On AUV actions to correctly label world information. Maurelli, F.; Saigol, Z.; Lane, D.; Cashmore, M.; Ridder, B.; and Magazzeni, D. In 2014 Oceans - St. John's, OCEANS 2014, 2015.
abstract   bibtex   
© 2014 IEEE. An Autonomous Underwater Vehicle (AUV) needs to demonstrate a number of capabilities, in order to carry on autonomous 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.
@inProceedings{
 title = {On AUV actions to correctly label world information},
 type = {inProceedings},
 year = {2015},
 identifiers = {[object Object]},
 id = {a7c6a928-3046-386a-b4da-142f89fabca9},
 created = {2019-08-06T09:25:07.588Z},
 file_attached = {false},
 profile_id = {dea4c3bc-a7c3-34d1-96ce-91b66d6beaab},
 last_modified = {2019-08-06T13:18:42.818Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 folder_uuids = {44368d8e-dd83-4216-b406-ed580392745c},
 private_publication = {false},
 abstract = {© 2014 IEEE. An Autonomous Underwater Vehicle (AUV) needs to demonstrate a number of capabilities, in order to carry on autonomous 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.},
 bibtype = {inProceedings},
 author = {Maurelli, F. and Saigol, Z. and Lane, D. and Cashmore, M. and Ridder, B. and Magazzeni, D.},
 booktitle = {2014 Oceans - St. John's, OCEANS 2014}
}
Downloads: 0