Abstract

Generative planners based on diffusion/flow matching can learn to synthesize long-horizon trajectories from demonstrations. However, real-world deployment requires (i) enforcing safety constraints during execution and (ii) tight online replanning at fast execution rates. Prior safe diffusion/flow planners generate the agent's full trajectory at once, while repeatedly perturbing intermediate states to satisfy safety constraints. This approach is not only computationally intensive, but also introduces distribution shift since the learned sampling dynamics is distinct from the system's execution dynamics. We propose SafeStreamingFlow, a goal-conditioned planner that aligns flow sampling dynamics with execution dynamics by sequentially integrating a learned state vector field with hierarchical state prediction. Importantly, we need to enforce safety constraints only for the executed step via high order control barrier functions. Across navigation, racing, and locomotion benchmarks, SafeStreamingFlow reduces planning latency and improves safety compared to existing methods, while maintaining competitive goal-reaching success.

Keywords

Subject

Publication details

Journal
Not available
Open access
Green open access

Cite this article

APA 7

Jang, S., Yang, J., Ancha, S., & Han, S. (2026). Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics. https://omanscience.com/en/articles/safe-streaming-flow-planning-by-aligning-sampling-dynamics-with-execution-dynamics

MLA 9

Jang, Seunghwan, et al. "Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics." https://omanscience.com/en/articles/safe-streaming-flow-planning-by-aligning-sampling-dynamics-with-execution-dynamics.

Chicago (author–date)

Jang, Seunghwan, Jeongyong Yang, Siddharth Ancha, and SooJean Han. 2026. "Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics." https://omanscience.com/en/articles/safe-streaming-flow-planning-by-aligning-sampling-dynamics-with-execution-dynamics.

Harvard

Jang, S., Yang, J., Ancha, S. and Han, S. (2026) 'Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics', Available at: https://omanscience.com/en/articles/safe-streaming-flow-planning-by-aligning-sampling-dynamics-with-execution-dynamics.

Vancouver

Jang S, Yang J, Ancha S, Han S. Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics. https://omanscience.com/en/articles/safe-streaming-flow-planning-by-aligning-sampling-dynamics-with-execution-dynamics

IEEE

S. Jang, J. Yang, S. Ancha, and S. Han, "Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics," https://omanscience.com/en/articles/safe-streaming-flow-planning-by-aligning-sampling-dynamics-with-execution-dynamics.