[vc_empty_space][vc_empty_space]
Collision-free coverage control of swarm robotics based on gaussian process regression to estimate sensory function in non-convex environment
Prabowo Y.A.a, Trilaksono B.R.a
a Control and Computer Systems Research Group, School of Electrical Engineering and Informatics, Bandung Institute of Technology, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2019, School of Electrical Engineering and Informatics. All rights reserved.In this paper, Gaussian Process Regression (GPR) is used to estimate the time-invariant sensory function by multi-robots while performing coverage control in an environment with known obstacles. Multi-robots are deployed to explore and exploit the unknown sensory function in a given area based on their centroid of Voronoi partition. The trade-off between exploration and exploitation is weighted based on the maximum posterior variance calculated using GPR. Each robot uses the Hybrid Reciprocal Velocity Obstacle (HRVO) method to navigate without having a collision with either its neighbors or the obstacles. The presence of the obstacles may cause the Voronoi polygon is not convex so that the centroid is probably located inside the obstacle. Consequently, the centroid must be moved to the reachable point. Then, the reachable point is chosen to make the cost of coverage function, which is a function of the reachable distance and its sensory function, to be minimum. The two main contributions in this paper are: (1) Integrating estimation and coverage control based on GPR with HRVO method and (2) An enhanced strategy which adds termination iteration rule to increase the estimation and coverage time performance. Software simulations are conducted to compare the performance results by using different the number of obstacles and their locations, the number of robots, and the strategies.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Coverage control,Gaussian process regression (GPR),Hybrid reciprocal velocity obstacle (HRVO),Swarm robotics[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.15676/ijeei.2019.11.1.8[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]