MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench
This work addresses the problem of generating stable and realistic humanoid robot behaviors in simulation for robotics researchers, but it is incremental as it builds on existing methods with specific improvements.
The authors tackled the HumanoidBench benchmark for whole-body humanoid control using MuJoCo MPC, finding that sparse rewards led to unrealistic behaviors, and proposed regularization terms that achieved the highest scores while maintaining realistic posture and smooth control.
We tackle the recently introduced benchmark for whole-body humanoid control HumanoidBench using MuJoCo MPC. We find that sparse reward functions of HumanoidBench yield undesirable and unrealistic behaviors when optimized; therefore, we propose a set of regularization terms that stabilize the robot behavior across tasks. Current evaluations on a subset of tasks demonstrate that our proposed reward function allows achieving the highest HumanoidBench scores while maintaining realistic posture and smooth control signals. Our code is publicly available and will become a part of MuJoCo MPC, enabling rapid prototyping of robot behaviors.