2.6 KiB
tags:: #zotero date:: 5/2023 publisher:: IEEE place:: "Melbourne, Australia" conference-name:: 2023 IEEE/ACM 18th Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) proceedings-title:: 2023 IEEE/ACM 18th Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) isbn:: 979-8-3503-1192-1 doi:: 10.1109/SEAMS59076.2023.00031 title:: @SUAVE: an exemplar for self-adaptive underwater vehicles pages:: 181-187 item-type:: conferencePaper access-date:: 2024-12-02T20:43:50Z rights:: https://doi.org/10.15223/policy-029 original-title:: SUAVE: an exemplar for self-adaptive underwater vehicles language:: en url:: https://ieeexplore.ieee.org/document/10173938/ short-title:: Suave authors:: Gustavo Rezende Silva, Juliane Päßler, Jeroen Zwanepol, Elvin Alberts, S. Lizeth Tapia Tarifa, Ilias Gerostathopoulos, Einar Broch Johnsen, Carlos Hernández Corbato library-catalog:: DOI.org (Crossref) links:: Local library, Web library
- Abstract
- Word count: 181 Implementing task logic and architectural adaptation for autonomous robots to cope with multiple tasks in diverse environments is a challenge. Methods from self-adaptive systems can be used to reduce development effort and improve maintainability by providing separation of concerns.However, only a few works have explored both task and architectural adaptation, and they do not address extensibility to new tasks or reuse across robotic applications. This paper proposes a novel knowledge-based solution for RObot Self-Adaptation (ROSA) that addresses the previous limitations and simplifies the design of task-and-architecture co-adaptation (TACA) in robotic applications. ROSA is a modular knowledge-based managing subsystem that solves TACA by providing a knowledge model that can capture all the application-specific knowledge required for the adaptation logic, and by reasoning uniquely about the captured knowledge at runtime to decide when and how the robotic system should adapt. This work provides a ROS 2-based open-source reference implementation of ROSA and demonstrate its feasibility and performance in an underwater robotics application. The experimental evaluation highlights the advantages of using ROSA to develop self-adaptive robotic systems in respect to reusability and development effort.
-
Attachments
- PDF {{zotero-imported-file JLRJW6PI, "Silva et al. - 2023 - SUAVE an exemplar for self-adaptive underwater vehicles.PDF"}}