Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization

Authors:
  • TLThomas Lew
    Thomas Lew
  • SSSumeet Singh
    Sumeet Singh
  • MPMario Prats
    Mario Prats
  • JBJeffrey Bingham
    Jeffrey Bingham
  • JWJonathan Weisz
    Jonathan Weisz
  • BHBenjie Holson
    Benjie Holson
  • XZXiaohan Zhang
    Xiaohan Zhang
  • VSVikas Sindhwani
    Vikas Sindhwani
  • YLYao Lu
    Yao Lu
  • FXFei Xia
    Fei Xia
  • PXPeng Xu
    Peng Xu
  • TZTingnan Zhang
    Tingnan Zhang

Abstract
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
All Related Versions