Enabling robots to perform complex manipulation tasks in open-world environments requires approaches to intelligence that bridge the traditional divide between symbolic and subsymbolic systems. Hybrid systems that combine reasoning over symbolic knowledge with probabilistically approximately correct inference over probability distributions promise to make robot manipulation actions generalizable, interpretable, and scalable to address real-world challenges. This talk explores how hybrid AI systems can enable robots to become not just capable agents, but also safe colleagues and companions for humans.
Benjamin Alt is Technical Director at the AICOR Lab at University of Bremen. He is collaborating with RBO in the Robotics Institute Germany (RIG) Technical Committee (TC) called Manipulate Anything, Anywhere, Anytime (MA3).
This talk is a collaboration between the Robotics and Biology Laboratory (RBO), the Robotics Institute Germany (RIG) and Science of Intelligence.