no code implementations • 13 Sep 2022 • Kun Wang, William R. Johnson III, Shiyang Lu, Xiaonan Huang, Joran Booth, Rebecca Kramer-Bottiglio, Mridul Aanjaneya, Kostas Bekris
This strategy is based on a differentiable physics engine that can be trained given limited data from a real robot.
no code implementations • 28 Feb 2022 • Kun Wang, Mridul Aanjaneya, Kostas Bekris
A model of NASA's icosahedron SUPERballBot on MuJoCo is used as the ground truth system to collect training data.
no code implementations • 10 Nov 2020 • Kun Wang, Mridul Aanjaneya, Kostas Bekris
The results indicate that only 0. 25\% of ground truth data are needed to train a policy that works on the ground truth system when the differentiable engine is used for training against training the policy directly on the ground truth system.
no code implementations • 9 Nov 2020 • Kun Wang, Mridul Aanjaneya, Kostas Bekris
We propose a novel differentiable physics engine for system identification of complex spring-rod assemblies.
no code implementations • L4DC 2020 • Kun Wang, Mridul Aanjaneya, Kostas Bekris
We propose a novel differentiable physics engine for system identification of complex spring-rod assemblies.