Prompt Informed Reinforcement Learning for Visual Coverage Path Planning

TL;DR

This paper introduces PIRL, a novel reinforcement learning approach that integrates large language models to dynamically shape rewards for UAV visual coverage, improving efficiency and coverage in complex environments.

Contribution

The study presents PIRL, a new method combining LLMs with RL for adaptive reward shaping in UAV coverage tasks, enhancing generalization and physical realism.

Findings

PIRL achieves up to 14% higher coverage in OpenAI Gym.

PIRL achieves up to 27% higher coverage in Webots.

PIRL improves battery efficiency and reduces redundancy.

Abstract

Visual coverage path planning with unmanned aerial vehicles (UAVs) requires agents to strategically coordinate UAV motion and camera control to maximize coverage, minimize redundancy, and maintain battery efficiency. Traditional reinforcement learning (RL) methods rely on environment-specific reward formulations that lack semantic adaptability. This study proposes Prompt-Informed Reinforcement Learning (PIRL), a novel approach that integrates the zero-shot reasoning ability and in-context learning capability of large language models with curiosity-driven RL. PIRL leverages semantic feedback from an LLM, GPT-3.5, to dynamically shape the reward function of the Proximal Policy Optimization (PPO) RL policy guiding the agent in position and camera adjustments for optimal visual coverage. The PIRL agent is trained using OpenAI Gym and evaluated in various environments. Furthermore, the sim-to-real-like ability and zero-shot generalization of the agent are tested by operating the agent in Webots simulator which introduces realistic physical dynamics. Results show that PIRL outperforms multiple learning-based baselines such as PPO with static rewards, PPO with exploratory weight initialization, imitation learning, and an LLM-only controller. Across different environments, PIRL outperforms the best-performing baseline by achieving up to 14% higher visual coverage in OpenAI Gym and 27% higher in Webots, up to 25% higher battery efficiency, and up to 18\% lower redundancy, depending on the environment. The results highlight the effectiveness of LLM-guided reward shaping in complex spatial exploration tasks and suggest a promising direction for integrating natural language priors into RL for robotics.