JPPD: Joint Prediction_Planning Diffusion with Differentiable Safety Guidance for Dynamic Obstacle Avoidance in Intelligent Transportation Systems

2026-06-14

AI Summary

This work addresses the challenge of safe and efficient navigation for low-speed autonomous platforms in shared traffic spaces populated by pedestrians and service robots. The authors propose a unified diffusion-based generative framework that jointly tackles multi-agent trajectory prediction and motion planning as a conditional joint trajectory generation task. By leveraging a causal Transformer to model spatiotemporal couplings among trajectories and integrating a differentiable safety potential field to guide the diffusion sampling process, the approach enables planning to reciprocally influence prediction. Furthermore, conditional flow matching is employed to reduce inference steps while preserving trajectory diversity. Experimental results demonstrate significant improvements in tail-end safety and operational efficiency across simulation, real-world pedestrian replay, Isaac Sim, and embedded deployment on ROS/Orin platforms, effectively reducing near-collisions, blocking time, induced deviations, and abrupt braking events.

Abstract

Shared-space transportation operation requires low-speed autonomous platforms to navigate safely and efficiently among pedestrians, service robots, micromobility users, carts, and other road users. Most existing systems decompose this problem into trajectory prediction followed by motion planning, which creates one-way information flow: predicted participant futures influence the robot plan, but the selected robot plan cannot influence the predicted multi-agent evolution. This paper presents a joint prediction-planning diffusion framework that treats participant prediction and robot planning as a single conditional trajectory generation problem, where the model samples the future robot trajectory and all participant trajectories from one coupled distribution using a causal Transformer with cross-trajectory attention. To replace heuristic repulsive post-processing, the framework introduces differentiable safety potential guidance, a time-varying occupancy-probability potential whose gradient directly guides the joint sampler, and conditional flow matching is used to reduce inference steps while preserving multimodal trajectory diversity. The evaluation emphasizes shared-space operational effects, including near misses, blockage time, induced participant deviation, hard-braking events, and embedded latency, rather than treating average displacement error and final displacement error as the main result. Experiments in scenario-grounded simulation, naturalistic pedestrian replay, Isaac Sim validation, and ROS/Orin deployment show that joint sampling improves tail safety and runtime efficiency over a separated prediction-then-planning baseline.

Problem

• shared-space navigation
• trajectory prediction
• motion planning
• dynamic obstacle avoidance
• multi-agent interaction

Innovation

• joint prediction-planning
• diffusion model
• differentiable safety guidance
• conditional flow matching
• shared-space navigation