Limits...
Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction.

de Greeff J, Belpaeme T - PLoS ONE (2015)

Bottom Line: We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot.In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive.This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

View Article: PubMed Central - PubMed

Affiliation: Centre for Robotics and Neural Systems, Plymouth University, Plymouth, United Kingdom; Interactive Intelligence Group, Delft University of Technology, Delft, the Netherlands.

ABSTRACT
Social learning is a powerful method for cultural propagation of knowledge and skills relying on a complex interplay of learning strategies, social ecology and the human propensity for both learning and tutoring. Social learning has the potential to be an equally potent learning strategy for artificial systems and robots in specific. However, given the complexity and unstructured nature of social learning, implementing social machine learning proves to be a challenging problem. We study one particular aspect of social machine learning: that of offering social cues during the learning interaction. Specifically, we study whether people are sensitive to social cues offered by a learning robot, in a similar way to children's social bids for tutoring. We use a child-like social robot and a task in which the robot has to learn the meaning of words. For this a simple turn-based interaction is used, based on language games. Two conditions are tested: one in which the robot uses social means to invite a human teacher to provide information based on what the robot requires to fill gaps in its knowledge (i.e. expression of a learning preference); the other in which the robot does not provide social cues to communicate a learning preference. We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot. People also seem to form a "mental model" of the robot, tailoring the tutoring to the robot's performance as opposed to using simply random teaching. In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive. This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

No MeSH data available.


Social-responsiveness.The responsiveness to the robot’s social cues plotted against the robot learning performance. Straight lines depict a 33% baseline of following the robot’s preference by chance (blue) and the mean value of social responsiveness (green).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4589374&req=5

pone.0138061.g006: Social-responsiveness.The responsiveness to the robot’s social cues plotted against the robot learning performance. Straight lines depict a 33% baseline of following the robot’s preference by chance (blue) and the mean value of social responsiveness (green).

Mentions: To quantify the extent with which participants were responsive to the robot’s social cues, we define social-responsiveness as the number of times the teacher’s exemplar choice matched the preference of the robot, divided by the total number of guessing games played. In the non-social condition, the robot did not calculate a preferred topic, so we compare the social responsiveness of participants in the social condition to a 33% baseline of following the robot’s preference by chance. In the social condition, it is clear that participants to various degrees adhere to the robot’s preference. Mean social-responsiveness in the social condition is 56.3% (SD = 18%), which is significantly different from chance (one-sample t test with t(18) = 5.5645, p < 0.0001), see Fig 6. Furthermore, the figure depicts the social-responsiveness for each participant against the robot learning performance in the social condition. What can clearly be observed is the general tendency of high social-responsiveness combined with a relatively high robot learning performance. It is also clear though that a high social-responsiveness does not guarantee a high robot learning performance; indeed, only a weak correlation was found between the two (social condition, Pearson’s r = 0.09).


Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction.

de Greeff J, Belpaeme T - PLoS ONE (2015)

Social-responsiveness.The responsiveness to the robot’s social cues plotted against the robot learning performance. Straight lines depict a 33% baseline of following the robot’s preference by chance (blue) and the mean value of social responsiveness (green).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4589374&req=5

pone.0138061.g006: Social-responsiveness.The responsiveness to the robot’s social cues plotted against the robot learning performance. Straight lines depict a 33% baseline of following the robot’s preference by chance (blue) and the mean value of social responsiveness (green).
Mentions: To quantify the extent with which participants were responsive to the robot’s social cues, we define social-responsiveness as the number of times the teacher’s exemplar choice matched the preference of the robot, divided by the total number of guessing games played. In the non-social condition, the robot did not calculate a preferred topic, so we compare the social responsiveness of participants in the social condition to a 33% baseline of following the robot’s preference by chance. In the social condition, it is clear that participants to various degrees adhere to the robot’s preference. Mean social-responsiveness in the social condition is 56.3% (SD = 18%), which is significantly different from chance (one-sample t test with t(18) = 5.5645, p < 0.0001), see Fig 6. Furthermore, the figure depicts the social-responsiveness for each participant against the robot learning performance in the social condition. What can clearly be observed is the general tendency of high social-responsiveness combined with a relatively high robot learning performance. It is also clear though that a high social-responsiveness does not guarantee a high robot learning performance; indeed, only a weak correlation was found between the two (social condition, Pearson’s r = 0.09).

Bottom Line: We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot.In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive.This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

View Article: PubMed Central - PubMed

Affiliation: Centre for Robotics and Neural Systems, Plymouth University, Plymouth, United Kingdom; Interactive Intelligence Group, Delft University of Technology, Delft, the Netherlands.

ABSTRACT
Social learning is a powerful method for cultural propagation of knowledge and skills relying on a complex interplay of learning strategies, social ecology and the human propensity for both learning and tutoring. Social learning has the potential to be an equally potent learning strategy for artificial systems and robots in specific. However, given the complexity and unstructured nature of social learning, implementing social machine learning proves to be a challenging problem. We study one particular aspect of social machine learning: that of offering social cues during the learning interaction. Specifically, we study whether people are sensitive to social cues offered by a learning robot, in a similar way to children's social bids for tutoring. We use a child-like social robot and a task in which the robot has to learn the meaning of words. For this a simple turn-based interaction is used, based on language games. Two conditions are tested: one in which the robot uses social means to invite a human teacher to provide information based on what the robot requires to fill gaps in its knowledge (i.e. expression of a learning preference); the other in which the robot does not provide social cues to communicate a learning preference. We observe that conveying a learning preference through the use of social cues results in better and faster learning by the robot. People also seem to form a "mental model" of the robot, tailoring the tutoring to the robot's performance as opposed to using simply random teaching. In addition, the social learning shows a clear gender effect with female participants being responsive to the robot's bids, while male teachers appear to be less receptive. This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.

No MeSH data available.