Towards Intuitive to Use and Safe Robots

Abstract: Humans and robots are increasingly sharing common workspaces and tasks. In such a scenario, robots need to safely interact, collaborate and learn with humans. The human-robot interactive process may rely on cognitive interfaces (using gestures, human behaviour, anticipation) and physical interfaces featuring physical contact with the robot. Reinforcement learning and sim-to-real represent a step towards building autonomous robot learning with a higher-level understanding of the world. All the above interfaces require safe robots, robots that can avoid collisions with moving humans/objects in unstructured environments. The research challenges for the future will be discussed, as well as the issues related to the implementation of collaborative robotic systems in industry. Laboratory and industry use cases will be presented.

Speaker(s): Vince Socci,

Endicott, New York, United States, Virtual: https://events.vtools.ieee.org/m/293695