Imitation learning is a popular approach for teaching motor skills to robots. However, most
approaches focus on extracting policy parameters from execution traces alone (ie, motion …

Decision-making is challenging in robotics environments with continuous object-centric
states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches …

Imitation learning is an effective and safe technique to train robot policies in the real world
because it does not depend on an expensive random exploration process. However, due to …

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end
policy which can adapt to changes in the environment during execution. While goal …

In this work we propose a novel end-to-end imitation learning approach which combines
natural language, vision, and motion information to produce an abstract representation of a …

It is challenging for robots to solve tasks in environments with continuous state and action
spaces, long horizons, and sparse feedback. Hierarchical approaches such as task and …

In robotic domains featuring continuous state and action spaces, planning in long-horizon
task is fundamentally hard, even when the transition model is deterministic and known. One …

Semi-physical simulation refers to the real-time simulation of some physical objects
accessed in the loop of the simulation experiment system, which can greatly shorten the …

To carry out diverse tasks in everyday human environments, future robots must generalize
beyond the knowledge they are equipped with. However, despite recent advances in" end-to …

Humans have often relied on mimicking nature for solving various problems that we
encounter. Visuomotor Policy (VMP) is one such framework that is inspired by the human …