← Back to Benchmarks
simmediumpolicy-learningmetric · varies

Flip Stunts on Bicycle Robots using Iterative Motion Imitation

Description

This work demonstrates a front-flip on bicycle robots via reinforcement learning, particularly by imitating reference motions that are infeasible and imperfect. To address this, we propose Iterative Motion Imitation(IMI), a method that iteratively imitates trajectories generated by prior policy rollouts. Starting from an initial reference that is kinematically or dynamically infeasible, IMI helps train policies that lead to feasible and agile behaviors. We demonstrate our method on Ultra-Mobilit

Source

http://arxiv.org/abs/2603.27944v1