The next generation of robots are going to work much more closely with humans and with other robots, and interact significantly with the environment around them. As a result, the key paradigms are shifting from isolated decision-making systems to one that involves shared control – with significant autonomy devolved to the robot platform; and end-users in the loop making only high-level decisions.
This talk will introduce technologies ranging from robust multi-modal sensing and shared representations to compliant actuation and scalable machine-learning techniques for real-time learning and adaptation, enabling us to reap the benefits of increased autonomy while still feeling securely in control.
This also raises some fundamental questions; e.g., while the robots are ready to share control, what is the optimal trade-off between autonomy and control with which we are comfortable?
Domains where this debate is relevant include self-driving cars, mining, shared manufacturing, exoskeletons for rehabilitation, active prosthetics, large-scale scheduling (e.g., transport) systems, as well as oil and gas exploration, to list a few.