ViewVR: Visual Feedback Modes to Achieve Quality of VR-based Telemanipulation

TL;DR

ViewVR introduces an immersive teleoperation system that aligns the operator's head movements with camera viewpoints using a 2-DoF robotic head, integrated with a UR3 manipulator and a RealSense camera. The authors compare dynamic, head-driven visual feedback against a static head camera across three tasks, showing about a 15% increase in task success rate while highlighting increased mental workload and motion sickness as considerations. The system uses modular operator/robot subsystems, UDP-based high-frequency head control, and Unity-based streaming to minimize latency. They discuss limitations such as lack of tactile feedback and plan future work on additional cameras, higher head degrees of freedom, and imitation-learning from collected data.

Abstract

The paper focuses on an immersive teleoperation system that enhances operator's ability to actively perceive the robot's surroundings. A consumer-grade HTC Vive VR system was used to synchronize the operator's hand and head movements with a UR3 robot and a custom-built robotic head with two degrees of freedom (2-DoF). The system's usability, manipulation efficiency, and intuitiveness of control were evaluated in comparison with static head camera positioning across three distinct tasks. Code and other supplementary materials can be accessed by link: https://github.com/ErkhovArtem/ViewVR

Figures (7)

• Figure 1: Operator teaches robot to manipulate the objects with ViewVR.
• Figure 2: System architecture of ViewVR.
• Figure 3: 2-DoF Robotic head with Intel RealSense D455 Depth Camera.
• Figure : "Pick&place servo"
• Figure : "Pick&place servo"