ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

Simulation has enabled unprecedented compute-scalable approaches to robot learning, However, many existing simulation frameworks typically support a narrow of scenes/tasks and luck features critical for scaling generalizable robotics and sim2real. We introduce and open-source ManiSkill3, the faster state-visual GPU parallelized robotics simulator with contact-rich physics targeting generalizable manipulation. Maniskill3 supports GPU parallelization of many aspects including simulation+rendering, heterogeneous simulation, pointclouds/voxels visual input, and more. Simulation with rendering on ManiSkills3 can run 10-1000x faster with 2-3x less GPU memory than other platforms, achieving up to 30,300+ FPS in benchmarked environments due to minimal python/pytorch overhead in the system, simulation on the GPU, and the use of the SAPIEN parallel rendering system.  Tasks that used to take hours to train can now take minutes. We further provide the most comprehensive range spanning 12 distinct domains including but not limited to mobile manipulation for tasks such as drawing, scenes designed by artists, or real-world digital twins. In addition, millions of demonstrations are frames are provided from motion planning, RL, and teleoperation. ManiSkill3 also provides a comprehensive set of baselines that span popular RL and learning-from-demonstrations algorithms.

Read More