Motion Dynamic RRT based Fluid Field - PPO for Dynamic TF/TA Routing Planning

2024-06-02

2024 IEEE Intelligent Vehicles Symposium (IV)

AI Summary

Real-time, long-range, and dynamically constrained terrain-following/terrain-avoidance (TF/TA) path planning for medium-to-large fixed-wing UAVs in complex topography remains challenging due to stringent aerodynamic, kinematic, and obstacle-avoidance requirements—especially without global terrain priors. Method: This paper proposes MD-RRT, a fluid-field modeling approach that uniquely integrates perturbed flow fields with artificial potential fields to reconstruct the state-action space of Proximal Policy Optimization (PPO), enabling end-to-end, dynamically feasible planning without global prior knowledge. The method unifies an improved RRT-based sampling strategy, high-fidelity fixed-wing aircraft dynamics modeling, and the PPO reinforcement learning framework. Results: Validated on real-world digital elevation model (DEM) data, the system generates kilometer-scale, collision-free trajectories in real time while satisfying aerodynamic, kinematic, and obstacle-avoidance constraints. It robustly accomplishes TF/TA missions under severe terrain undulation and dynamic obstacles, significantly overcoming the fundamental trade-off among real-time performance, planning horizon, and constraint compliance inherent in existing approaches.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Intelligent Robots: Motion and Path Planning
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Existing local dynamic route planning algorithms, when directly applied to terrain following/terrain avoidance, or dynamic obstacle avoidance for large and medium-sized fixed-wing aircraft, fail to simultaneously meet the requirements of real-time performance, long-distance planning, and the dynamic constraints of large and medium-sized aircraft. To deal with this issue, this paper proposes the Motion Dynamic RRT based Fluid Field - PPO for dynamic TF/TA routing planning. Firstly, the action and state spaces of the proximal policy gradient algorithm are redesigned using disturbance flow fields and artificial potential field algorithms, establishing an aircraft dynamics model, and designing a state transition process based on this model. Additionally, a reward function is designed to encourage strategies for obstacle avoidance, terrain following, terrain avoidance, and safe flight. Experimental results on real DEM data demonstrate that our algorithm can complete long-distance flight tasks through collision-free trajectory planning that complies with dynamic constraints, without the need for prior global planning.

Problem

• Flight Path Planning
• Obstacle Avoidance
• Real-time Adaptation

Innovation

• Dynamic RRT
• PPO Algorithm
• Complex Terrain Path Planning