Real-time vibrotactile pattern generation and identification using discrete event-driven feedback

Abstract

This study assesses human identification of vibrotactile patterns by using real-time discrete event-driven feedback. Previously acquired force and bend sensor data from a robotic hand were used to predict movement-type (stationary, flexion, contact, extension, release) and object-type (no object, hard object, soft object) states by using decision tree (DT) algorithms implemented in a field-programmable gate array (FPGA). Six able-bodied humans performed a 2- and 3-step sequential pattern recognition task in which state transitions were signaled as vibrotactile feedback. The stimuli were generated according to predicted classes represented by two frequencies (F1: 80 Hz, F2: 180 Hz) and two magnitudes (M1: low, M2: high) calibrated psychophysically for each participant; and they were applied by two actuators (Haptuators) placed on upper arms. A soft/hard object was mapped to F1/F2; and manipulating it with low/high force was assigned to M1/M2 in the left actuator. On the other hand, flexion/extension movement was mapped to F1/F2 in the right actuator, with movement in air as M1 and during object manipulation as M2. DT algorithm performed better for the object-type (97%) than the movement-type (88%) classification in real time. Participants could recognize feedback associated with 14 discrete-event sequences with low-to-medium accuracy. The performance was higher (76 ± 9% recall, 76 ± 17% precision, 78 ± 4% accuracy) for recognizing any one event in the sequences. The results show that FPGA implementation of classification for discrete event-driven vibrotactile feedback can be feasible in haptic devices with additional cues in the physical context.

Keywords:

• Vibrotactile feedback
• somatosensory
• tactile sensor
• proprioceptive sensor
• decision tree
• FPGA
• discrete event-driven sensory feedback control

Acknowledgements

The authors thank İpek Karakuş and David Alejandro Vargas for their help in discussions on machine learning and FPGA coding.

Author contributions

İ. E. and B. G. conceived and designed research. İ. E. performed the experiments, analysed data, and prepared the figures. Both authors interpreted results of experiments, drafted manuscript, edited and revised the manuscript, and approved final version of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by Council of Higher Education 100/2000 program to İ. E. and by TÜBİTAK [Grant 117F481] within European Union’s FLAG-ERA JTC 2017 project GRAFIN to B.G.