Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion

Vineet Punyamoorty, Pascal Jutras-Dubé, Ruqi Zhang, Vaneet Aggarwal, Damon Conover, Aniket Bera

Abstract: By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories in deterministic environments, they face challenges in dynamic settings with moving obstacles. Effective collision avoidance demands continuous monitoring and adaptive decision-making. While re-planning at every time step could ensure safety, it introduces substantial computational overhead due to the repetitive prediction of overlapping state sequences—a process that is particularly costly with diffusion models, known for their intensive iterative sampling procedure. We propose an adaptive generative planning approach that dynamically adjusts re-planning frequency based on the uncertainty of action predictions. Our method minimizes the need for frequent, computationally expensive, and redundant re-planning while maintaining robust collision avoidance performance. In experiments, we obtain a 13.5% increase in the mean trajectory length and 12.7% increase in mean reward over long-horizon planning, indicating a reduction in collision rates, and improved ability to navigate the environment safely.

External IDs:dblp:conf/iros/PunyamoortyJZACB25