Chat-Driven Reconfiguration of Model Predictive Control

TL;DR

ChatMPC introduces a natural language interface for model predictive control, enabling non-expert users to personalize and adapt control systems interactively, with proven convergence guarantees and real-time validation in robotics tasks.

Contribution

The paper presents ChatMPC, a novel framework that allows natural language-based personalization and environmental adaptation in model predictive control, with theoretical convergence analysis and practical validation.

Findings

Achieves exponential convergence with consistent feedback.

Demonstrates finite-time convergence for tolerance-based users.

Validates real-time performance in robot navigation and semi-autonomous driving.

Abstract

Traditional control personalization requires users to understand optimization parameters and provide repetitive numerical feedback, creating significant barriers for non-expert users. To deal with this issue, we propose ChatMPC, a model predictive control framework that enables users to personalize control systems and adapt to environmental changes through natural language interaction. The framework operates in two modes: personalization, where users iteratively adjust control behavior to their preferences, and co-development, where users provide real-time environmental information that complements sensor data. We establish convergence guarantees under different user behavior models, demonstrating exponential convergence for consistent feedback and finite-time convergence with logarithmic interaction complexity for tolerance-based users. We validate ChatMPC through experiments in robot navigation with personalized obstacle avoidance and semi-autonomous driving with conversational obstacle reporting. Both experiments achieve real-time performance and demonstrate effective adaptation to user preferences and environmental changes.