CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous Vehicles

2025-03-03

AI Summary

To address safety and efficiency challenges in real-time obstacle avoidance for autonomous vehicles operating in highly dynamic, complex environments, this paper proposes an LLM-driven adaptive safety corridor planning method. The approach integrates a large language model (LLM) into an online model predictive control (MPC) framework—marking the first such incorporation—to dynamically generate Sigmoid-parameterized safety corridor boundaries via semantic understanding of environmental cues, thereby enabling end-to-end mapping from scene semantics to motion constraints. Constraint-aware optimal control is solved using differential dynamic programming (DDP), ensuring collision-free trajectories, real-time feasibility, and trajectory optimality while operating in a compressed state space. Simulation and real-world vehicle experiments demonstrate that the method significantly improves obstacle avoidance success rate (+23.6%) and reduces planning latency (−41.2%) compared to conventional MPC, achieving zero collisions in highly dynamic scenarios.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Safety and Robustness

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

In this paper, we present Corridor-Agent (CorrA), a framework that integrates large language models (LLMs) with model predictive control (MPC) to address the challenges of dynamic obstacle avoidance in autonomous vehicles. Our approach leverages LLM reasoning ability to generate appropriate parameters for sigmoid-based boundary functions that define safe corridors around obstacles, effectively reducing the state-space of the controlled vehicle. The proposed framework adjusts these boundaries dynamically based on real-time vehicle data that guarantees collision-free trajectories while also ensuring both computational efficiency and trajectory optimality. The problem is formulated as an optimal control problem and solved with differential dynamic programming (DDP) for constrained optimization, and the proposed approach is embedded within an MPC framework. Extensive simulation and real-world experiments demonstrate that the proposed framework achieves superior performance in maintaining safety and efficiency in complex, dynamic environments compared to a baseline MPC approach.

Problem

• Dynamic obstacle avoidance for autonomous vehicles
• Integration of LLMs with MPC for safe corridor generation
• Ensuring collision-free trajectories with computational efficiency

Innovation

• Integrates LLMs with MPC for obstacle avoidance
• Uses sigmoid-based boundary functions for safe corridors
• Employs DDP for constrained optimization in MPC