Automatic relational scene representation for safe robotic manipulation tasks
2013 (English)Conference paper (Refereed)
In this paper, we propose a new approach forautomatically building symbolic relational descriptions of staticconfigurations of objects to be manipulated by a robotic system.The main goal of our work is to provide advanced cognitiveabilities for such robotic systems to make them more aware ofthe outcome of their actions. We describe how such symbolicrelations are automatically extracted for configurations ofbox-shaped objects using notions from geometry and staticequilibrium in classical mechanics. We also present extensivesimulation results as well as some real-world experiments aimedat verifying the output of the proposed approach.
Place, publisher, year, edition, pages
Robotics Computer Science
Research subject Computer Science
IdentifiersURN: urn:nbn:se:oru:diva-32395OAI: oai:DiVA.org:oru-32395DiVA: diva2:664340
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)