FAEL: Fast Autonomous Exploration for Large-scale Environments With a Mobile Robot

Huang, Junlong; Zhou, Boyu; Fan, Zhencheng; Zhu, Yilin; Jie, Yingrui; Li, Longwei; Cheng, Hui

doi:10.1109/lra.2023.3236573

Cited by 11 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensors SLAM Method Path Planning [7] Lidar EKF SLAM Active revisit path planning [43] RGBD 1 , Lidar 2 , IMU 3 , WE 14 ES-DSF (EKF based) 15 A* [72] Lidar, RGB Hector SLAM Artificial potential fields [58] Lidar 4 , RGBD 5 Graph based NMPC 16 , A* [73] RGB Graph based CAO 20 [6] Lidar, RGB EKF-SLAM Maze solver algorithm [35] Lidar Lidar 2D 9 , 3D 10 Graph SLAM-based ESDSF 23 Modified D* [11] MBS 29 Graph SLAM RRT* [78] RGB EKF SLAM OCBN 24 [79] Lidar, IMU Sensor-based SLAM - [13] RGBD, Lidar 11 FastSLAM DRL 25 [12] RGB, IMU Graph SLAM RRT [38] RGB ORB-SLAM RPP 26 [80] Lidar, IMU RIEKF SLAM-based A-SLAM - [80] RGB Object SLAM - [57] RGBD 1 ORBSLAM 2 TEB local planner [65] Lidar Gmapping Deep Q learning [26] RGBD 12 , 13 , IMU Graph SLAM - [64] Lidar OpenKarto (g2o) DWA 18 [81] Lidar Gmapping DDPG 30 [82] Lidar Graph SLAM A* [66] Lidar Open Karto (g2o) Dijkstra [83] Lidar 31 EKF SLAM A* [84] RGBD 5 , IMU ORBSLAM 3, VINS Fusion - 1 Microsoft Kinect. 2 SICK LMS-100.…”

Section: Article Yearmentioning

confidence: 99%

Active SLAM: A Review on Last Decade

Ahmed,

Masood,

Fremont

et al. 2023

Sensors

View full text Add to dashboard Cite

This article presents a comprehensive review of the Active Simultaneous Localization and Mapping (A-SLAM) research conducted over the past decade. It explores the formulation, applications, and methodologies employed in A-SLAM, particularly in trajectory generation and control-action selection, drawing on concepts from Information Theory (IT) and the Theory of Optimal Experimental Design (TOED). This review includes both qualitative and quantitative analyses of various approaches, deployment scenarios, configurations, path-planning methods, and utility functions within A-SLAM research. Furthermore, this article introduces a novel analysis of Active Collaborative SLAM (AC-SLAM), focusing on collaborative aspects within SLAM systems. It includes a thorough examination of collaborative parameters and approaches, supported by both qualitative and statistical assessments. This study also identifies limitations in the existing literature and suggests potential avenues for future research. This survey serves as a valuable resource for researchers seeking insights into A-SLAM methods and techniques, offering a current overview of A-SLAM formulation.

show abstract

Section: Article Yearmentioning

confidence: 99%

Active SLAM: A Review on Last Decade

Ahmed,

Masood,

Fremont

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Information-theoretic approaches (Bourgault et al 2002; Corah and Michael 2019; Lauri and Ritala 2016; Tabib et al 2022; Charrow et al 2015) are considered to be mathematically sound as they directly aim to optimize map quality but are computationally demanding in practice. Frontier-based approaches (Burgard et al 2005; Krátký et al 2021; Saroya et al 2020; Yamauchi 1997; Zhou et al 2021; Colares and Chaimowicz 2016; Tao et al 2023; Huang et al 2023), despite being heuristics, typically generate trajectories similar to information-theoretic approaches with less computational burden. Graph search–based approaches (Cao et al 2021; Dang et al 2020; Kulkarni et al 2022; Dharmadhikari et al 2020; Yang et al 2021; Huang et al 2023) build on the previous approaches by explicitly modeling topology, resulting in solutions that are scalable to large environments.…”

Section: Related Workmentioning

confidence: 99%

“…Frontier-based approaches (Burgard et al 2005; Krátký et al 2021; Saroya et al 2020; Yamauchi 1997; Zhou et al 2021; Colares and Chaimowicz 2016; Tao et al 2023; Huang et al 2023), despite being heuristics, typically generate trajectories similar to information-theoretic approaches with less computational burden. Graph search–based approaches (Cao et al 2021; Dang et al 2020; Kulkarni et al 2022; Dharmadhikari et al 2020; Yang et al 2021; Huang et al 2023) build on the previous approaches by explicitly modeling topology, resulting in solutions that are scalable to large environments.…”

