2026-10-14T14:23:05Z https://www.scidb.cn/oai

10.57760/sciencedb.02239 2022-08-17T09:13:56Z

2022-08-17 ManiSkill-2022 doi:10.57760/sciencedb.02239 en ManiSkill2 is a large-scale robotic manipulation benchmark, focusing on learning generalizable robot agents and manipulation skills. It features 2000+ diverse objects, 20 task categories, and a large-scale demonstration set in SAPIEN(https://sapien.ucsd.edu/), a fully-physical, realistic simulator. The benchmark can be used to study 2D & 3D vision-based imitation learning, reinforcement learning, and motion planning, etc. We invite you to participate in the associated ManiSkill 2022 challenge(https://sapien.ucsd.edu/challenges/maniskill/2022/) where we will be awarding prizes to the teams who achieve the highest success rates in our environments.This dataset contains the demonstration datasets for ManiSkill2 (https://github.com/haosulab/ManiSkill2/). Robotics ; Computer Vision; Reinforcement Learning Jiayuan Gu Fanbo Xiang Xinyue Wei Xiqiang Liu Yihe Tang Xuanlin Li Hao Su PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank