Resources
DART
DART is a collaborative, cross-platform, open source library which provides data structures and algorithms for kinematic and dynamic applications in robotics and computer animation. DART is distinguished by its accuracy and stability due to its use of generalized coordinates to represent articulated rigid body systems and Featherstone’s Articulated Body Algorithm to compute the dynamics of motion.
NimblePhysics
A fast and feature-complete differentiable physics engine for articulated rigid body simulation. NimblePhysics computes analytical gradients through the LCP formulation of inelastic contact by exploiting the sparsity of the LCP solution. NimblePhysics supports complex contact geometry and approximating continuous-time elastic collision.
AddBiomechanics
AddBiomechanics is a set of cloud-based tools that process motion capture data efficiently, accurately and automatically. It simultaneously optimizes over skeleton scaling, joint angles, joint torques and contact forces to autonomously produce high-quality human motions in minutes on a standard consumer laptop. Users can upload their data to be automatically processed for free in the cloud. The shared data will then be automatically aggregated into a single large dataset ready for machine learning applications.
CIRCLE: Capture In Rich Contextual Environments
We present CIRCLE, a dataset containing 10 hours of full-body reach- ing motion from 5 subjects across nine scenes, paired with ego-centric information of the environment represented in various forms, such as RGBD videos. We use this dataset to train a model that generates human motion conditioned on scene information. Leveraging our dataset, the model learns to use ego-centric scene information to achieve non- trivial reaching tasks in the context of complex 3D scenes.
Assistive Gym
Assistive Gym is a physics-based simulation framework for physical human-robot interaction and robotic assistance. Assistive Gym is integrated into the OpenAI Gym interface, enabling the use of existing reinforcement learning and control algorithms to teach robots how to interact with people. This is a collaborated project with Georgia Tech Healthcare Robotics Lab.