Section: Related Workmentioning

confidence: 99%

“…Our work with the proposed system has also directly motivated many ongoing projects related to fundamental technical improvements for specific subsystems that were beyond the scope of the current system. We list examples as follows:• Improvements to SLAM for aerial robots and reliable visual-SLAM algorithms for light-weight aerial robots (Zhao et al 2021, 2023; Ebadi et al 2022);• Planning the deployment locations and times of multiple aerial robots (Lee et al, 2021a, 2021b; Mitchell et al, 2023);• Behavior tree structure learning from simulations or a formal problem definition (Scheide et al 2021);• Fast Euclidean distance transform mapping implementation with OpenVDB (Zhu et al 2021);• Predictive topological mapping and exploration (Saroya et al 2020, 2021; Yang et al 2021; Sukkar et al 2019; Choudhury et al 2018; McCammon and Hollinger 2021; Kim et al 2023);• Semantics-based frontier selection for exploration (Hu et al 2023; Rankin et al 2021);• Planning the use of limited communication resources (Tatum 2020; Best et al 2018b; Anderson and Hollinger 2021);• Decentralized coordination with explicit sharing of intent (Best et al 2019; Sukkar et al 2019; Best and Hollinger 2020; Kim et al 2023). …”

Section: Lessons Learned and Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-robot, multi-sensor exploration of multifarious environments with full mission aerial autonomy

Best,

Garg,

Keller

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

We present a coordinated autonomy pipeline for multi-sensor exploration of confined environments. We simultaneously address four broad challenges that are typically overlooked in prior work: (a) make effective use of both range and vision sensing modalities, (b) perform this exploration across a wide range of environments, (c) be resilient to adverse events, and (d) execute this onboard teams of physical robots. Our solution centers around a behavior tree architecture, which adaptively switches between various behaviors involving coordinated exploration and responding to adverse events. Our exploration strategy exploits the benefits of both visual and range sensors with a generalized frontier-based exploration algorithm and an OpenVDB-based map processing pipeline. Our local planner utilizes a dynamically feasible trajectory library and a GPU-based Euclidean distance transform map to allow fast and safe navigation through both tight doorways and expansive spaces. The autonomy pipeline is evaluated with an extensive set of field experiments, with teams of up to three robots that fly up to 3 m/s and distances exceeding 1 km in confined spaces. We provide a summary of various field experiments and detail resilient behaviors that arose: maneuvering narrow doorways, adapting to unexpected environment changes, and emergency landing. Experiments are also detailed from the DARPA Subterranean Challenge, where our proposed autonomy pipeline contributed to us winning the “Most Sectors Explored” award. We provide an extended discussion of lessons learned, release software as open source, and present a video that illustrates our extensive field trials.

show abstract

“…It is essential for robotic applications in search and rescue, as well as security patrol missions. Unmanned ground vehicles (UGVs) use different types of sensors, such as three‐dimensional (3D) Light Detection and Rangings (LiDARs) and cameras, for explorations (Dang et al, 2020; Huang et al, 2023). LiDAR sensors output point clouds, making geometric information of operating environments easily obtainable.…”

Section: Introductionmentioning

confidence: 99%

Whole‐body motion planning and tracking of a mobile robot with a gimbal RGB‐D camera for outdoor 3D exploration

Wang,

Chen,

2024

Journal of Field Robotics

View full text Add to dashboard Cite

Autonomous exploration is a fundamental problem for certain applications of unmanned ground vehicles (UGVs). Depth cameras are widely used in exploring indoor and specific outdoor environments. However, existing methods suffer from inefficient and unstable performance of exploration in open outdoor environments. This study develops a framework to achieve fast and robust three‐dimensional exploration by UGVs with a gimbal camera in challenging outdoor environments. A hierarchical reactive planning approach based on a multilayered map is proposed to improve exploration efficiency. Additionally, an adaptive semantic mapping algorithm is proposed to more accurately and stably represent the environmental localization uncertainty. Localization uncertainty is integrated into the planning approach to decrease odometry drift and prevent localization failure, further enhancing the exploration robustness. A viewpoint tracking controller based on terrain‐aware model predictive control is proposed to guarantee the accuracy of the planned viewpoint tracking and to further improve the robustness of localization and exploration on rough terrains. Finally, several physical‐engine simulations and experiments in outdoor environments are performed. The comparisons to existing state‐of‐the‐art approaches have verified the effectiveness of the proposed approach. The code of our system will be available at https://github.com/HITSZ-NRSL/Open3DExplorer.git.

show abstract

FAEL: Fast Autonomous Exploration for Large-scale Environments With a Mobile Robot

Cited by 11 publications

References 30 publications

Active SLAM: A Review on Last Decade

Active SLAM: A Review on Last Decade

Multi-robot, multi-sensor exploration of multifarious environments with full mission aerial autonomy

Whole‐body motion planning and tracking of a mobile robot with a gimbal RGB‐D camera for outdoor 3D exploration

Contact Info

Product

Resources

About