Safety
DynCur-Geo: Dynamic Curiosity Reward Shaping for Multimodal Active Geo-Localization
arXiv:2608.18673v1 Announce Type: new Abstract: Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations, supporting time-sensitive appl
arXiv:2608.18673v1 Announce Type: new 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.
Related
- Uncertainty-Aware Hierarchical Re-Localization in OpenStreetMap via Semantic Alignment
- SASGeo: Stability-Aware Semantic Map Localization for GNSS-Denied UAVs -- A Framework and Synthetic Proof of Concept
- Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
- Parallel Tempering Initial Sampling in Inference-Time Reward Alignment
Source: arXiv cs.CV | 2026-08-20