A SLAM-based approach for underwater mapping using AUVs with poor inertial information

Hammond, Marcus; Rock, Stephen M.

doi:10.1109/auv.2014.7054419

Cited by 11 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inertial package in [8] also shows highly accurate results as it is a simulation derivative of the INS in [5], [7], [10]. Lastly, [6] and [9] use SLAM to address missing, or noisy inertial information, showing improvement, but with drift still present.…”

Section: A Underwater Slam With Sonarmentioning

confidence: 97%

“…Graph-based pose SLAM has been used to support many successful underwater sonar-based SLAM applications. Ship hull inspection using a forward-looking imaging sonar is demonstrated in [5], multibeam profiling sonar SLAM traversing an underwater canyon is achieved in [6], and planar SLAM using imaging sonar observations of the seafloor is described in [7]. Additionally, [8] uses a factor graph to perform dense reconstruction of complex 3D structures using multibeam profiling sonar.…”

Section: A Underwater Slam With Sonarmentioning

confidence: 99%

See 1 more Smart Citation

Overhead Image Factors for Underwater Sonar-based SLAM

McConnell¹,

Chen²,

Englot³

2022

Preprint

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) is a critical capability for any autonomous underwater vehicle (AUV). However, robust, accurate state estimation is still a work in progress when using low-cost sensors. We propose enhancing a typical low-cost sensor package using widely available and often free prior information; overhead imagery. Given an AUV's sonar image and a partially overlapping, globallyreferenced overhead image, we propose using a convolutional neural network (CNN) to generate a synthetic overhead image predicting the above-surface appearance of the sonar image contents. We then use this synthetic overhead image to register our observations to the provided global overhead image. Once registered, the transformation is introduced as a factor into a pose SLAM factor graph. We use a state-of-the-art simulation environment to perform validation over a series of benchmark trajectories and quantitatively show the improved accuracy of robot state estimation using the proposed approach. We also show qualitative outcomes from a real AUV field deployment. Video attachment: https://youtu.be/_uWljtp58ks

show abstract

Section: A Underwater Slam With Sonarmentioning

confidence: 97%

Section: A Underwater Slam With Sonarmentioning

confidence: 99%

Overhead Image Factors for Underwater Sonar-based SLAM

McConnell¹,

Chen²,

Englot³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A solution to the SLAM problem based on a multibeam sonar measurement for autonomous underwater vehicles (AUVs) with limited inertial information was proposed in Hammond and Rock (2015). The described method utilises the GraphSLAM for determination of robot poses.…”

Section: Underwater Navigationmentioning

confidence: 99%

Robotic system for off-shore infrastructure monitoring

Ciszewski

Mitka

Kohut

et al. 2017

Journal of Marine Engineering & Technology

View full text Add to dashboard Cite

In this paper, a novel modular reconfigurable mobile inspection robotic system is presented. The system consists of two underwater robotic platforms, including a tracked mobile robot for moving on rough terrain and a remotely operated vehicle robot for free underwater operation. Applications of the system include structural monitoring of off-shore infrastructure made of steel, concrete or other materials. The system is equipped with a 3D sonar, high-definition cameras and laser sensors to navigate underwater and locate structural defects. Mathematical models of the tracked robot are derived for operation underwater. Operation and verification of the ROV vision system is shown. The system sensing equipment is capable of performing simultaneous localisation and mapping tasks, thus an algorithm for navigation and localisation of defects based on sensor fusion is proposed and discussed.

show abstract

“…Position estimates are typically made based on these sensor measurements through dead reckoning (DR) or the use of an extended Kalman filter (EKF). Simple DR suffers from cumulative drift in position, which is unbounded and is typically in the order of 5% of distance travelled [4]. For a mission where a vehicle travels several kilometres, we would expect position uncertainty of several tens of metres.…”

Section: Introductionmentioning

confidence: 99%

Submap bathymetric SLAM using structured light in underwater environments

Massot-Campos

Oliver

Bodenmann

et al. 2016

2016 IEEE/OES Autonomous Underwater Vehicles (AUV)

View full text Add to dashboard Cite

Abstract-This article presents a bathymetric SLAM (simultaneous localization and mapping) solution for underwater vehicles by addressing the registration of point clouds gathered from single line laser-based structured light systems. While structured light can be applied to generate millimetre resolution seafloor bathymetry, the accuracy of the maps generated is typically constrained by the localization accuracy of the vehicles used. In this work, relative uncertainties in vehicle localisation are reduced by implementing bathymetric SLAM using temporally constrained submaps. We demonstrate that the method described can overcome misalignments by correcting errors in localisation and can be used to generate self-consistent high-resolution seafloor bathymetric maps.

show abstract

A SLAM-based approach for underwater mapping using AUVs with poor inertial information

Cited by 11 publications

References 18 publications

Overhead Image Factors for Underwater Sonar-based SLAM

Overhead Image Factors for Underwater Sonar-based SLAM

Robotic system for off-shore infrastructure monitoring

Submap bathymetric SLAM using structured light in underwater environments

Contact Info

Product

Resources

About