CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations

CASSI - Cooperative Adversarial Self-supervised Skill Imitation

Controlling the Solo12 Quadruped Robot with Deep Reinforcement Learning

SOLOBACKFLIP - Generating a full backflip

SOLOLEAP - Moving forward with a jumping motion

SOLOWAVE - Producing wave-like locomotion behavior

Improved Control Scheme for the Solo Quadruped and Experimental Comparison of MPCs

Real time contact planning and control of the Solo robot in 3d environments

BiConMP: A Nonlinear Model Predictive Control Framework for Whole Body Motion Planning

Solo12 outdoor experiment at LAAS, Autonomy Update

First cordless test of Solo12, WiFi + Battery update

Solo8 v2 bounding based on Reinforcement Learning

Solo8 v2 jumping based on Reinforcement Learning

Solo12 Reactive Stepping in New York / NYU

Hybrid Collision Model for Safety Collision Avoidance

Learning a Centroidal Motion Planner for Legged Locomotion

Reactive Walking Controller for Solo-12

Learning to jump high!

A set of new tests on Bolt.

First successful tests on our new biped robot "Bolt"

Executing high jumps for testing the impact resistance of the Solo8 hardware

Optimal contact locations for 92 cm vertical jump

Learning variable impedance control

Reactive walking controller in simulation (Centroidal MPC + TSID + PD+)

Jump with damped landing!

Introduction Video - Open Dynamic Robot Initiative

20200219 Solo8 and Solo12 quadruped

20200127 Solo8 Box Climb Jump