Return to search

Surveillance Path Planning for Unmanned Ground Vehicles

Advancements in the field of robotics together with an increased need for surveillance  have lead to an interest in utilizing autonomous agents  for area monitoring at sensitive installations. For this Master's thesis, an informative path planner called  Autonomous Surveillance Planner (ASP) was developed to be used with unmanned ground vehicles for area monitoring.  It discretizes an area of operations  into cells and assigns each cell an intruder probability. The planner then chooses the  optimal path by minimizing a cost function describing the probability of not finding an intruder along a path. Since the minimization is computationally costly, the computed path does not cover the entire area but instead only a small portion at a time.  The path from the ASP is then relayed to a timed elastic band local planner which adjusts  the path such that it avoids obstacles and is fast for an agent to execute, as well as computes control signals.   The algorithms were tested both in simulations and during field tests with promising results, showcasing that using unmanned ground vehicles for autonomous area monitoring has potential to be used in a real-world application. ASP was fast enough to be used in real-time  and was able to fully cover the area of operations. The local planner was computationally  demanding, but was able to avoid obstacles and make the agent follow the global path. / <p>Opponent: Samuel Ericson Andersson</p>

Identiferoai:union.ndltd.org:UPSALLA1/oai:DiVA.org:liu-204988
Date January 2024
CreatorsWiman, David
PublisherLinköpings universitet, Reglerteknik
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, info:eu-repo/semantics/bachelorThesis, text
Formatapplication/pdf
Rightsinfo:eu-repo/semantics/openAccess

Page generated in 0.0016 seconds