Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training
Not on the map. Why?
Abstract (arXiv)
This paper presents a hierarchical decision-making framework for unmanned aerial vehicle (UAV) missions motivated by search-and-rescue (SAR) scenarios under limited simulation training. The framework combines a fixed rule-based high-level advisor with an online goal-conditioned low-level reinforcement learning (RL) controller. To stress-test early adaptation, we also consider a strict no-pretraining deployment regime. The high-level advisor is defined offline from a structured task specification and compiled into deterministic rules. It provides interpretable mission- and safety-aware guidance through recommended actions, avoided actions, and regime-dependent arbitration weights. The low-level controller learns online from task-defined dense rewards and reuses experience through a mode-aware prioritized replay mechanism augmented with rule-derived metadata. We evaluate the framework on two tasks: battery-aware multi-goal delivery and moving-target delivery in obstacle-rich environments. Across both tasks, the proposed method improves early safety and sample efficiency primarily by reducing collision terminations, while preserving the ability to adapt online to scenario-specific dynamics.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 30 references that are in the map. First posted on arXiv 29 Apr 2026.
Builds on
15 of 30 references.
References · 15
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2024Reinforcement learningcited by 236
- 2017Trial without Error: Towards Safe Reinforcement Learning via Human Interventioncited by 102
- 2022You Only Live Once: Single-Life Reinforcement Learningcited by 23
- 2021Large Batch Simulation for Deep Reinforcement Learningcited by 18
- 2025Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Modelscited by 6
- 2026Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulationcited by 6
- 2023UAV Path Planning Employing MPC- Reinforcement Learning Method Considering Collision Avoidancecited by 4
- 2024Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replaycited by 4
- 2024PPO-based Dynamic Control of Uncertain Floating Platforms in the Zero-G Environmentcited by 4
- 2025A Survey on DRL based UAV Communications and Networking: DRL Fundamentals, Applications and Implementationscited by 4
- 2023Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specificationscited by 3
3 more
- 2023Safe Hierarchical Reinforcement Learning for CubeSat Task Scheduling Based on Energy Consumptioncited by 3
- 2025Motion Control in Multi-Rotor Aerial Robots Using Deep Reinforcement Learningcited by 2
- 2025MPC-based Deep Reinforcement Learning Method for Space Robotic Control with Fuel Sloshing Mitigationcited by 2
Built on by
Not cited yet.