AI 中文总结
本文提出DynCur-Geo动态好奇心框架，通过距离感知门与势能奖励塑造优化多模态主动地理定位，在多场景实验中较基线方法取得一致性能提升。
AI 中文摘要
主动地理定位可让低空无人机从有限的局部航拍观测中搜索指定目标，为搜救、应急巡检等时间敏感型应用提供支持。然而，多模态目标线索、受限视野及稀疏反馈使得平衡探索与目标收敛变得困难。现有好奇心驱动方法在搜索过程中会分配固定的内在奖励权重，当智能体接近目标后仍会持续奖励新奇性，进而引发绕路。本文提出DynCur-Geo，一种动态好奇心框架，可根据剩余目标距离调整基于预测误差的内在奖励。距离感知门机制鼓励早期探索，并在智能体接近目标时将策略转向目标导向行为，同时基于势能的奖励塑造提供密集的进展引导。在多模态、跨场景、受灾场景及长距离设置下的实验表明，该方法相较于主动地理定位基线方法取得了一致的性能提升。
英文摘要
Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations, supporting time-sensitive applications such as search and rescue and emergency inspection. However, multimodal target cues, restricted views, and sparse feedback make it difficult to balance exploration with target convergence. Existing curiosity-driven methods assign a fixed intrinsic-reward weight throughout search, which can continue rewarding novelty after the agent nears the target and induce detours. We propose DynCur-Geo, a dynamic curiosity framework that adjusts prediction-error intrinsic reward according to remaining target distance. A distance-aware gate encourages early exploration and shifts the policy toward goal-directed behavior near the target, while potential-based reward shaping supplies dense progress guidance. Experiments across multimodal, cross-scene, disaster-affected, and long-range settings show consistent gains over active geo-localization baselines.
Comments24 pages, 18 figures, 15 tables. The main paper is 7 pages, with supplementary material included
