Search papers, labs, and topics across Lattice.
This paper introduces a modular reinforcement learning framework for controlling bipedal soccer robots, separating gait generation from complex actions using an open-loop oscillator and RL-based feedback. A posture-driven state machine switches between ball-seeking/kicking and fall recovery networks to prevent state interference. The fall recovery network is trained using a progressive force attenuation curriculum, enabling rapid autonomous recovery in simulations.
Bipedal soccer robots can now autonomously recover from falls in under a second thanks to a novel RL framework.
Developing bipedal football robots in dynamiccombat environments presents challenges related to motionstability and deep coupling of multiple tasks, as well ascontrol switching issues between different states such as up-right walking and fall recovery. To address these problems,this paper proposes a modular reinforcement learning (RL)framework for achieving adaptive multi-task control. Firstly,this framework combines an open-loop feedforward oscilla-tor with a reinforcement learning-based feedback residualstrategy, effectively separating the generation of basic gaitsfrom complex football actions. Secondly, a posture-driven statemachine is introduced, clearly switching between the ballseeking and kicking network (BSKN) and the fall recoverynetwork (FRN), fundamentally preventing state interference.The FRN is efficiently trained through a progressive forceattenuation curriculum learning strategy. The architecture wasverified in Unity simulations of bipedal robots, demonstratingexcellent spatial adaptability-reliably finding and kicking theball even in restricted corner scenarios-and rapid autonomousfall recovery (with an average recovery time of 0.715 seconds).This ensures seamless and stable operation in complex multi-task environments.
