# Star-Searcher: A Complete and Efficient Aerial System for Autonomous Target Search in Complex Unknown Environments

**Authors:** Yiming Luo, Zixuan Zhuang, Neng Pan, Chen Feng, Shaojie Shen, Fei Gao, Hui Cheng, Boyu Zhou  
**arXiv:** [2402.16348](https://arxiv.org/abs/2402.16348)  
**Date:** 2024-02-26  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2402.16348v1/

## Key points

- Authors address the challenge of autonomous target search using UAVs in complex unknown environments
- Introduce Star-Searcher as an innovative aerial system with specialized sensor suites, mapping capabilities, and planning modules
- Development of a hierarchical planner with visibility-based viewpoint clustering method for path planning
- Hierarchical planner breaks down planning process into global and local sub-problems for efficient path coverage
- Global path planning component utilizes history-aware mechanism to mitigate motion inconsistency
- Comprehensive comparisons show Star-Searcher outperforms existing methods in simulation and real-world scenarios
- Plan to make approach open-source through a repository at https://github.com/SYSU-STAR/STAR-Searcher

## Summary

, , , , 

In their paper titled "Star-Searcher: A Complete and Efficient Aerial System for Autonomous Target Search in Complex Unknown Environments," authors Yiming Luo, Zixuan Zhuang, Neng Pan, Chen Feng, Shaojie Shen, Fei Gao, Hui Cheng, and Boyu Zhou address the challenge of autonomous target search using unmanned aerial vehicles (UAVs) in complex unknown environments. The researchers introduce Star-Searcher as an innovative aerial system equipped with specialized sensor suites, mapping capabilities, and planning modules designed to optimize the searching process. One of the key contributions of this work is the development of a hierarchical planner that incorporates a visibility-based viewpoint clustering method to tackle path planning challenges arising from increased inspection requirements. By breaking down the planning process into global and local sub-problems, the hierarchical planner ensures efficient global and local path coverage in real-time. Moreover, the global path planning component utilizes a history-aware mechanism to mitigate motion inconsistency resulting from frequent map changes. The authors conducted comprehensive comparisons with state-of-the-art methods in both simulation and real-world scenarios. The results demonstrate that Star-Searcher outperforms existing approaches by enabling shorter flight paths, reduced time spent on target search missions, and higher completeness rates in locating targets. Furthermore, the researchers plan to make their approach open-source for community benefit through a repository available at https://github.com/SYSU-STAR/STAR-Searcher. Overall,this paper presents a sophisticated solution for autonomous target search using UAVs in challenging environments. By integrating advanced sensor technology with intelligent planning algorithms, Star-Searcher represents a significant advancement in optimizing aerial search operations and holds promise for various applications requiring efficient target localization capabilities.