analiza aiqbench
This study establishes a new baseline for autonomous two-wheeled racing by integrating Soft Actor-Critic with a self-paced curriculum that dynamically adjusts task difficulty without manual intervention. The approach successfully addresses the unique stability challenges of motorbikes, demonstrating superior training efficiency and lap times compared to standard methods in a high-fidelity physics simulator. This work marks a significant step forward in generalizing deep reinforcement learning techniques from four-wheeled vehicles to more complex, balance-sensitive platforms.
Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation
arXiv:2606.09236v1 Announce Type: new 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.
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.
Presented at the "1st Workshop on Generalization in Autonomous Driving: Paradigms, Practice, and Public Road Demonstrations" at ICRA 2026, Vienna. Oral+poster presentation
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2606.09236 [cs.RO]
(or arXiv:2606.09236v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.09236 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 210 cuvinte
Subiecte conexe
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
arXiv · 30 sept. 2026
Discovering autonomous quantum error correction via deep reinforcement learning
arXiv · 3 iun. 2026
Models Can't Remember Their Training. Neither Can You.
LessWrong · 19 iul. 2026
Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement Learning
arXiv · 5 oct. 2026