AI Insight
Researchers developed a framework for training autonomous superbike racing agents using deep reinforcement learning combined with self-paced curriculum learning in a physics-accurate simulator. The system uses Soft Actor-Critic algorithms with dynamically generated progressively challenging tasks, incorporating proprioceptive features, lean-angle history, and track information to control the motorbike. Results show that the self-paced curriculum approach outperforms standard reinforcement learning in training efficiency, lap times, and driving stability across multiple tracks and bike models.
Why it matters
This work establishes the first baseline for autonomous motorbike racing using reinforcement learning, addressing the substantially more complex challenge of two-wheeled vehicle control compared to existing four-wheeled autonomous racing systems. The self-paced curriculum learning approach could potentially be applied to real-world motorcycle safety systems and autonomous two-wheeled vehicle development.
Understand the Science
Abstract: Autonomous Racing has seen remarkable progress through deep Reinforcement Learning (RL), primarily for four-wheeled vehicles. However, motorbikes introduce substantially greater complexity due to the need to manage balance and lean angle, in addition to more reactive steering and throttle control, and a smaller weight. In this work, we present a framework for training an autonomous agent to race a superbike in VRider SBK, a physics-accurate Unity-based motorbike simulator. Our approach integrates Soft Actor-Critic (SAC) with Self-Paced curriculum Deep reinforcement Learning (SPDL), which dynamically generates progressively more challenging tasks based on the agent’s performance, without requiring manual curriculum design. The agent’s state space comprises proprioceptive features extended with lean-angle history, along with global track features via course points. The reward signal is shaped to encourage progress along the track while penalizing instability-inducing behaviors specific to two-wheeled dynamics. Preliminary experimental results demonstrate that SPDL outperforms SAC alone in training efficiency, lap time, and driving stability across multiple tracks and motorbike models, establishing a first baseline for RL-based autonomous motorbike racing.
Source: Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation