DUGiDocsAdvanced underwater vehicle manipulation through real-time motion planning
Text Complet
A key challenge in autonomous mobile manipulation is the ability to
determine in real-time how to safely execute complex tasks when placed in an
unknown world. In response to those arising needs in the underwater domain,
this thesis focused on investigating the use of Motion Planning to increase
the autonomy of I-AUVs. we initially present a modeling and integration of
our I-AUV through MoveIt! framework, in the presence of virtual obstacles.
Then, we performed a deep analysis of the state of the art motion planning
techniques. Later, we identified planner specifications for underwater
intervention: Real-Time response for a high DOF system, Consistency,
Efficient trajectories in terms of safety, and system loose coupling. As a
consequence, we propose a new motion planning algorithm under the umbrella of
search-based method, that exploits the loose coupling nature of an I-AUV
while generating consistent, efficient, and safe trajectories in unknown
environments. The proposed algorithm has been validated both in simulation
and in a water tank
L'accés als continguts d'aquesta tesi queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by/4.0/
Localització