Real-Time Robot Gesture Control Using Online Feedback Data with Multi-tracking Capture System

This study uses a Vicon system, a high-speed accurate marker-based motion capture system aiming to develop a wireless low-latency gesture control method that requires no hardware development and no on-board power source. A novel control is designed to track a rigid-body object’s motion in the workspace and translate it to robot control signals. The system has five main components: a host PC with a Vicon software named Tracker, a set of eight Vicon Vantage V8 infrared cameras, a client PC that receives Tracker’s broadcasted data over the Ethernet, a robot model named youBot provided by KUKA, and a rigid-body object that will act as the gesture controller. Using an Application Programming Interface (API) called DataStream, it is successfully obtained the pose (position and orientation) of the rigid-body object and processed it to remotely control the KUKA youBot robot with high accuracy and no recognizable latency. Although it is similar to a combination of accelerometer-based and gyroscope-based controllers, the gesture controller requires no specific hardware besides a set of retro-reflective markers for tracking purposes. The proposed control method proves beneficial during the robotics prototyping phase, where different control mechanisms can be replicated and tested within the motion capture system’s range before deciding the best one for the target application. Furthermore, the robot’s odometry can also be tracked during testing, making a motion capture system a valuable tool for the evaluation of motion control.