Autonomous Search Systems, phase 2

Important results from the project

The project aim has been to demonstrate an aerial autonomous search system (manned or not), using image-based Automatic Target Search System by means of pattern recognition, perception, reasoning, decision-making and machine learning combining available resources for situation assessment and possible delivering of survival-related supplies on Search and Rescue missions. The project has achieved its goals in that the autonomous search system now have developed novel functionalities related to how these systems can be used in more sophisticated mission scenarios.

Expected long term effects

The project has met the expected results. The Swedish and Brazilian parts have been integrated and demonstrated. Common interfaces and information representations have enabled seamless integration with demonstrations at, among other things, the WASP WARA-PS workshop event 2023, with large participation from academia and industry. The project has also generated two scientific articles, where one is approved for publication, as well as submitted two conference articles to the 17th Multi-disciplinary International Conference on Artificial Intelligence (MIWAI 2024).

Approach and implementation

Functions associated with the task, information, and interaction perspectives were integrated into an autonomous search system demonstrator/prototype. The image analysis based classification subsystem from the Brazilian del project was integrated into this AuSSys prototype. Several SAR (Search and Rescue) scenarios have been defined and demonstrated during the WASP WARA-PS workshops, both 2022 (phase 1) and 2023 (phase 2), using the integrated software prototypes developed within the project.