EPIC: A Lightweight LiDAR-Based AAV Exploration Framework for Large-Scale Scenarios

激光雷达 史诗 比例(比率) 计算机科学 遥感 环境科学 航空航天工程 地质学 工程类 地理 地图学 艺术 文学类
作者
Shuang Geng,Zelin Ning,Fu Zhang,Boyu Zhou
出处
期刊:IEEE robotics and automation letters [Institute of Electrical and Electronics Engineers]
卷期号:10 (5): 5090-5097 被引量:42
标识
DOI:10.1109/lra.2025.3555878
摘要

Autonomous exploration is a fundamental problem for various applications of autonomous aerial vehicles (AAVs). Recently, LiDAR-based exploration has gained significant attention due to its ability to generate high-precision point cloud maps of large-scale environments. While the point clouds are inherently informative for navigation, many existing exploration methods still rely on additional, often expensive, environmental representations. This reliance stems from two main reasons: the need for frontier detection or information gain computation, which typically depends on memory-intensive occupancy grid maps, and the high computational complexity of path planning directly on point clouds, primarily due to costly collision checking. To address these limitations, we present EPIC, a lightweight LiDAR-based AAV exploration framework that directly exploits point cloud data to explore large-scale environments. EPIC introduces a novel observation map based on the quality of point clouds, treating the environment as a collection of small surface patches and evaluating their observation quality. It maintains and updates this quality using spatial hashing. By guiding the AAV from well-observed to poorly-observed areas, EPIC eliminates the need for global occupancy grid maps, while ensuring robust exploration and effective performance across diverse environments. We also propose an incremental topological graph construction method operating directly on point clouds, enabling real-time path planning in large-scale environments. Leveraging these components, we build a hierarchical planning framework that generates agile and energy-efficient trajectories, achieving significantly reduced memory consumption and computation time compared to most existing methods. Extensive simulations and real-world experiments demonstrate that EPIC achieves faster exploration while significantly reducing memory consumption compared to state-of-the-art methods.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
1秒前
2秒前
星辰大海的应助被生半夏采纳,获得10
2秒前
2秒前
及禾发布了新的文献求助10
2秒前
含糊的云朵完成签到 ,获得积分10
3秒前
3秒前
3秒前
3秒前
WT发布了新的文献求助10
3秒前
生动寒凝完成签到,获得积分10
3秒前
bird0421完成签到 ,获得积分10
4秒前
li完成签到 ,获得积分10
5秒前
wty发布了新的文献求助10
5秒前
6秒前
星指江南完成签到,获得积分10
7秒前
xx完成签到,获得积分10
7秒前
半点禅完成签到,获得积分10
8秒前
8秒前
潇洒的诗桃完成签到,获得积分0
8秒前
云飞雪落完成签到 ,获得积分10
9秒前
冷静夜蕾发布了新的文献求助10
9秒前
11秒前
ptyz霍建华完成签到 ,获得积分10
11秒前
激动的海豚完成签到,获得积分10
11秒前
cdercder的应助被皮卡丘采纳,获得10
11秒前
wang发布了新的文献求助10
12秒前
直率翠绿完成签到,获得积分10
13秒前
xx发布了新的文献求助10
13秒前
洛泱完成签到 ,获得积分10
13秒前
14秒前
跳跃的岂愈完成签到,获得积分10
15秒前
畅快的静蕾完成签到,获得积分10
15秒前
16秒前
16秒前
16秒前
CipherSage的应助被冷静夜蕾采纳,获得10
16秒前
丘比特的应助被Han采纳,获得10
16秒前
17秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188221
求助须知:如何正确求助?哪些是违规求助? 9576025
关于积分的说明 21845049
捐赠科研通 7786165
什么是DOI,文献DOI怎么找? 3435226
关于科研通互助平台的介绍 2559559
邀请新用户注册赠送积分活动 2482157