SLIDER: Sparse History-Guided Aerial Robot Target Search using Sliding Local Maps

2026-07-11

AI Summary

This work addresses the challenge of efficient autonomous exploration for aerial robots in large-scale unknown environments, where balancing wide-area coverage, fine-grained perception, and real-time decision-making remains difficult. The authors propose a lightweight active exploration framework that eschews dense global mapping by integrating a sliding local map with sparse global historical information. A novel real-time observation quality assessment mechanism, grounded in historical poses and sensor models, is introduced to guide exploration. Additionally, the framework employs an incremental viewpoint clustering strategy and constructs a sparse topological graph to enable scalable navigation. Experimental results demonstrate that the proposed system significantly outperforms state-of-the-art methods in terms of memory consumption, decision latency, and search efficiency.

Abstract

Efficient exploration and target search in large-scale unknown environments remain challenging for aerial robots due to the demands of broad spatial coverage, fine-grained perception, and real-time decision-making. This paper presents SLIDER, a lightweight and memory-efficient framework that avoids reliance on globally dense maps by combining a local sliding map with sparse global history information. A novel observation quality evaluation method is proposed, leveraging historical poses and sensor models to assess point cloud data in real-time, enabling efficient frontier detection. To support scalable and responsive planning, an incremental viewpoint clustering strategy dynamically adapts to local updates, significantly reducing the number of candidate targets and decreasing computational load. A sparse global topological map is incrementally maintained to assist global planning and cost evaluation. Extensive simulations and real-world experiments demonstrate that the proposed system outperforms state-of-the-art methods in memory usage, decision latency, and search efficiency.

Problem

• aerial robot
• target search
• large-scale unknown environments
• efficient exploration
• real-time decision-making

Innovation

• sliding local map
• sparse global history
• observation quality evaluation
• incremental viewpoint clustering
• topological map