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

arXiv: https://arxiv.org/abs/1907.10412 · HTML: https://mlsanity.com/paper/1907.10412/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [Learning Reward Functions from Scale Feedback](https://mlsanity.com/paper/2110.00284/) (2021)
- [Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstration](https://mlsanity.com/paper/2412.14309/) (2024)
- [Reward Learning with Trees: Methods and Evaluation](https://mlsanity.com/paper/2210.01007/) (2022)
- [Enhancing Goal Inference via Correction Timing](https://mlsanity.com/paper/2602.18603/) (2026)
- [Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2305.16924/) (2023)
- [On the Effect of Robot Errors on Human Teaching Dynamics](https://mlsanity.com/paper/2409.09827/) (2024)
- [Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration](https://mlsanity.com/paper/2609.13982/) (2026)

## Abstract (arXiv)

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 behavior. 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.