Areas of Research

Developing the algorithms, data, and hardware needed for robots to dynamically manipulate physical objects and systems to perform useful tasks, such as assembly, repair and transport. Our research is aimed at going beyond the static grasping and manipulation that currently dominates the field.

To expand the tasks robots can do autonomously, we are exploring performance of long-horizon tasks through composition of natural dynamic behavior elements. Our approach uses reinforcement learning for control, high-level direction by AI algorithms, incremental learning of new behavior, and adaptation to novel environments.

Today's AI models struggle to transfer learned skills to new physical tasks, especially those requiring precise force control and tight tolerances. RAI is developing foundation models that allow robots to accomplish complex physical tasks by combining data-driven learning techniques with principled models that embody the physicality of robotic systems.

Building advanced sensors that provide robots (including wheeled, humanoid, and quadruped designs) with a deep understanding of their surroundings. Combined with our robust mobility solutions, this capability will enable semantic navigation through a wide variety of environments, including factories, homes and cities.

Integrating robots into daily life will have an impact on human society. Our approach combines rigorous scientific research with a deep understanding of the socio-technical systems — including the social, legal, and ethical contexts — that shape the outcomes of robotics. Together, these efforts generate applicable insights for robots to seamlessly integrate into our world.