Active planning for underwater inspection and the benefit of adaptivity

@article{Hollinger2013ActivePF,
  title={Active planning for underwater inspection and the benefit of adaptivity},
  author={Geoffrey A. Hollinger and Brendan Englot and Franz S. Hover and Urbashi Mitra and Gaurav S. Sukhatme},
  journal={The International Journal of Robotics Research},
  year={2013},
  volume={32},
  pages={18 - 3}
}
We discuss the problem of inspecting an underwater structure, such as a submerged ship hull, with an autonomous underwater vehicle (AUV). Unlike a large body of prior work, we focus on planning the views of the AUV to improve the quality of the inspection, rather than maximizing the accuracy of a given data stream. We formulate the inspection planning problem as an extension to Bayesian active learning, and we show connections to recent theoretical guarantees in this area. We rigorously analyze… 

Figures from this paper

Robust online adaptive sensor-driven survey planning for single and multiple autonomous underwater vehicles

TLDR
A cooperative trajectory estimation algorithm is developed that is particularly well-suited to operate within the challenging underwater communications channel and is robust to localization sensor noise and can guarantee coverage in a real field coverage sense not just a planning sense.

Coverage Path Planning with Realtime Replanning and Surface Reconstruction for Inspection of 3D Underwater Structures using Autonomous Underwater Vehicles

TLDR
A replanning algorithm based on stochastic trajectory optimization that reshapes the nominal path to cope with the actual target structure perceived in situ to go beyond previous approaches in the literature and go beyond the unrealistic assumption of an idealized path execution.

Online View Planning for Inspecting Unexplored Underwater Structures

TLDR
The proposed algorithm iteratively incorporates exteroceptive sensor data and replans the next-best-view in order to fully map an underwater structure and provides real-world results using the Sparus II AUV.

Online Motion Planning for Unexplored Underwater Environments using AUVs

TLDR
An approach to endow an autonomous underwater vehicle (AUV) with the capabilities to move through unexplored environments by proposing a computational framework for planning feasible and safe paths and using the Sparus II performing autonomous missions in different real-world scenarios.

Motion Planning for Unexplored Underwater Environments using Autonomous Underwater Vehicles

TLDR
An approach to endow an autonomous underwater vehicle (AUV) with the capabilities to move through unexplored environments is presented, and a computational framework for planning feasible and safe paths is proposed.

Coverage Path Planning with Real‐time Replanning and Surface Reconstruction for Inspection of Three‐dimensional Underwater Structures using Autonomous Underwater Vehicles

TLDR
A replanning algorithm based on a stochastic trajectory optimization that reshapes the nominal path to cope with the actual target structure perceived in situ, and a pipeline of state‐of‐the‐art surface reconstruction techniques that apply to the data acquired by the AUV to obtain 3D models of the inspected structures that show the benefits of the planning method for 3D mapping.

Online motion planning for unexplored underwater environments using autonomous underwater vehicles

TLDR
An approach to endow an autonomous underwater vehicle with the capabilities to move through unexplored environments by proposing a computational framework for planning feasible and safe paths and using the Sparus II performing autonomous missions in different real‐world scenarios.

Belief-space Planning for Active Visual SLAM in Underwater Environments.

TLDR
A Gaussian belief-space planning formulation that accounts for the randomness of the loop-closure measurements in visual SLAM is designed and it is shown that this aversion to uncertainty in the posterior belief leads to desirable and intuitive behavior within active SLAM.

Autonomous Data Collection With Limited Time for Underwater Vehicles

TLDR
Simulation and field experiments demonstrate the efficiency of the approach in planning collision-free and dynamically feasible trajectories that reduce the accrued penalty in the problem of autonomous data collection.

An informative path planning framework for UAV-based terrain monitoring

TLDR
This article introduces a general informative path planning framework for monitoring scenarios using an aerial robot, focusing on problems in which the value of sensor information is unevenly distributed in a target area and unknown a priori.
...

References

SHOWING 1-10 OF 78 REFERENCES

Uncertainty-driven view planning for underwater inspection

TLDR
A method for constructing 3D meshes from sonar-derived point clouds that provides watertight surfaces, and uncertainty modeling is introduced through non-parametric Bayesian regression to provide novel cost functions for planning the path of the AUV to minimize a metric of inspection performance.

Active Classification: Theory and Application to Underwater Inspection

TLDR
The problem in which an autonomous vehicle must classify an object based on multiple views is formulated as an extension to Bayesian active learning, and the benefit of acting adaptively as new information becomes available is formally analyzed.

Advanced perception, navigation and planning for autonomous in-water ship hull inspection

TLDR
On the open hull, integrated acoustic and visual mapping processes to achieve closed-loop control relative to features such as weld-lines and biofouling are integrated, and new large-scale planning routines are implemented so as to achieve full imaging coverage of all the structures, at a high resolution.

Imaging sonar-aided navigation for autonomous underwater harbor surveillance

TLDR
This paper extracts dense features from a forward-looking imaging sonar and applies pair-wise registration between sonar frames to obtain an improved estimate of the vehicle trajectory and shows results from several experiments that demonstrate drift-free navigation in various underwater environments.

Efficient Multi-robot Search for a Moving Target

TLDR
It is proved that solving the MESPP problem requires maximizing a non-decreasing, submodular objective function, which leads to theoretical bounds on the performance of the proposed linearly scalable approximation algorithm.

Efficient Informative Sensing using Multiple Robots

TLDR
ESIP (efficient Single-robot Informative Path planning), an approximation algorithm for optimizing the path of a single robot, and a general technique, sequential allocation, which can be used to extend any single robot planning algorithm, such as eSIP, for the multi-ro robot problem.

Real‐Time SLAM with Octree Evidence Grids for Exploration in Underwater Tunnels

TLDR
An efficient octree data structure is presented that makes it feasible to maintain the hundreds of maps needed by the particle filter to accurately model large environments and can exploit spatial locality and temporal shared ancestry between particles to reduce the processing and storage requirements.

Pose-graph visual SLAM with geometric model selection for autonomous underwater ship hull inspection

  • Ayoung KimR. Eustice
  • Computer Science
    2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2009
TLDR
The application of vision based simultaneous localization and mapping (SLAM) to the problem of autonomous ship hull inspection by an underwater vehicle validates the algorithm's potential to provide in-situ navigation in the underwater environment for trajectory control, while generating a texture-mapped 3D model of the ship hull as a byproduct for inspection.

Planning Complex Inspection Tasks Using Redundant Roadmaps

TLDR
This work generates paths on a par with dual sampling, with reduced computational effort for fast, automated planning of robotic inspections involving complex 3D structures, using an a priori triangle mesh model obtained from real sonar data and comprised of 100,000 primitives.

Developing visual sensing strategies through next best view planning

TLDR
An incremental approach is developed, which alternates between an accuracy-driven next best view determination and recursive path planning, and a novel cost function that quantifies the expected contribution of future viewing configurations.
...