A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing
cs.LG, cs.AI, cs.RO
Submitted: 2025-03-10
Updated: 2025-08-27
Comments: Accepted for publication at IROS 2025
Journal ref: 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9830-9837, 2025
DOI: 10.1109/IROS60139.2025.11247769
Code: https://github.com/CadenzaCoda/ConstraintAwareIL
License: http://creativecommons.org/licenses/by/4.0/
The gist: Guaranteeing constraint satisfaction is challenging in imitation learning (IL), particularly in tasks that require operating near a system's handling limits.
Terminology
Abstract
Guaranteeing constraint satisfaction is challenging in imitation learning (IL), particularly in tasks that require operating near a system's handling limits. Traditional IL methods, such as Behavior Cloning (BC), often struggle to enforce constraints, leading to suboptimal performance in high-precision tasks. In this paper, we present a simple approach to incorporating safety into the IL objective. Through simulations, we empirically validate our approach on an autonomous racing task with both full-state and image feedback, demonstrating improved constraint satisfaction and greater consistency in task performance compared to BC.
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks