基于远见的政策，用于使用强化学习（RL）进行模拟中的擦拭操作。为了启用零射击SIM到运行的部署，我们将RL策略与全身轨迹优化框架相吻合，以计算基础和ARM联合轨迹，以执行所需的擦拭动作，同时保证约束满意度。我们广泛地验证了模拟和硬件的方法。视频：https：//youtu.be/inorkp4f3ei
We propose a framework to enable multipurpose assistive mobile robots to autonomously wipe tables to clean spills and crumbs. This problem is challenging, as it requires planning wiping actions while reasoning over uncertain latent dynamics of crumbs and spills captured via high-dimensional visual observations. Simultaneously, we must guarantee constraints satisfaction to enable safe deployment in unstructured cluttered environments. To tackle this problem, we first propose a stochastic differential equation to model crumbs and spill dynamics and absorption with a robot wiper. Using this model, we train a vision-based policy for planning wiping actions in simulation using reinforcement learning (RL). To enable zero-shot sim-to-real deployment, we dovetail the RL policy with a whole-body trajectory optimization framework to compute base and arm joint trajectories that execute the desired wiping motions while guaranteeing constraints satisfaction. We extensively validate our approach in simulation and on hardware. Video: https://youtu.be/inORKP4F3EI
