Abstract
If robots are going to be deployed to the real world, they need to be able to adapt to changes in both environment and task. This has turned out to be a very difficult challenge as robots often rely on rigid rules or one algorithm to solve everything. Humans, on the other hand, are able to switch between thinking fast and slow, according to the theory of dual process thinking from psychology. Why not give robots the same ability?
This talk will explore why incorporating both “fast” and “slow” decision processes into robotic systems matters, and how it might be achieved.
Bio
Tobias L?mo is a PhD fellow at RITMO, working on the PIRC project. His research draws inspiration from human psychology to develop smarter and more adaptable robots. He explores how robotics, deep learning, and reinforcement learning can be combined in novel ways, with a focus on creating integrated systems that improve robot performance and flexibility.