Constraining Streaming Flow Models for Adapting Learned Robot Trajectory Distributions

2026-02-17

AI Summary

This work addresses the challenge that existing streaming trajectory generation methods struggle to satisfy safety and task constraints—such as joint limits and obstacle avoidance—in real time during deployment. The authors propose the Constraint-Aware Streaming Flow (CASF) framework, which, for the first time, embeds constraints directly into the execution of streaming flow policies. By constructing a local Riemannian metric via differentiable distance functions and dynamically reshaping the velocity field through metric pullback, CASF enables projection-free, smooth, and safe real-time trajectory adaptation. The method preserves multimodality and reactivity while ensuring dynamic consistency. Experiments demonstrate that CASF outperforms conventional post-hoc projection approaches in both simulation and real-world tasks, achieving superior performance in constraint satisfaction, trajectory smoothness, and feasibility.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Satisfaction
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Security and Privacy: Large-scale security measurements

Abstract

Robot motion distributions often exhibit multi-modality and require flexible generative models for accurate representation. Streaming Flow Policies (SFPs) have recently emerged as a powerful paradigm for generating robot trajectories by integrating learned velocity fields directly in action space, enabling smooth and reactive control. However, existing formulations lack mechanisms for adapting trajectories post-training to enforce safety and task-specific constraints. We propose Constraint-Aware Streaming Flow (CASF), a framework that augments streaming flow policies with constraint-dependent metrics that reshape the learned velocity field during execution. CASF models each constraint, defined in either the robot's workspace or configuration space, as a differentiable distance function that is converted into a local metric and pulled back into the robot's control space. Far from restricted regions, the resulting metric reduces to the identity; near constraint boundaries, it smoothly attenuates or redirects motion, effectively deforming the underlying flow to maintain safety. This allows trajectories to be adapted in real time, ensuring that robot actions respect joint limits, avoid collisions, and remain within feasible workspaces, while preserving the multi-modal and reactive properties of streaming flow policies. We demonstrate CASF in simulated and real-world manipulation tasks, showing that it produces constraint-satisfying trajectories that remain smooth, feasible, and dynamically consistent, outperforming standard post-hoc projection baselines.

Problem

• robot trajectory adaptation
• safety constraints
• streaming flow policies
• constraint enforcement
• real-time trajectory adjustment

Innovation

• Streaming Flow Policies
• Constraint-Aware Control
• Differentiable Distance Functions
• Real-time Trajectory Adaptation
• Metric Reshaping