A survey of robot learning from demonstration

Argall, Brenna; Chernova, Sonia; Veloso, Manuela; Browning, Brett

doi:10.1016/j.robot.2008.10.024

Cited by 2,662 publications

(1,777 citation statements)

References 56 publications

Supporting

Mentioning

1,761

Contrasting

Unclassified

Order By: Relevance

“…One invaluable implication of this work is the possibility of conducting novel work in the field of Learning from Demonstration (LfD) (Argall et al, 2009;Billing & Hellstrm, 2010). LfD itself focuses on enabling human non-expert users to teach robots new capabilities using various interactive teaching methods as opposed to explicit programming.…”

Section: Future Workmentioning

confidence: 99%

“…Nevertheless, there still is a large subset HRI studies which can take advantage of modern crowdsourcing techniques. While we do not try to enumerate all types of appropriate studies, we note that studies dealing with interface design, feedback, or testing particular types of Learning from Demonstration (Argall, Chernova, Veloso, & Browning, 2009) techniques are examples of types of studies that could be appropriate.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Robot Management System: A Framework for Conducting Human-Robot Interaction Studies Through Crowdsourcing

Toris¹,

Kent²,

Chernova³

2014

Journal of Human-Robot Interaction

Self Cite

View full text Add to dashboard Cite

Human-Robot Interaction (HRI) is a rapidly expanding field of study that focuses on allowing nonroboticist users to naturally and effectively interact with robots. The importance of conducting extensive user studies has become a fundamental component of HRI research; however, due to the nature of robotics research, such studies often become expensive, time consuming, and limited to constrained demographics. In this work, we present the Robot Management System (RMS), a novel framework for bringing robotic experiments to the web. We present a detailed description of our open-source system and describe an initial trial of the RMS as a means of conducting user studies. Using a series of navigation and manipulation tasks with a PR2 robot, we compare three user study conditions: users that are co-present with the robot, users that are recruited to the university laboratory but control the robot from a different room, and remote web-based users. Our findings show little statistical differences between usability patterns across these groups, validating the use of web-based crowdsourcing techniques for certain types of HRI evaluations.

show abstract

Section: Future Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Robot Management System: A Framework for Conducting Human-Robot Interaction Studies Through Crowdsourcing

Toris¹,

Kent²,

Chernova³

2014

Journal of Human-Robot Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…In dynamic scenarios, dynamic object properties such as velocities are included as well [2,3] but depending on the task and the objects that are involved, any object attribute can be added, e.g., color, shape, size. The robot perceives the world using a perceptual system possibly containing multiple sensors such as cameras and laser scanners.…”

Section: Introductionmentioning

confidence: 99%

Semantic world modeling using probabilistic multiple hypothesis anchoring

Elfring

Dries

Molengraft

et al. 2013

Robotics and Autonomous Systems

View full text Add to dashboard Cite

“…The step of perception of the demonstrated actions and the states of the world is accomplished by employing different sensing modalities, e.g., electro -magnetic sensors [5], inertial sensors [4], optical marker-based systems [6], vision cameras [7], etc. The focus of this work is on robot learning by using external form of task perception [8], i.e., the sensors are placed externally with respect to the demonstrating agent, as opposed to the perception modes that employ sensing devices mounted directly on the demonstrator's body. The external perceptibility systems relate to the use of vision cameras for observation of demonstrated tasks.…”

Section: Introductionmentioning

confidence: 99%