Performance-aware exploration algorithm for search and rescue robots.
Presented at: UNSPECIFIED.
Autonomous navigation in unknown cluttered environments is one of the main challenges for search and rescue robots inside collapsed buildings. Evaluation and comparison of exploration algorithms inside various simulated search fields is crucial to attain fast victim localisation. Thus in this paper we discuss an algorithmic development and proliferation of realistic after--disaster test fields. Furthermore we evaluate a performance--aware exploration algorithm inside the developed search fields. We ascertain that it is possible to reduce the overall victim discovery time significantly, relative to an unstructured search algorithm across environments of a range of complexities. Moreover, it is possible to achieve performance that approaches to our optimal victim discovery time.
|Type:||Conference item (UNSPECIFIED)|
|Title:||Performance-aware exploration algorithm for search and rescue robots|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science
UCL > School of BEAMS > Faculty of Engineering Science > Computer Science
Archive Staff Only