Unverified50% confidenceFactExact time
Agility Robotics' bipedal robot Digit and Tesla's Optimus humanoid robot both made extensive use of simulation training to accelerate capability development between 2023 and 2024
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedAgility Robotics的Digit和宇树科技的H1的运动策略都经过数十亿步仿真训练后才部署到真实硬件76% similarUnverifiedA 2023 study by a Berkeley team demonstrated that bipedal robot policies trained through large-scale domain randomization can achieve zero-shot transfer to real hardware.71% similarUnverifiedETH Zurich's ANYmal quadruped robot team used the Sim2Real method to enable the robot to learn adaptive walking on rough terrain, with the policy trained entirely in simulation.69% similarUnverifiedETH Zurich's ANYmal quadruped robot and multiple studies from UC Berkeley have demonstrated that carefully designed simulation training strategies can be deployed to physical robots with almost zero adjustments.68% similarVerifiedIn 2019, OpenAI used domain randomization techniques to train a robotic hand to solve a Rubik's Cube, randomizing more than 100 physical parameters (including friction coefficients, object mass, and joint damping), and ultimately succeeded in transferring the policy to a physical robot.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/891797API
curl https://kongchang.com/api/v1/knowledge/claims/891797MCP
get_claim(id=891797)