Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion
This addresses the problem of computational inefficiency in collision avoidance for robotics or autonomous systems, representing an incremental improvement over existing methods.
The paper tackles the challenge of using diffusion models for planning in dynamic environments with moving obstacles, proposing an adaptive generative planning approach that adjusts replanning frequency based on action prediction uncertainty, resulting in a 13.5% increase in mean trajectory length and a 12.7% increase in mean reward.
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 replanning at every timestep 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 replanning frequency based on the uncertainty of action predictions. Our method minimizes the need for frequent, computationally expensive, and redundant replanning while maintaining robust collision avoidance performance. In experiments, we obtain a 13.5% increase in the mean trajectory length and a 12.7% increase in mean reward over long-horizon planning, indicating a reduction in collision rates and an improved ability to navigate the environment safely.