Teleoperation for a ball-catching task with significant dynamics

Smith, Christian; Bratt, Mattias; Christensen, Henrik I.

doi:10.1016/j.neunet.2008.03.011

Cited by 12 publications

(13 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our formalism and analysis build on machine learning, control theory, and human-robot interaction to provide insight into shared control. We suggest possible challenges, as well as opportunities that could arise from the tight interaction between the robot and the user: adaptation to the context and (Rosenberg, 1993) no (Marayong et al, 2003) (Debus et al, 2000) (You and Hauser, 2011) (Kim et al, 2011) (Marayong et al, 2002) (Leeper et al, 2012) predefined behaviors (Demiris and Hayes, 2002) (Fagg et al, 2004) (Crandall and Goodrich, 2002) no (Aigner and McCarragher, 1997) (Gerdes and Rossetter, 2001) (You and Hauser, 2011) (Marayong et al, 2002) predefined behaviors (Yu et al, 2005) no (Kofman et al, 2005) (Shen et al, 2004) (Smith et al, 2008) predefined behaviors MPC/minimum-jerk (Anderson et al, 2010) (Loizou and Kumar, 2007) (Weber et al, 2009) predefined behaviors (Aarno et al, 2005) (Yu et al, 2005) (Vasquez et al, 2005) fixed goals (2D) no (Ziebart et al, 2009) fully flexible (2D) no the user, predicting and expressing intent, and capitalizing on the user's reactions. These challenges and opportunities are not only applicable to shared control, but conceivably to humanrobot collaboration in general.…”

Section: Robot Predictionmentioning

confidence: 99%

A policy-blending formalism for shared control

Dragan

Srinivasa

2013

The International Journal of Robotics Research

298

312

View full text Add to dashboard Cite

Abstract-In shared control teleoperation, the robot assists the user in accomplishing the desired task, making teleoperation easier and more seamless. Rather than simply executing the user's input, which is hindered by the inadequacies of the interface, the robot attempts to predict the user's intent, and assists in accomplishing it. In this work, we are interested in the scientific underpinnings of assistance: we propose an intuitive formalism that captures assistance as policy blending, illustrate how some of the existing techniques for shared control instantiate it, and provide a principled analysis of its main components: prediction of user intent and its arbitration with the user input. We define the prediction problem, with foundations in Inverse Reinforcement Learning, discuss simplifying assumptions that make it tractable, and test these on data from users teleoperating a robotic manipulator. We define the arbitration problem from a control-theoretic perspective, and turn our attention to what users consider good arbitration. We conduct a user study that analyzes the effect of different factors on the performance of assistance, indicating that arbitration should be contextual: it should depend on the robot's confidence in itself and in the user, and even the particulars of the user. Based on the study, we discuss challenges and opportunities that a robot sharing the control with the user might face: adaptation to the context and the user, legibility of behavior, and the closed loop between prediction and user behavior.

show abstract

Section: Robot Predictionmentioning

confidence: 99%

A policy-blending formalism for shared control

Dragan

Srinivasa

2013

The International Journal of Robotics Research

298

312

View full text Add to dashboard Cite

show abstract

“…[1]- [6], [18] no [10], [11] predefined paths/behaviors [4], [6]- [8] no [12] predefined paths/behaviors [9], [20]- [22] no [13] predefined paths/behaviors [12], [14] predefined paths/behaviors [23] fixed environment, goals (2D) no [24] fully flexible (goal+policy) (2D) no the robot is able to generate a full policy for completing the task on its own, rather than an attractive/repulsive force or a constraint (e.g. [9], [20]).…”

Section: Methodsmentioning

confidence: 99%

“…Aside from work that classifies which one of a predefined set of paths or behaviors the user is currently engaging [10], [11], most work assumes the robot has access to the user's intent, e.g. that it knows what object to grasp and how (except in [22], which deals with time delays in ball catching by projecting the input forward in time using a minimum-jerk model). Predicting or recognizing intent has received a lot of attention outside of the teleoperation domain, dating back to high-level plan recognition [26].…”

Section: Methodsmentioning

confidence: 99%

Formalizing Assistive Teleoperation

Dragan

Srinivasa

2012

Robotics: Science and Systems VIII

107

View full text Add to dashboard Cite

Abstract-In assistive teleoperation, the robot helps the user accomplish the desired task, making teleoperation easier and more seamless. Rather than simply executing the user's input, which is hindered by the inadequacies of the interface, the robot attempts to predict the user's intent, and assists in accomplishing it. In this work, we are interested in the scientific underpinnings of assistance: we formalize assistance under the general framework of policy blending, show how previous work methods instantiate this formalism, and provide a principled analysis of its main components: prediction of user intent and its arbitration with the user input. We define the prediction problem, with foundations in Inverse Reinforcement Learning, discuss simplifying assumptions that make it tractable, and test these on data from users teleoperating a robotic manipulator under various circumstances. We propose that arbitration should be moderated by the confidence in the prediction. Our user study analyzes the effect of the arbitration type, together with the prediction correctness and the task difficulty, on the performance of assistance and the preferences of users.

show abstract

“…Thus, there is only one possible MJ trajectory for a given start and end, and it can be found by solving a simple system of linear equations. This is illustrated with an example of a human's reaching motion recorded from an experiment in [16] with the MJ trajectory superimposed, in Fig. 1.…”

Section: B Minimum Jerk Motion Modelmentioning

confidence: 99%

Wiimote robot control using human motion models

Smith

Christensen

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

As mass-market video game controllers have become more advanced, there has been a recent increase in interest for using these as intuitive and inexpensive control devices. In this paper we examine position control for a robot using a wiimote game controller. We show that human motion models can be used to achieve better precision than traditional tracking approaches, sufficient for simpler tasks. We also present an experiment that shows that very intuitive control can be achieved, as novice subjects can control a robot arm through simple tasks after just a few minutes of practice and minimal instructions.

show abstract

Teleoperation for a ball-catching task with significant dynamics

Cited by 12 publications

References 43 publications

A policy-blending formalism for shared control

A policy-blending formalism for shared control

Formalizing Assistive Teleoperation

Wiimote robot control using human motion models

Contact Info

Product

Resources

About