Combined Task and Action Learning from Human Demonstrations for Mobile Manipulation Applications

by   Tim Welschehold, et al.

Learning from demonstrations is a promising paradigm for transferring knowledge to robots. However, learning mobile manipulation tasks directly from a human teacher is a complex problem as it requires learning models of both the overall task goal and of the underlying actions. Additionally, learning from a small number of demonstrations often introduces ambiguity with respect to the intention of the teacher, making it challenging to commit to one model for generalizing the task to new settings. In this paper, we present an approach to learning flexible mobile manipulation action models and task goal representations from teacher demonstrations. Our action models enable the robot to consider different likely outcomes of each action and to generate feasible trajectories for achieving them. Accordingly, we leverage a probabilistic framework based on Monte Carlo tree search to compute sequences of feasible actions imitating the teacher intention in new settings without requiring the teacher to specify an explicit goal state. We demonstrate the effectiveness of our approach in complex tasks carried out in real-world settings.



There are no comments yet.


page 1

page 3

page 7


Gaussian-Process-based Robot Learning from Demonstration

Endowed with higher levels of autonomy, robots are required to perform i...

Correct Me if I am Wrong: Interactive Learning for Robotic Manipulation

Learning to solve complex manipulation tasks from visual observations is...

Interactive Policy Learning through Confidence-Based Autonomy

We present Confidence-Based Autonomy (CBA), an interactive algorithm for...

Task-Adaptive Robot Learning from Demonstration under Replication with Gaussian Process Models

Learning from Demonstration (LfD) is a paradigm that allows robots to le...

Learning the Semantics of Manipulation Action

In this paper we present a formal computational framework for modeling m...

Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics

A key challenge in Imitation Learning (IL) is that optimal state actions...

Neural Task Success Classifiers for Robotic Manipulation from Few Real Demonstrations

Robots learning a new manipulation task from a small amount of demonstra...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.