Dynamic High-Order Control Barrier Functions with Diffuser for Safety-Critical Trajectory Planning at Signal-Free Intersections

2024-11-29

arXiv.org

AI Summary

In autonomous driving at uncontrolled intersections, simultaneous trajectory planning for multiple maneuvers (e.g., straight-through and turning) faces a fundamental trade-off between safety and efficiency. Method: This paper proposes a novel framework integrating Dynamic High-Order Control Barrier Functions (DHOCBFs) with a diffusion-based generative model (DSC-Diffuser). It introduces a task-guided multi-behavior learning mechanism and employs real-time adaptive safety constraint modulation to significantly reduce policy conservatism. Contribution/Results: Evaluated under complex, uncertain interactive scenarios, the system achieves 100% collision avoidance, reduces trajectory tracking error by 42%, and supports expert-demonstration-driven end-to-end safe planning. The framework demonstrates strong generalization capability and engineering practicality, enabling robust, efficient, and provably safe multi-maneuver planning in dynamic urban environments.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Planning safe and efficient trajectories through signal-free intersections presents significant challenges for autonomous vehicles (AVs), particularly in dynamic, multi-task environments with unpredictable interactions and an increased possibility of conflicts. This study aims to address these challenges by developing a unified, robust, adaptive framework to ensure safety and efficiency across three distinct intersection movements: left-turn, right-turn, and straight-ahead. Existing methods often struggle to reliably ensure safety and effectively learn multi-task behaviors from demonstrations in such environments. This study proposes a safety-critical planning method that integrates Dynamic High-Order Control Barrier Functions (DHOCBF) with a diffusion-based model, called Dynamic Safety-Critical Diffuser (DSC-Diffuser). The DSC-Diffuser leverages task-guided planning to enhance efficiency, allowing the simultaneous learning of multiple driving tasks from real-world expert demonstrations. Moreover, the incorporation of goal-oriented constraints significantly reduces displacement errors, ensuring precise trajectory execution. To further ensure driving safety in dynamic environments, the proposed DHOCBF framework dynamically adjusts to account for the movements of surrounding vehicles, offering enhanced adaptability and reduce the conservatism compared to traditional control barrier functions. Validity evaluations of DHOCBF, conducted through numerical simulations, demonstrate its robustness in adapting to variations in obstacle velocities, sizes, uncertainties, and locations, effectively maintaining driving safety across a wide range of complex and uncertain scenarios. Comprehensive performance evaluations demonstrate that DSC-Diffuser generates realistic, stable, and generalizable policies, providing flexibility and reliable safety assurance in complex multi-task driving scenarios.

Problem

• Ensures safety in dynamic signal-free intersections for AVs
• Integrates DHOCBF with diffusion model for multi-task learning
• Reduces displacement errors and adapts to surrounding vehicles

Innovation

• Dynamic High-Order Control Barrier Functions enhance safety
• Diffusion-based model learns multi-task behaviors efficiently
• Goal-oriented constraints reduce trajectory execution errors