SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
This addresses safety and admissibility issues in planning for various systems, offering a novel method for constraint satisfaction without retraining, though it is incremental as it builds on existing FM approaches.
The paper tackled the problem of flow matching (FM) lacking formal guarantees for state and action constraints and dynamic consistency in planning, resulting in SAD-Flower, a framework that uses a virtual control input to provide these guarantees without retraining, outperforming baselines in constraint satisfaction across tasks.
Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction is a fundamental and crucial requirement for the safety and admissibility of planned trajectories on various systems. Moreover, existing FM planners do not ensure the dynamical consistency, which potentially renders trajectories inexecutable. We address these shortcomings by proposing SAD-Flower, a novel framework for generating Safe, Admissible, and Dynamically consistent trajectories. Our approach relies on an augmentation of the flow with a virtual control input. Thereby, principled guidance can be derived using techniques from nonlinear control theory, providing formal guarantees for state constraints, action constraints, and dynamic consistency. Crucially, SAD-Flower operates without retraining, enabling test-time satisfaction of unseen constraints. Through extensive experiments across several tasks, we demonstrate that SAD-Flower outperforms various generative-model-based baselines in ensuring constraint satisfaction.