Investigating the Effects of Robot Engagement Communication on Learning from Demonstration
On the map: Offline RL and imitation learning from data → Robot learning from demonstration
Abstract (arXiv)
Robot Learning from Demonstration (RLfD) is a technique for robots to derive policies from instructors' examples. Although the reciprocal effects of student engagement on teacher behavior are widely recognized in the educational community, it is unclear whether the same phenomenon holds true for RLfD. To fill this gap, we first design three types of robot engagement behavior (attention, imitation, and a hybrid of the two) based on the learning literature. We then conduct, in a simulation environment, a within-subject user study to investigate the impact of different robot engagement cues on humans compared to a "without-engagement" condition. Results suggest that engagement communication significantly changes the human's estimation of the robots' capability and significantly raises their expectation towards the learning outcomes, even though we do not run actual learning algorithms in the experiments. Moreover, imitation behavior affects humans more than attention does in all metrics, while their combination has the most profound influences on humans. We also find that communicating engagement via imitation or the combined behavior significantly improve humans' perception towards the quality of demonstrations, even if all demonstrations are of the same quality.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. Builds on 6 of its 73 references that are in the map. First posted on arXiv 3 May 2020.
Builds on
6 of 73 references.
References · 6
- 2016Generative Adversarial Imitation Learningcited by 1,576
- 2014Interactive Policy Learning through Confidence-Based Autonomycited by 29
- 2016Comparing Human-Centric and Robot-Centric Sampling for Robot Deep Learning from Demonstrationscited by 17
- 2019Adversarial Imitation Learning from Incomplete Demonstrationscited by 16
- 2018Expressing Robot Incapabilitycited by 12
- 2019Estimating Emotional Intensity from Body Poses for Human-Robot Interactioncited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Active Robot Curriculum Learning from Online Human Demonstrations
- 2019Quantifying Teaching Behaviour in Robot Learning from Demonstration
- 2026Teaching Robot Policies to Humans Using Erroneous Examples ↗
- 2021Training Humans to Train Robots Dynamic Motor Skills
- 2022Quantifying Demonstration Quality for Robot Learning and Generalization
- 2025Training People to Reward Robots
- 2024Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstration
- 2023How Can Everyday Users Efficiently Teach Robots by Demonstrations?