-
University of Michigan
Stars
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
[RA-L 2023 Best Paper] Official Code Release for LONER: LiDAR Only Neural Representations for Real-Time SLAM
Write planning task as Python classes, then translate to PDDL. Type checking included.
A PLEN2 Robot learns to walk using Twin-Delayed Deep Deterministic Policy Gradient in Gazebo and PyBullet with a custom OpenAI Gym interface
A Swift library for connecting to ROS using ROSBridge and Websockets