2021/11/11 by I-Chun Arthur Liu, Shagun Uppal, Liu, I-Chun Arthur +10 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Artificial intelligence #Code (set theory) #Computer science #Computer vision #FOS: Computer and information sciences #Human–computer interaction #Machine Learning (cs.LG) #Machine learning #Motion (physics) #Multimodal Machine Learning Applications #Planner #Reinforcement Learning in Robotics #Reinforcement learning #Robot #Robotic Path Planning Algorithms #Robotics (cs.RO) #cs.AI #cs.LG #cs.RO
paper · pdf · doi:10.48550/arxiv.2111.06383
published in arXiv (Cornell University) (Cornell University) · Published at the Conference on Robot Learning (CoRL) 2021
arxiv created 2021/11/11 · openalex publication_date 2021/11/11 · arxiv updated 2021/11/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations. Prior work tackles the exploration problem by integrating motion planning and reinforcement learning. However, the motion planner augmented policy requires access to state information, which is often not available in the real-world settings. To this end, we propose to distill a state-based motion planner augmented policy to a visual control policy via (1) visual behavioral cloning to remove the motion planner dependency along with its jittery motion, and (2) vision-based reinforcement learning with the guidance of the smoothed trajectories from the behavioral cloning agent. We evaluate our method on three manipulation tasks in obstructed environments and compare it against various reinforcement learning and imitation learning baselines. The results demonstrate that our framework is highly sample-efficient and outperforms the state-of-the-art algorithms. Moreover, coupled with domain randomization, our policy is capable of zero-shot transfer to unseen environment settings with distractors. Code and videos are available at https://clvrai.com/mopa-pd