On AUV actions to correctly label world information

Francesco Maurelli; Zeyn Saigol; David Michael Lane; Michael Cashmore; Bram Ridder; Daniel Magazzeni

On AUV actions to correctly label world information

Francesco Maurelli, Zeyn Saigol, David Michael Lane, Michael Cashmore, Bram Ridder, Daniel Magazzeni

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

An Autonomous Underwater Vehicle (AUV) needs to demonstrate a number of capabilities, in order to carry on au- tonomous missions with success. One of the key areas is correctly understanding the surrounding environment. However, most of the state-of-the-art approaches in labelling world information are based on the analysis of a single frame, whilst - especially in scenarios where the vehicle interact with complex structures - there is the need of sensor data from multiple views, in order to correctly classify world information. This paper presents an active approach to solve this problem, with a tree-based (path)- planner which makes the vehicle executing a specific set of actions (following a specific trajectory), in order to discriminate among several possibilities. Results in simulation, with varying parameters, have shown that the algorithm is always bringing the robot to locations where it is expected that measurements would be different, according to the different environment.

Original language	English
Title of host publication	IEEE International Conference OCEANS 2014, St John's
Publisher	IEEE
Publication status	Published - 14 Sept 2014

Cite this

@inproceedings{b3fc25fe1af44452ac8c8e09099d4dc2,

title = "On AUV actions to correctly label world information",

abstract = "An Autonomous Underwater Vehicle (AUV) needs to demonstrate a number of capabilities, in order to carry on au- tonomous missions with success. One of the key areas is correctly understanding the surrounding environment. However, most of the state-of-the-art approaches in labelling world information are based on the analysis of a single frame, whilst - especially in scenarios where the vehicle interact with complex structures - there is the need of sensor data from multiple views, in order to correctly classify world information. This paper presents an active approach to solve this problem, with a tree-based (path)- planner which makes the vehicle executing a specific set of actions (following a specific trajectory), in order to discriminate among several possibilities. Results in simulation, with varying parameters, have shown that the algorithm is always bringing the robot to locations where it is expected that measurements would be different, according to the different environment.",

author = "Francesco Maurelli and Zeyn Saigol and Lane, {David Michael} and Michael Cashmore and Bram Ridder and Daniel Magazzeni",

year = "2014",

month = sep,

day = "14",

language = "English",

booktitle = "IEEE International Conference OCEANS 2014, St John's",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - On AUV actions to correctly label world information

AU - Maurelli, Francesco

AU - Saigol, Zeyn

AU - Lane, David Michael

AU - Cashmore, Michael

AU - Ridder, Bram

AU - Magazzeni, Daniel

PY - 2014/9/14

Y1 - 2014/9/14

N2 - An Autonomous Underwater Vehicle (AUV) needs to demonstrate a number of capabilities, in order to carry on au- tonomous missions with success. One of the key areas is correctly understanding the surrounding environment. However, most of the state-of-the-art approaches in labelling world information are based on the analysis of a single frame, whilst - especially in scenarios where the vehicle interact with complex structures - there is the need of sensor data from multiple views, in order to correctly classify world information. This paper presents an active approach to solve this problem, with a tree-based (path)- planner which makes the vehicle executing a specific set of actions (following a specific trajectory), in order to discriminate among several possibilities. Results in simulation, with varying parameters, have shown that the algorithm is always bringing the robot to locations where it is expected that measurements would be different, according to the different environment.

AB - An Autonomous Underwater Vehicle (AUV) needs to demonstrate a number of capabilities, in order to carry on au- tonomous missions with success. One of the key areas is correctly understanding the surrounding environment. However, most of the state-of-the-art approaches in labelling world information are based on the analysis of a single frame, whilst - especially in scenarios where the vehicle interact with complex structures - there is the need of sensor data from multiple views, in order to correctly classify world information. This paper presents an active approach to solve this problem, with a tree-based (path)- planner which makes the vehicle executing a specific set of actions (following a specific trajectory), in order to discriminate among several possibilities. Results in simulation, with varying parameters, have shown that the algorithm is always bringing the robot to locations where it is expected that measurements would be different, according to the different environment.

M3 - Conference contribution

BT - IEEE International Conference OCEANS 2014, St John's

PB - IEEE

ER -

On AUV actions to correctly label world information

Abstract

Fingerprint

Cite this