Event
asRoBallet achieves dynamic balancing of spherical robots using friction-aware reinforcement learning
1 reports · 1 sources
asRoBallet proposes a dynamic balancing control method for spherical underactuated robots based on friction-aware reinforcement learning, starting from the underactuated dynamics and the two-layer contact friction of wheel-ball-ground, and derives the kinematic mapping and dynamic balancing mechanism of the spherical chassis. This method uses proximal policy optimization (PPO) to train position-holding and velocity-tracking policies, and uses friction domain randomization to improve the policy's adaptability under different friction conditions.
Report timeline
- asRoBallet: Dynamic Balance Control of Spherical Underactuated Robots via Friction-Aware Reinforcement Learning
asRoBallet achieves dynamic balance control of spherical underactuated robots through friction-aware reinforcement learning. Starting from underactuated dynamics and the two-layer contact friction among wheel, ball, and ground, it derives the kinematic mapping and dynamic balance mechanism of the spherical chassis. The method uses proximal policy optimization (PPO) to train position-holding and velocity-tracking policies, and applies friction domain randomization to improve policy adaptability under different friction conditions.
Guyuehome ·