Constraint-Aware Diffusion Guidance for Imitation Learning

We propose Constraint-Aware Diffusion Guidance (CoDiG), a constraint-aware imitation learning framework based on conditional diffusion models. Unlike conventional imitation learning methods, which often fail to generalize to unseen or constrained environments, CoDiG enforces safety and physical feasibility during inference via barrier function guidance. Our method learns from a limited number of expert demonstrations without reward supervision or environment interaction, and is capable of generating safe and feasible trajectories in real time. A warm-start strategy further accelerates sampling by reusing previous outputs. We evaluate CoDiG on a miniature autonomous racing platform in a challenging obstacle avoidance task, demonstrating robust generalization, near time-optimal performance, and 100% success rate in dynamic scenarios. Our results highlight the potential of constraint-aware diffusion models as a data-efficient and deployable solution for safe imitation learning in robotics.

Authors

• Hao Ma School of Artificial Intelligence, University of Chinese Academy of Science Institute of Automation, Chinese Academy of Sciences
• Sabrina Bodmer
• Andrea Carron
• Melanie Zeilinger
• Michael Muehlebach

Keywords

• Autonomous Racing
• constraint satisfaction
• Diffusion models
• Imitation Learning
• Safe Control