A Comparison of Remote Robot Teleoperation Interfaces for General Object Manipulation

Kent, David; Saldanha, Carl; Chernova, Sonia

doi:10.1145/2909824.3020249

Cited by 51 publications

(37 citation statements)

References 22 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the system is being used to develop and evaluate new algorithms for inverse kinematics, trajectory planning, control and cooperation with other mobile robots, and these results will be reported in future articles. References [56,57] are also important in this context. Husain et al [56] use depth data to segment an object from the background and track it moving within the workspace.…”

Section: Resultsmentioning

confidence: 99%

Vision-Based Assisted Tele-Operation of a Dual-Arm Hydraulically Actuated Robot for Pipe Cutting and Grasping in Nuclear Environments

et al. 2019

View full text Add to dashboard Cite

This article investigates visual servoing for a hydraulically actuated dual-arm robot, in which the user selects the object of interest from an on-screen image, whilst the computer control system implements via feedback control the required position and orientation of the manipulators.To improve on the current joystick direct tele-operation commonly used as standard in the nuclear industry, which is slow and requires extensive operator training, the proposed assisted tele-operation makes use of a single camera mounted on the robot. Focusing on pipe cutting as an example, the new system ensures that one manipulator automatically grasps the user-selected pipe, and appropriately positions the second for a cutting operation. Initial laboratory testing (using a plastic pipe) shows the efficacy of the approach for positioning the manipulators, and suggests that for both experienced and inexperienced users, the task is completed significantly faster than via tele-operation.

show abstract

Section: Resultsmentioning

confidence: 99%

Vision-Based Assisted Tele-Operation of a Dual-Arm Hydraulically Actuated Robot for Pipe Cutting and Grasping in Nuclear Environments

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In addition, specific scenarios will require the presence of other features. Scenarios involving repetition or complex tasks are likely to benefit from having input methods that are facile (6), for instance to provide multiple knot tying demonstrations for LfD [29]. An easy to learn (7) input method may allow non-expert users to confidently (5) provide demonstrations for one-shot learning (e.g., [40]).…”

Section: Characterizing Input Methodsmentioning

confidence: 99%

“…Prior work has compared specific input devices for learning from demonstration [1]- [3] and for real-time control [4]- [6]. We look for other broad categories in the robotics literature that utilize demonstrations and list them as usage paradigms in Section III-A.…”

Section: Related Workmentioning

confidence: 99%

Characterizing Input Methods for Human-to-Robot Demonstrations

Praveena

Subramani

Mutlu

et al. 2019

2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Human demonstrations are important in a range of robotics applications, and are created with a variety of input methods. However, the design space for these input methods has not been extensively studied. In this paper, focusing on demonstrations of hand-scale object manipulation tasks to robot arms with two-finger grippers, we identify distinct usage paradigms in robotics that utilize human-to-robot demonstrations, extract abstract features that form a design space for input methods, and characterize existing input methods as well as a novel input method that we introduce, the instrumented tongs. We detail the design specifications for our method and present a user study that compares it against three common input methods: free-hand manipulation, kinesthetic guidance, and teleoperation. Study results show that instrumented tongs provide high quality demonstrations and a positive experience for the demonstrator while offering good correspondence to the target robot.

show abstract

“…Teleoperation mechanisms vary from game interfaces [26] to free-space positioning interfaces [20]. A comparison of various control interfaces shows that general purpose hardware is deficient while special purpose hardware is more accurate but is not widely available [19,26]. Virtual reality-based free-space controllers have recently been proposed both for data collection [23,39] and policy learning [40,43].…”

Section: Related Workmentioning

confidence: 99%

Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity

Mandlekar

Booher

Spero

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Large, richly annotated datasets have accelerated progress in fields such as computer vision and natural language processing, but replicating these successes in robotics has been challenging. While prior data collection methodologies such as self-supervision have resulted in large datasets, the data can have poor signal-to-noise ratio. By contrast, previous efforts to collect task demonstrations with humans provide better quality data, but they cannot reach the same data magnitude. Furthermore, neither approach places guarantees on the diversity of the data collected, in terms of solution strategies. In this work, we leverage and extend the RoboTurk platform to scale up data collection for robotic manipulation using remote teleoperation. The primary motivation for our platform is two-fold: (1) to address the shortcomings of prior work and increase the total quantity of manipulation data collected through human supervision by an order of magnitude without sacrificing the quality of the data and (2) to collect data on challenging manipulation tasks across several operators and observe a diverse set of emergent behaviors and solutions. We collected over 111 hours of robot manipulation data across 54 users and 3 challenging manipulation tasks in 1 week, resulting in the largest robot dataset collected via remote teleoperation. We evaluate the quality of our platform, the diversity of demonstrations in our dataset, and the utility of our dataset via quantitative and qualitative analysis. For additional results, supplementary videos, and to download our dataset, visit roboturk.stanford.edu/realrobotdataset

show abstract

A Comparison of Remote Robot Teleoperation Interfaces for General Object Manipulation

Cited by 51 publications

References 22 publications

Vision-Based Assisted Tele-Operation of a Dual-Arm Hydraulically Actuated Robot for Pipe Cutting and Grasping in Nuclear Environments

Vision-Based Assisted Tele-Operation of a Dual-Arm Hydraulically Actuated Robot for Pipe Cutting and Grasping in Nuclear Environments

Characterizing Input Methods for Human-to-Robot Demonstrations

Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity

Contact Info

Product

Resources

About