🤖 AI Summary
This paper addresses the joint path planning problem for unmanned ground vehicle (UGV)–unmanned aerial vehicle (UAV) cooperative systems, where the UGV acts as a mobile charging station to dynamically recharge energy-constrained UAVs under energy-path coupling constraints, aiming to minimize total mission time.
Method: We first formalize the dynamic ground-to-air charging process by modeling the energy-path coupling relationship. Then, we propose a two-stage energy-aware algorithm: (i) generating an initial tour via the Traveling Salesman Problem (TSP) formulation, and (ii) refining it using Monte Carlo Tree Search (MCTS) under strict energy constraints. The method jointly optimizes UGV mobility energy consumption and UAV endurance limitations while enabling multi-agent coordinated decision-making.
Results: Extensive simulations across multiple scales and real-world hardware experiments demonstrate that the algorithm is computationally efficient, robust, and achieves mission times close to the theoretical optimum—significantly outperforming conventional baseline approaches.
📝 Abstract
We investigate the problem of energy-constrained planning for a cooperative system of an Unmanned Ground Vehicles (UGV) and an Unmanned Aerial Vehicle (UAV). In scenarios where the UGV serves as a mobile base to ferry the UAV and as a charging station to recharge the UAV, we formulate a novel energy-constrained routing problem. To tackle this problem, we design an energy-aware routing algorithm, aiming to minimize the overall mission duration under the energy limitations of both vehicles. The algorithm first solves a Traveling Salesman Problem (TSP) to generate a guided tour. Then, it employs the Monte-Carlo Tree Search (MCTS) algorithm to refine the tour and generate paths for the two vehicles. We evaluate the performance of our algorithm through extensive simulations and a proof-of-concept experiment. The results show that our algorithm consistently achieves near-optimal mission time and maintains fast running time across a wide range of problem instances.