SAPIEN: A SimulAted Part-based Interactive ENvironment

TL;DR

SAPIEN is a realistic, physics-rich simulated environment designed for household robotic tasks, supporting detailed part-level understanding and enabling advanced vision and interaction research.

Contribution

It introduces a large-scale, articulated object environment that advances simulation realism and supports diverse robotic vision and interaction tasks.

Findings

Effective part detection and motion attribute recognition by state-of-the-art algorithms

Successful robotic interaction tasks using heuristic and reinforcement learning methods

Potential to explore new research directions in robot cognition and environment understanding

Abstract

Building home assistant robots has long been a pursuit for vision and robotics researchers. To achieve this task, a simulated environment with physically realistic simulation, sufficient articulated objects, and transferability to the real robot is indispensable. Existing environments achieve these requirements for robotics simulation with different levels of simplification and focus. We take one step further in constructing an environment that supports household tasks for training robot learning algorithm. Our work, SAPIEN, is a realistic and physics-rich simulated environment that hosts a large-scale set for articulated objects. Our SAPIEN enables various robotic vision and interaction tasks that require detailed part-level understanding.We evaluate state-of-the-art vision algorithms for part detection and motion attribute recognition as well as demonstrate robotic interaction tasks using heuristic approaches and reinforcement learning algorithms. We hope that our SAPIEN can open a lot of research directions yet to be explored, including learning cognition through interaction, part motion discovery, and construction of robotics-ready simulated game environment.