Autonomous Exploration of Complex Underwater Environments Using a Probabilistic Next-Best-View Planner

Palomeras, Narcís; Hurtós, Natàlia; Vidal, Eduard; Carreras, Marc

doi:10.1109/lra.2019.2896759

Cited by 43 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This representation is used by the view planner to calculate a set of candidate viewpoints and by the path planner to obtain a free path from the current position to the next-best-viewpoint. This article focuses on the active SLAM part of the system, whereas the view planner used is the one reported in [3]. Note, however, that this exploration framework could use any view planner capable of computing a set of candidate viewpoints that further explore the scene and the number of unknown cells observable from them, given an octree that represents the already explored region.…”

Section: Methodsmentioning

confidence: 99%

“…Despite the fact that the method combines an off-line view planning and SLAM, it does not check if the resulting trajectory will allow the SLAM algorithm to keep the localization uncertainty bounded, enforcing only some overlap between viewpoints. We have also presented solutions that do not require a preliminary map, but that do not localize the vehicle while exploring the 2D [27] or 3D [3] scene, nor use the robot state uncertainty to drive the exploration.…”

Section: Related Workmentioning

confidence: 99%

“…In a previous article [3] we presented a probabilistic next-best-view planner for a hover-capable autonomous underwater vehicle (AUV), that allowed for mapping complex environments without an a priori model of the scene. In the present article, we propose a method that combines our previous next-best-view planner with an active SLAM method to jointly solve the autonomous exploration problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Active SLAM for Autonomous Underwater Exploration

2019

Self Cite

View full text Add to dashboard Cite

Exploration of a complex underwater environment without an a priori map is beyond the state of the art for autonomous underwater vehicles (AUVs). Despite several efforts regarding simultaneous localization and mapping (SLAM) and view planning, there is no exploration framework, tailored to underwater vehicles, that faces exploration combining mapping, active localization, and view planning in a unified way. We propose an exploration framework, based on an active SLAM strategy, that combines three main elements: a view planner, an iterative closest point algorithm (ICP)-based pose-graph SLAM algorithm, and an action selection mechanism that makes use of the joint map and state entropy reduction. To demonstrate the benefits of the active SLAM strategy, several tests were conducted with the Girona 500 AUV, both in simulation and in the real world. The article shows how the proposed framework makes it possible to plan exploratory trajectories that keep the vehicle's uncertainty bounded; thus, creating more consistent maps.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Active SLAM for Autonomous Underwater Exploration

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, computing coverage percentage without the original reference model is considered difficult. The work presented in [19,30] terminates if no viewpoint has an IG above a predefined threshold while the work in [31] terminates if the difference in total entropy reduction decreased below a predefined threshold. Three termination conditions are used in our Guided NBV method: comparing the current NBV process iteration number with a predefined maximum iterations number, checking the global entropy E change after n iterations [32], or when no valid viewpoints are generated by the viewpoint sampling component.…”

Section: Terminationmentioning

confidence: 99%

“…The work in [17] shows that frontier method consumes time on evaluating the various amounts of viewpoints in outdoor environments while Oshima et al [18] was able to mitigate this by finding the centroids of randomly scattered points near the frontiers using clustering, and then evaluating them as candidate viewpoints. A similar approach is performed in [19], which generates viewpoints randomly and prioritizes them, and then selects the viewpoints based on the visibility and distance. In addition to this, the work in [16] selects the frontiers that minimizes the velocity changes.…”

Section: Introductionmentioning

confidence: 99%

Guided Next Best View for 3D Reconstruction of Large Complex Structures

Almadhoun

Abduldayem

Taha³

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

In this paper, a Next Best View (NBV) approach with a profiling stage and a novel utility function for 3D reconstruction using an Unmanned Aerial Vehicle (UAV) is proposed. The proposed approach performs an initial scan in order to build a rough model of the structure that is later used to improve coverage completeness and reduce flight time. Then, a more thorough NBV process is initiated, utilizing the rough model in order to create a dense 3D reconstruction of the structure of interest. The proposed approach exploits the reflectional symmetry feature if it exists in the initial scan of the structure. The proposed NBV approach is implemented with a novel utility function, which consists of four main components: information theory, model density, traveled distance, and predictive measures based on symmetries in the structure. This system outperforms classic information gain approaches with a higher density, entropy reduction and coverage completeness. Simulated and real experiments were conducted and the results show the effectiveness and applicability of the proposed approach.

show abstract

Multisensor online 3D view planning for autonomous underwater exploration

Vidal

Palomeras

Istenič

et al. 2020

Journal of Field Robotics

View full text Add to dashboard Cite

This study presents a novel octree‐based three‐dimensional (3D) exploration and coverage method for autonomous underwater vehicles (AUVs). Robotic exploration can be defined as the task of obtaining a full map of an unknown environment with a robotic system, achieving full coverage of the area of interest with data from a particular sensor or set of sensors. While most robotic exploration algorithms consider only occupancy data, typically acquired by a range sensor, our approach also takes into account optical coverage, so the environment is discovered with occupancy and optical data of all discovered surfaces in a single exploration mission. In the context of underwater robotics, this capability is of particular interest, since it allows one to obtain better data while reducing operational costs and time. This study expands our previous study in 3D underwater exploration, which was demonstrated through simulation, presenting improvements in the view planning (VP) algorithm and field validation. Our proposal combines VP with frontier‐based (FB) methods, and remains light on computations even for 3D environments thanks to the use of the octree data structure. Finally, this study also presents extensive field evaluation and validation using the Girona 500 AUV. In this regard, the algorithm has been tested in different scenarios, such as a harbor structure, a breakwater structure, and an underwater boulder.

show abstract

Autonomous Exploration of Complex Underwater Environments Using a Probabilistic Next-Best-View Planner

Cited by 43 publications

References 18 publications

Active SLAM for Autonomous Underwater Exploration

Active SLAM for Autonomous Underwater Exploration

Guided Next Best View for 3D Reconstruction of Large Complex Structures

Multisensor online 3D view planning for autonomous underwater exploration

Contact Info

Product

Resources

About