Improving User Specifications for Robot Behavior through Active Preference Learning: Framework and Evaluation

07/24/2019
by   Nils Wilde, et al.
0

An important challenge in human robot interaction (HRI) is enabling non-expert users to specify complex tasks for autonomous robots. Recently, active preference learning has been applied in HRI to interactively shape a robot's behaviour. We study a framework where users specify constraints on allowable robot movements on a graphical interface, yielding a robot task specification. However, users may not be able to accurately assess the impact of such constraints on the performance of a robot. Thus, we revise the specification by iteratively presenting users with alternative solutions where some constraints might be violated, and learn about the importance of the constraints from the users' choices between these alternatives. We demonstrate our framework in a user study with a material transport task in an industrial facility. We show that nearly all users accept alternative solutions and thus obtain a revised specification through the learning process, and that the revision leads to a substantial improvement in robot performance. Further, the learning process reduces the variances between the specifications from different users and thus makes the specifications more similar. As a result, the users whose initial specifications had the largest impact on performance benefit the most from the interactive learning.

READ FULL TEXT

page 1

page 2

page 7

page 8

page 10

research
01/28/2019

Bayesian Active Learning for Collaborative Task Specification Using Equivalence Regions

Specifying complex task behaviours while ensuring good robot performance...
research
07/24/2023

Advancing Robot Autonomy for Long-Horizon Tasks

Autonomous robots have real-world applications in diverse fields, such a...
research
08/29/2023

Optometrist's Algorithm for Personalizing Robot-Human Handovers

With an increasing interest in human-robot collaboration, there is a nee...
research
05/08/2020

Active Preference Learning using Maximum Regret

We study active preference learning as a framework for intuitively speci...
research
08/26/2021

Improving HRI through robot architecture transparency

In recent years, an increased effort has been invested to improve the ca...
research
07/28/2022

Impactful Robots: Evaluating Visual and Audio Warnings to Help Users Brace for Impact in Human Robot Interaction

Wearable robotic devices have potential to assist and protect their user...
research
06/08/2020

From Demonstrations to Task-Space Specifications: Using Causal Analysis to Extract Rule Parameterization from Demonstrations

Learning models of user behaviour is an important problem that is broadl...

Please sign up or login with your details

Forgot password? Click here to reset