Project Overview
This project focuses on developing robust locomotion policies for a miniature humanoid robot using Deep Reinforcement Learning (PPO) in NVIDIA Isaac Sim. The goal is to bridge the sim-to-real gap, allowing the policy to handle uneven terrain and external perturbations on physical hardware.
The Team
[Team Photo Placeholder - To be added later]
Sim-to-Real Research Team
Our research focuses on:
- Domain Randomization: Training policies that are robust to variations in friction, mass, and sensor noise.
- Sim-to-Real Transfer: Deploying policies trained in Isaac Sim directly onto physical hardware.
- Robust Locomotion: Enabling the humanoid to walk on uneven terrain and recover from pushes.