Comparing a Graphical User Interface, Hand Gestures and Controller in Virtual Reality for Robot Teleoperation

Chen, Jialin; Moemeni, Armaghan; Caleb-Solly, Praminda

doi:10.1145/3568294.3580165

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The control scheme that maps a user’s motion to the robot’s motion can only be designed based on the information that the control interface can provide. The most common control interfaces fall into three categories: video-game-style controllers with buttons and joysticks, master/puppet systems, and direct, human-as-the-master master/puppet systems ( Gong et al, 2019 ; Li et al, 2019 ; Chen et al, 2023 ). These three kinds of systems each capture different kinds of information and are suitable for particular robots.…”

Section: Related Workmentioning

confidence: 99%

Clustering user preferences for personalized teleoperation control schemes via trajectory similarity analysis

Molnar,

Agrawal,

Chernova

2024

Front. Robot. AI

View full text Add to dashboard Cite

Successful operation of a teleoperated robot depends on a well-designed control scheme to translate human motion into robot motion; however, a single control scheme may not be suitable for all users. On the other hand, individual personalization of control schemes may be infeasible for designers to produce. In this paper, we present a method by which users may be classified into groups with mutually compatible control scheme preferences. Users are asked to demonstrate freehand motions to control a simulated robot in a virtual reality environment. Hand pose data is captured and compared with other users using SLAM trajectory similarity analysis techniques. The resulting pairwise trajectory error metrics are used to cluster participants based on their control motions, without foreknowledge of the number or types of control scheme preferences that may exist. The clusters identified for two different robots shows that a small number of clusters form stably for each case, each with its own control scheme paradigm. Survey data from participants validates that the clusters identified through this method correspond to the participants’ control scheme rationales, and also identify nuances in participant control scheme descriptions that may not be obvious to designers relying only on participant explanations of their preferences.

show abstract

Section: Related Workmentioning

confidence: 99%

Clustering user preferences for personalized teleoperation control schemes via trajectory similarity analysis

Molnar,

Agrawal,

Chernova

2024

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…V ISUAL SLAM (Simultaneous Localization and Mapping) techniques provide compelling solutions for environment awareness and self-localization for cyber-physical systems and have been applied in areas such as augmented reality (AR), robot navigation [1], robot-object interaction [2], and human-robot interaction [3]. VSLAM enables the tracking of movement in physical systems, such as robots, based on changes in the visible environment.…”

Section: Introductionmentioning

confidence: 99%

RDSP-SLAM: Robust Object-Aware SLAM Based on Deep Shape Priors

Okonkwo,

Yang,

Sun

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Object-aware systems such as Deep Shape prior SLAM (DSP-SLAM), provide a feasible technique for creating environment sparse maps , while representing scene objects as complete 3D models. Such systems provide a compelling solution for improving the intelligence of care robots and enriching the user experience in augmented (AR) applications. However, owing to the abrupt and unpredictable movements exhibited by users during AR engagements and real-time robot responses to changes in situations and commands, the robustness and speed of sensor data processing are imperative. DSP-SLAM suffers from a low-performance speed of 10 -15 fps, though it is based on ORB-SLAM2 which can run at 30 fps. This is mainly because the instance segmentation approach has an average latency of 53ms(18.86fps). To improve tracking robustness, keyframes must be processed at a fast rate. We use a state-of-the-art one-stage deep learning detector, which significantly reduces the wait time for detection-based data association during keyframe creation, and finally present Robust Deep Shape Prior SLAM (RDSP-SLAM). The results show that segmentation was performed at 20ms (50fps), while the object 3D reconstruction quality is the same as that of DSP-SLAM. RDSP-SLAM accepts RGB sequential images at 30fps and tracks them at a mean latency of 38fps.

show abstract