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

• URL: http://arxiv.org/abs/2608.18673v1
• Date: Wed, 19 Aug 2026 08:24:49 GMT
• Title: DynCur-Geo: Dynamic Curiosity Reward Shaping for Multimodal Active Geo-Localization
• Abstract summary: Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations.<n>Existing curiosity-driven methods assign a fixed intrinsic-reward weight throughout search.<n>We propose DynCur-Geo, a dynamic curiosity framework that adjusts prediction-error intrinsic reward according to remaining target distance.
• Score: 13.538716801280769
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• MPPI-based Informative Trajectory Planning for Search and Capture of Drifting Targets with ASVs [0.8602553195689513]
  We address the problem of search and capture of drifting targets using a hybrid planning framework.<n>A planner directly generates kinematic-level commands by optimising continuous trajectories over long horizons.<n>Experiments show that our planner outperforms the chosen planning baselines.
  arXiv  Detail & Related papers  (2026-06-10T12:44:25Z)
• Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning [72.13218601075958]
  We introduce textbfWanderBench, the first open access global geolocation benchmark for actionable geolocation reasoning in embodied scenarios.<n>We propose textbfGeoAoT (Action of Thought), a underlineGeolocation framework with underlineAction of underlineThough, which couples reasoning with embodied actions.<n>Experiments on 19 large multimodal models show that GeoAoT achieves superior fine-grained localization and stronger generalization in dynamic environments.
  arXiv  Detail & Related papers  (2026-03-11T06:24:10Z)
• GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration [24.01750902074338]
  Active Geo-localization (AGL) is the task of localizing a goal within a predefined search area.<n>Current methods approach AGL as a goal-reaching reinforcement learning problem with a distance-based reward.<n>We propose GeoExplorer, an AGL agent that incorporates curiosity-driven exploration through intrinsic rewards.
  arXiv  Detail & Related papers  (2025-07-31T20:23:25Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• GOMAA-Geo: GOal Modality Agnostic Active Geo-localization [49.599465495973654]
  We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. GOMAA-Geo is a goal modality active geo-localization agent for zero-shot generalization between different goal modalities.
  arXiv  Detail & Related papers  (2024-06-04T02:59:36Z)
• Reinforcement Learning for Agile Active Target Sensing with a UAV [10.070339628481445]
  This paper develops a deep reinforcement learning approach to plan informative trajectories. It exploits its current belief of the target states and incorporates inaccurate sensor models for high-fidelity classification. A unique characteristic of our approach is that it is robust to varying amounts of deviations from the true target distribution.
  arXiv  Detail & Related papers  (2022-12-16T01:01:17Z)
• SRRT: Exploring Search Region Regulation for Visual Object Tracking [58.68120400180216]
  We propose a novel tracking paradigm, called Search Region Regulation Tracking (SRRT) SRRT applies a proposed search region regulator to estimate an optimal search region dynamically for each frame. On the large-scale LaSOT benchmark, SRRT improves SiamRPN++ and TransT with absolute gains of 4.6% and 3.1% in terms of AUC.
  arXiv  Detail & Related papers  (2022-07-10T11:18:26Z)
• Tracking by Joint Local and Global Search: A Target-aware Attention based Approach [63.50045332644818]
  We propose a novel target-aware attention mechanism (termed TANet) to conduct joint local and global search for robust tracking. Specifically, we extract the features of target object patch and continuous video frames, then we track and feed them into a decoder network to generate target-aware global attention maps. In the tracking procedure, we integrate the target-aware attention with multiple trackers by exploring candidate search regions for robust tracking.
  arXiv  Detail & Related papers  (2021-06-09T06:54:15Z)
• Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking [62.13213518417047]
  We propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy. In particular, we construct dynamic appearance model that contains multiple target templates, each of which provides its own attention for locating the target in the new frame. After spanning the whole sequence, we introduce a multi-trajectory selection network to find the best trajectory that delivers improved tracking performance.
  arXiv  Detail & Related papers  (2021-03-30T05:36:31Z)
• Dynamic Subgoal-based Exploration via Bayesian Optimization [7.297146495243708]
  Reinforcement learning in sparse-reward navigation environments is challenging and poses a need for effective exploration. We propose a cost-aware Bayesian optimization approach that efficiently searches over a class of dynamic subgoal-based exploration strategies. An experimental evaluation demonstrates that the new approach outperforms existing baselines across a number of problem domains.
  arXiv  Detail & Related papers  (2019-10-21T04:24:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.