DynCur-Geo: Dynamic Curiosity Reward Shaping for Multimodal Active Geo-Localization

2026-08-19

AI Summary

DynCur-Geo通过动态调整预测误差内在奖励来解决低空无人机在多模态主动地理定位中平衡探索与目标收敛的问题。

Abstract

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.

Problem

• Active geo-localization
• Multimodal target cues
• Sparse feedback

Innovation

• Dynamic Curiosity
• Prediction-error Intrinsic Reward
• Distance-aware Gate
• Potential-based Reward Shaping