Robot Talk Episode 121 – Adaptable robots for the house, with Lerrel Pinto

Claire chatted to Lerrel Pinto from New York University about utilizing machine studying to coach robots to adapt to new environments.

Lerrel Pinto is an Assistant Professor of Computer Science at New York University (NYU). His analysis is aimed toward getting robots to generalize and adapt within the messy world we stay in. His lab focuses broadly on robotic studying and choice making, with an emphasis on large-scale studying (each knowledge and fashions); illustration studying for sensory knowledge; growing algorithms to mannequin actions and behavior; reinforcement studying for adapting to new situations; and constructing open-source, inexpensive robots.