The Implementation Principles of a Multi-Channel Human-Machine Interface

   Different implementation principles of a multi-channel human-machine control interface for robotic complex or cyber-physical system are discussed. When an operator executes a command via the interface, type-I and type-II errors may occur during command recognition. The type I error occurs when the operator executes the command, but it is not recognized. The type II error occurs when the command is recognized although the operator does not execute it. In case of using several human-machine interaction channels, the problem of choosing the command to execute arises because of the presence of conflicting commands that can be recognized from different channels and in the same time require the same resources for execution. To solve this problem, two main principles have been determined. The first principle is to implement a decision-making system, which receives commands through control channels (interfaces), and makes a decision about the command to be  executed. The second principle is to choose and use only the most efficient control method. Examples of implementation of decision-making system and algorithm of choosing one control method are presented. To implement these algorithms, various criteria of interface efficiency are considered. Based on the generated confusion matrices, a number of experiments have been carried out to determine the number of errors in command recognition and to calculate type-I and type-II errors for each algorithm.

1. Gridnev A. A., Voznenko T. I., Chepin E. V. The decision-making system for a multi-channel robotic device control // Procedia computer science, 2018. V. 123. P. 149–154. doi: 10.1016/j.procs.2018.01.024

2. Voznenko T. I., Kudryavtsev K. Y. Algorithm for Multi-Channel Robotic Device Control Based on Minimizing Bayesian Risk // Procedia Computer Science, 2021. V. 190. P. 803–807. doi: 10.1016/j.procs.2021.06.093

3. Voznenko T. I., Gridnev A. A., Kudryavtsev K. Y., Chepin E. V. The Decomposition Method of Multichannel Control System Based on Extended BCI for a Robotic Wheelchair // Advances in Intelligent Systems and Computing, 2020. V. 948. P. 562–567. doi: 10.1007/978-3-030-25719-4_73

4. Voznenko T. I., Gridnev A. A., Chepin E. V., Kudryavtsev K. Y. The command interpretation in decomposition method of multi-channel control for a robotic device.// Procedia Computer Science, 2020. V. 169. P. 152–157. doi: 10.1016/j.procs.2020.02.127

5. Stehman S. V. Selecting and interpreting measures of thematic classification accuracy. //Remote Sensing of Environment, 1997. V. 62. № 1. P. 77–89. doi: 10.1016/S0034-4257(97)00083-7

6. Biswas K. K., Basu S. K. Gesture recognition using Microsoft Kinect® / In The 5th international conference on automation, robotics and applications, 2011. P. 100–103. doi: 10.1109/ICARA.2011.6144864

7. Abdelnasser H., Youssef M., Harras K. A. Wigest: A ubiquitous wifi-based gesture recognition system / In 2015 IEEE conference on computer communications (INFOCOM), 2015. P. 1472–1480. doi: 10.1109/INFOCOM.2015.7218525

8. Voznenko T. I., Gridnev A.A., Chepin E.V., Kudryavtsev K. Y. Comparison Between Coordinated Control and Interpretation Methods for Multi-channel Control of a Mobile Robotic Device.// Advances in Intelligent Systems and Computing, 2021. V. 1310. P. 558–564. doi: 10.1007/978-3-030-65596-9_68

9. Petrova A., Chepin, E., Voznenko T. Using Environmental Objects as Visual Stimuli in BCI-based Interaction System: Theoretical Approach.// Procedia Computer Science, 2021. V. 190. P. 670–677. doi: 10.1016/j.procs.2021.06.109