Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation
This work addresses robotic manipulation tasks for researchers and practitioners, presenting incremental improvements by combining existing techniques.
The paper tackled object manipulation in robotics by comparing learning-from-demonstrations and heuristic rule-based methods, achieving competitive performance in the SAPIEN ManiSkill Challenge 2021 with results like improved imitation learning via Transformer-based networks.
This paper presents an overview and comparative analysis of our systems designed for the following two tracks in SAPIEN ManiSkill Challenge 2021: No Interaction Track: The No Interaction track targets for learning policies from pre-collected demonstration trajectories. We investigate both imitation learning-based approach, i.e., imitating the observed behavior using classical supervised learning techniques, and offline reinforcement learning-based approaches, for this track. Moreover, the geometry and texture structures of objects and robotic arms are exploited via Transformer-based networks to facilitate imitation learning. No Restriction Track: In this track, we design a Heuristic Rule-based Method (HRM) to trigger high-quality object manipulation by decomposing the task into a series of sub-tasks. For each sub-task, the simple rule-based controlling strategies are adopted to predict actions that can be applied to robotic arms. To ease the implementations of our systems, all the source codes and pre-trained models are available at \url{https://github.com/caiqi/Silver-Bullet-3D/}.