Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions

2026-05-19

AI Summary

This work addresses the high computational cost and limited real-time performance of centralized trajectory optimization in cooperative handover tasks between unmanned aerial vehicles and unmanned ground vehicles. To overcome these challenges, the authors propose a learning-augmented planning framework that leverages a decoupled encoder–decoder LSTM network to generate dynamically feasible, high-quality initial trajectories. These trajectories serve as intelligent warm starts for a centralized optimizer, significantly accelerating convergence. The approach achieves over threefold speedup in planning while maintaining a 100% success rate, thereby enabling efficient and reliable trajectory generation for heterogeneous multi-robot systems.

Abstract

This paper presents a learning-augmented trajectory planning framework for cooperative unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV) handover missions. While centralized trajectory optimization ensures dynamic feasibility and task optimality, its high computational cost limits real-time applicability. We propose a neural surrogate planner utilizing decoupled encoder-decoder long short-term memory (LSTM) networks to generate coordinated handover trajectory predictions from the task specifications. These predictions serve as informed warm starts for the downstream centralized optimizer, thereby accelerating convergence to dynamically feasible solutions. Benchmark evaluations demonstrate that the learning-augmented planning framework achieves more than a threefold speedup and 100% optimization success rate compared to cold start optimization. The results indicate that combining data-driven inference with model-based refinement enables fast and reliable trajectory generation for heterogeneous multi-robot systems.

Problem

• trajectory planning
• cooperative aerial-ground handover
• computational cost
• real-time applicability
• multi-robot systems

Innovation

• learning-augmented planning
• neural surrogate planner
• cooperative UAV-UGV handover
• warm-start optimization
• LSTM trajectory prediction