Benchmarking dexterous dual-arm/hand robotic manipulation

Abstract

DEXMART is a European large-scale integrating project (IP) funded in the Seventh Framework Programme. The acronym stands for DEXterous and autonomous dual-arm/hand robotic manipulation with sMART sensory-motor skills: A bridge from natural to artificial cognition. The project is focused on artificial systems reproducing smart sensory-motor human skills, which operate in unstructured real-world environments. The emphasis is on manipulation capabilities achieved by dexterous and autonomous, and also human aware dual arm/hand robotic systems. The challenge is to allow a dual-arm robot including two multi-fingered redundant hands to grasp and manipulate the same objects used by human beings. The objects shall be allowed to have different shape, dimension, and weight. As compared to research and development on humanoid robots in Asia, the focus in Europe is rather on useful service tasks than pure social entertainment. Applications of robot companions range from a helper in family homes to executing tasks in offices, public environments and in professional services. Another important application area is the assistance to elderly and mobility-impaired persons that could be helped to achieve some independence from full time caring personnel. For this scenario the robot has to reach almost the same manipulation skills as a human being. The realisation of a truly dexterous and autonomous dual-arm/hand manipulation system is still an open research issue: bimanual manipulation is such a complex task combining different strategies, constraints, goals, advanced sensing and actuating technologies, requiring new concepts and design of artificial cognitive systems. In this context the question is raised how to measure and evaluate the progress of one’s own research and how to compare the results with others. This is especially difficult if one wishes to evaluate the performance of real, physical, intelligent robot systems interacting with the real world.