Lecture

Learning Models for Belief-Driven Mobile Manipulation Tasks

Description

This lecture explores learning models for solving belief-driven mobile manipulation tasks in open environments. It covers topics such as continuous error checking, recovery, and actions like leaping, grasping, dragging, climbing, throwing, and stacking. The instructor presents a technical approach involving Aspect Transition Graphs, Active Belief Planner, and Landscape of Attractors. Additionally, the lecture discusses Intrinsically Motivated Structure Learning, habituation thresholds, and examples of stacking experiments.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.