Teaching Human Teachers to Teach Robot Learners

Sena, Aran; Zhao, Yuchen; Howard, Matthew

doi:10.1109/icra.2018.8461194

Cited by 13 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effectiveness of this framework as a means of helping novices during LfD is then shown in two experiments with novice users, extending the work presented in (Sena et al, 2018). It is shown in these validation experiments that the evaluation and feedback tools derived from the proposed framework allow for improving teaching performance, in the order of a 180% improvement relative to unguided conditions.…”

Section: Introductionmentioning

confidence: 66%

Quantifying teaching behavior in robot learning from demonstration

Sena

Howard

2019

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

Learning from demonstration allows for rapid deployment of robot manipulators to a great many tasks, by relying on a person showing the robot what to do rather than programming it. While this approach provides many opportunities, measuring, evaluating and improving the person's teaching ability has remained largely unexplored in robot manipulation research. To this end, a model for learning from demonstration is presented here which incorporates the teacher's understanding of, and influence on, the learner. The proposed model is used to clarify the teacher's objectives during learning from demonstration, providing new views on how teaching failures and efficiency can be defined. The benefit of this approach is shown in two experiments (n = 30 and n = 36, respectively), which highlight the difficulty teachers have in providing effective demonstrations, and show how ∼ 169 − 180% improvement in teaching efficiency can be achieved through evaluation and feedback shaped by the proposed framework, relative to unguided teaching.

show abstract

Section: Introductionmentioning

confidence: 66%

Quantifying teaching behavior in robot learning from demonstration

Sena

Howard

2019

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Defining a "good" demonstration is a difficult task. There are existing attempts to measure "goodness" by coverage in case of free space motions Sena et al (2018), but for incontact tasks there exists no current work. In the experiments we simply explained the demonstrators how an informative demonstrations should be performed-the development of a general metric of informativeness for compliant motion demonstrations is outside the scope of this paper and an interesting direction for future research.…”

Section: Discussionmentioning

confidence: 99%

Imitation learning-based framework for learning 6-D linear compliant motions

2021

View full text Add to dashboard Cite

We present a novel method for learning from demonstration 6-D tasks that can be modeled as a sequence of linear motions and compliances. The focus of this paper is the learning of a single linear primitive, many of which can be sequenced to perform more complex tasks. The presented method learns from demonstrations how to take advantage of mechanical gradients in in-contact tasks, such as assembly, both for translations and rotations, without any prior information. The method assumes there exists a desired linear direction in 6-D which, if followed by the manipulator, leads the robot’s end-effector to the goal area shown in the demonstration, either in free space or by leveraging contact through compliance. First, demonstrations are gathered where the teacher explicitly shows the robot how the mechanical gradients can be used as guidance towards the goal. From the demonstrations, a set of directions is computed which would result in the observed motion at each timestep during a demonstration of a single primitive. By observing which direction is included in all these sets, we find a single desired direction which can reproduce the demonstrated motion. Finding the number of compliant axes and their directions in both rotation and translation is based on the assumption that in the presence of a desired direction of motion, all other observed motion is caused by the contact force of the environment, signalling the need for compliance. We evaluate the method on a KUKA LWR4+ robot with test setups imitating typical tasks where a human would use compliance to cope with positional uncertainty. Results show that the method can successfully learn and reproduce compliant motions by taking advantage of the geometry of the task, therefore reducing the need for localization accuracy.

show abstract

“…Fryer and Boyee (2016) observed that while it is clear that teachers are able to play a supportive role, studies have yet to examine the teacher's influence on students' motivation in compulsory learning contexts. Other factor according may be the teacher's lack of prior experience (novice) (Sena et al, 2018); and lack of preparation and confidence (Savitz et al, 2019). On the contrary, the ADM students observed that their teachers moderately show appropriate behavior even during unguarded moments and applies knowledge on social learning in dealing with them.…”

Section: Level Of Implementation Of Alternative Delivery Mode (Adm) When Analyzed In Terms Of Social Regard For Learningmentioning

confidence: 99%

Alternative Delivery Mode (Adm) Program Delivery and Performance of Students

Lucero¹

2020

EJOE

View full text Add to dashboard Cite

Alternative Delivery Mode (ADM) of instruction had become an option of schools, parents, and learners to access education. Despite its implementation for several years, research on its delivery and students’ academic performance was not endeavored. Hence, this study was conducted to determine the relationship of Alternative Delivery Mode (ADM) program and performance of the students. The respondents of the study were 30 students from nine elementary schools in the Division of Digos, Davao del Sur. Results showed that most of the respondents enrolled in the Alternative Delivery Mode (ADM) were male, at age 11, and were laborers. Most of them were low performers. The respondents rated the Alternative Delivery Mode (ADM) implementation as moderate. It further revealed that there was no significant difference in the level of implementation of Alternative Delivery Mode in terms of gender and age but it showed significant relationship between the level of implementation of the program and the performance of the students. Intensification of Alternative Delivery Mode (ADM) was recommended. Article visualizations:<img src="/-counters-/edu_01/0720/a.php" alt="Hit counter" />

show abstract

Teaching Human Teachers to Teach Robot Learners

Cited by 13 publications

References 12 publications

Quantifying teaching behavior in robot learning from demonstration

Quantifying teaching behavior in robot learning from demonstration

Imitation learning-based framework for learning 6-D linear compliant motions

Alternative Delivery Mode (Adm) Program Delivery and Performance of Students

Contact Info

Product

Resources

About