Series

Locomotion Zero To Hero

The "Locomotion Zero To Hero" series has 7 parts — read them in order from part 1.

locomotionroboticsPart 1

History and theory of robot movement control — ZMP, CPG, inverse kinematics before RL dominated.

2/5/202611 min read

locomotionrlai-perceptionPart 2

How RL is applied to locomotion — from reward design, observation space to training pipeline with Isaac Lab.

2/9/202610 min read

locomotionquadrupedrlPart 3

Hands-on train locomotion policy with legged_gym and deploy to 4-legged Unitree Go2 robot — from sim to real.

2/13/202610 min read

locomotionrlresearchPart 4

Analyzing Walk-These-Ways paper — train one single policy for multiple movement types with multiplicity of behavior.

2/17/20269 min read

locomotionrlparkourPart 5

Analyzing Extreme Parkour and SoloParkour — teaching robots to jump, climb stairs and overcome complex terrain with RL.

2/21/20269 min read

locomotionbipedalhumanoidPart 6

Challenges of bipedal robot control — balance, fall recovery, terrain adaptation from Cassie to Digit and humanoid.

2/25/202610 min read

locomotionsim2realrlPart 7

Transferring locomotion policy from simulation to real robot — domain randomization, actuator networks, and best practices.

3/1/202612 min read