Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions
This work addresses the computational bottleneck of real-time trajectory optimization for cooperative aerial-ground robot handover tasks.
The paper proposes a learning-augmented trajectory planning framework for UAV-UGV handover missions that uses LSTM-based neural surrogate to generate warm starts for a centralized optimizer, achieving over 3x speedup and 100% optimization success rate compared to cold start optimization.
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.