Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds
2026-07-20 • Robotics
Robotics
AI summaryⓘ
The authors developed a way for robot legs to move smoothly using a computer learning method called reinforcement learning. They trained their robot in a special computer simulation by using Nvidia's Isaac Sim and Isaac Lab tools. When they tested their trained robot on a real Unitree Go1 robot, it performed well without needing extra adjustments, keeping up with speeds and recovering from falls better than the robot's usual controller. This shows their method can teach robots to walk in the real world right after training in simulation. Their work helps bridge the gap between virtual practice and real robot movement.
reinforcement learninglocomotionsim-to-real gapIsaac SimIsaac LabUnitree Go1robotics simulationvelocity trackingwhole-body controlquadruped robots
Authors
Jordan Dowdy, Jean Chagas Vaz
Abstract
Learning-based approaches to locomotion have risen in popularity in recent years, showing the capability for complex legged locomotion and whole-body control. Reinforcement learning (RL), the primary learning-based approach for locomotion, often utilizes a high-performance simulation tool, providing a controlled and efficient training and development environment. However, policies that perform well in simulation frequently encounter unexpected challenges when deployed on a physical system, known as the sim-to-real gap. This work presents a robust RL locomotion framework capable of whole-body control. The proposed RL framework utilizes Nvidia's new set of simulation tools, Isaac Sim, and its companion RL framework, Isaac Lab, for training, achieving a zero-shot sim-to-real policy. The performance of our policy is validated on physical hardware using the Unitree Go1, with experimental results showing similar velocity tracking performance to the quadruped's integrated controller, with a greater ability to recover from large disturbances, and achieve linear velocities of 2.0 m/s and angular velocities of 1.8 rad/s.