End-to-End Predictive Planner for Autonomous Driving with Consistency Models

2025-02-12

AI Summary

Traditional autonomous driving pipelines decouple prediction and planning, resulting in weak multi-agent interaction capability and low computational efficiency. This paper proposes the first end-to-end consistent modeling framework tailored for multi-agent coordination, jointly representing high-dimensional, multimodal trajectories of both ego and surrounding agents to enable real-time interactive decision-making (e.g., proactive yielding, cooperative lane-changing). We innovatively introduce an online multi-objective guided sampling mechanism that balances hard constraint satisfaction with behavioral interpretability, and adopt alternating-direction guidance combined with data-driven joint training. On the Waymo Open Motion (WOMD) benchmark, our method outperforms state-of-the-art approaches by improving trajectory diversity by 12.7%, increasing constraint satisfaction rate by 9.3%, significantly enhancing interaction plausibility, and reducing sampling steps by 60%—thereby meeting real-time inference requirements.

Technology Category

• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Trajectory prediction and planning are fundamental components for autonomous vehicles to navigate safely and efficiently in dynamic environments. Traditionally, these components have often been treated as separate modules, limiting the ability to perform interactive planning and leading to computational inefficiency in multi-agent scenarios. In this paper, we present a novel unified and data-driven framework that integrates prediction and planning with a single consistency model. Trained on real-world human driving datasets, our consistency model generates samples from high-dimensional, multimodal joint trajectory distributions of the ego and multiple surrounding agents, enabling end-to-end predictive planning. It effectively produces interactive behaviors, such as proactive nudging and yielding to ensure both safe and efficient interactions with other road users. To incorporate additional planning constraints on the ego vehicle, we propose an alternating direction method for multi-objective guidance in online guided sampling. Compared to diffusion models, our consistency model achieves better performance with fewer sampling steps, making it more suitable for real-time deployment. Experimental results on Waymo Open Motion Dataset (WOMD) demonstrate our method's superiority in trajectory quality, constraint satisfaction, and interactive behavior compared to various existing approaches.

Problem

• Unified prediction and planning framework
• Interactive multi-agent trajectory generation
• Real-time deployment efficiency improvement

Innovation

• End-to-end predictive planning framework
• Consistency model for trajectory generation
• Multi-objective guidance with online sampling