Spatial Envelope MPC: High Performance Driving without a Reference

2025-09-22

AI Summary

To address the safety and real-time performance limitations of conventional model predictive control (MPC) approaches in high-performance autonomous driving—particularly under extreme operating conditions where reliance on predefined reference trajectories degrades robustness and responsiveness—this paper proposes a reference-free envelope-based MPC framework. The method integrates an optimization-oriented, computationally efficient vehicle dynamics model with a continuously differentiable envelope representation of the drivable region, enabling joint trajectory planning and control synthesis. Leveraging synergistic reinforcement learning and numerical optimization, the framework ensures dynamic feasibility, safety robustness, and real-time execution. Compared to traditional tracking-based MPC, it overcomes fundamental performance bottlenecks and is validated in simulation and on physical vehicles across demanding scenarios—including race-track driving, emergency obstacle avoidance, and off-road navigation—demonstrating substantial improvements in decision latency, boundary safety, and task generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

This paper presents a novel envelope based model predictive control (MPC) framework designed to enable autonomous vehicles to handle high performance driving across a wide range of scenarios without a predefined reference. In high performance autonomous driving, safe operation at the vehicle's dynamic limits requires a real time planning and control framework capable of accounting for key vehicle dynamics and environmental constraints when following a predefined reference trajectory is suboptimal or even infeasible. State of the art planning and control frameworks, however, are predominantly reference based, which limits their performance in such situations. To address this gap, this work first introduces a computationally efficient vehicle dynamics model tailored for optimization based control and a continuously differentiable mathematical formulation that accurately captures the entire drivable envelope. This novel model and formulation allow for the direct integration of dynamic feasibility and safety constraints into a unified planning and control framework, thereby removing the necessity for predefined references. The challenge of envelope planning, which refers to maximally approximating the safe drivable area, is tackled by combining reinforcement learning with optimization techniques. The framework is validated through both simulations and real world experiments, demonstrating its high performance across a variety of tasks, including racing, emergency collision avoidance and off road navigation. These results highlight the framework's scalability and broad applicability across a diverse set of scenarios.

Problem

• Enabling autonomous vehicles to handle high performance driving without predefined references
• Addressing limitations of reference-based control frameworks at vehicle dynamic limits
• Integrating dynamic feasibility and safety constraints into unified planning framework

Innovation

• Envelope MPC without predefined reference trajectory
• Combining reinforcement learning with optimization techniques
• Unified planning and control framework with dynamic constraints