A genetic planner for mission planning of cooperative agents in an underwater environment
2017 (English)In: The 2016 IEEE Symposium Series on Computational Intelligence SSCI'16, 2017, 7850163Conference paper (Refereed)
In this paper, a Genetic Algorithm (GA) is used for solving underwater mission planning problem. The proposed genetic planner is capable of utilizing multiple Autonomous Underwater Vehicles (AUVs) and Remotely Operated Vehicles (ROVs) in a mission plan, as well as running multiple tasks in parallel on the agents level. The problem is described using STRIPS modeling language. The proposed planner shows high robustness regarding initial population set, which is randomly generated. Chromosomes have variable length, consisting of active and inactive genes. Various genetic operators are used in order to improve convergence of the algorithm. Although genetic planner presented in this work is for underwater missions, this planning approach is universal, and it is not domain dependent. Results for a realistic case study with five AUVs and almost 30 tasks show that this approach can be used successfully for solving complex mission planning problems.
Place, publisher, year, edition, pages
High-Level Planning, Genetic Algorithms, Mission Planning, Multi-Agent Systems, Underwater robotics
IdentifiersURN: urn:nbn:se:mdh:diva-34089DOI: 10.1109/SSCI.2016.7850163ScopusID: 2-s2.0-85016008798OAI: oai:DiVA.org:mdh-34089DiVA: diva2:1056587
The 2016 IEEE Symposium Series on Computational Intelligence SSCI'16, 6-9 Dec 2016, Athens, Greece
ProjectsSmart and networking underWAter Robots in cooperation MesheS