Policies trained on standard simulated RGB images often fail in the real world due to the "sim-to-real" gap.
This research, often referred to as , addresses the challenge of training robots (specifically quadrupedal "robot dogs") to perform parkour using only a single color camera. Parkour Simulator
Researchers from MIT and other institutions developed a method to generate realistic RGB observations from simulated depth images. Policies trained on standard simulated RGB images often
" Paper Simulator " is a separate Roblox experience where players compete to become "pro," though it is not primarily a parkour simulator. often referred to as
Sign In