ZOOM LINK
Meeting ID: 995 9695 0090
Passcode: 153207

Embodied intelligence is the ultimate lifelong learning problem. If you had a robot in your home, you would likely ask it to do all sorts of varied chores, like setting the table for dinner, preparing lunch, and doing a load of laundry. The things you would ask it to do might also change over time, for example to use new appliances. You would want your robot to learn to do your chores and adapt to any changes quickly.

In this talk, I will explain how we can leverage various forms of modularity that are common in robotics to develop powerful lifelong learning mechanisms. My talk will then dive into two complementary algorithms that exploit these notions. The first approach operates in a pure reinforcement learning setting using modular neural networks. In this context, I will also introduce a new benchmark domain designed to assess the compositional capabilities of reinforcement learning methods for robots. The second method operates in a novel, more structured framework for task and motion planning systems, and I will show an example deploying these ideas on a physical Spot robot. I will close my talk by describing a vision for how we can construct the next generation of home assistant robots that leverage large-scale data to continually improve their own capabilities.

Hosted by Professor Laura Ray.