Authors: (1) Ruohan Zhang, Department of Computer Science, Stanford University, Institute for Human-Centered AI (HAI), Stanford University & Equally contributed; zharu@stanford.edu; (2) Sharon Lee, Department of Computer Science, Stanford University & Equally contributed; zharu@stanford.edu; (3) Minjune Hwang, Department of Computer Science, Stanford University & Equally contributed; zharu@stanford.edu; (4) Ayano Hiranaka, Department of Mechanical Engineering, Stanford University & Equally contributed; zharu@stanford.edu; (5) Chen Wang, Department of Computer Science, Stanford University; (6) Wensi Ai, Department of Computer Science, Stanford University; (7) Jin Jie Ryan Tan, Department of Computer Science, Stanford University; (8) Shreya Gupta, Department of Computer Science, Stanford University; (9) Yilun Hao, Department of Computer Science, Stanford University; (10) Ruohan Gao, Department of Computer Science, Stanford University; (11) Anthony Norcia, Department of Psychology, Stanford University (12) Li Fei-Fei, 1Department of Computer Science, Stanford University & Institute for Human-Centered AI (HAI), Stanford University; (13) Jiajun Wu, Department of Computer Science, Stanford University & Institute for Human-Centered AI (HAI), Stanford University. Table of Links Abstract & Introduction Brain-Robot Interface (BRI): Background The NOIR System Experiments Results Conclusion, Limitations, and Ethical Concerns Acknowledgments & References Appendix 1: Questions and Answers about NOIR Appendix 2: Comparison between Different Brain Recording Devices Appendix 3: System Setup Appendix 4: Task Definitions Appendix 5: Experimental Procedure Appendix 6: Decoding Algorithms Details Appendix 7: Robot Learning Algorithm Details Appendix 6: Decoding Algorithms Details For both SSVEP and MI, we select a subset of channels and discard the signals from the rest, as shown in Figure 6. They correspond to the visual cortex for SSVEP, and the motor and visual areas for MI (with peripheral areas). For muscle tension (jaw clenching), we retain all channels. . To predict the object of interest, we apply Canonical Correlation Analysis (CCA) as shown in [77] to the collected SSVEP data. As each potential object of interest is flashing at a different frequency, we are able to generate reference signals Yf for each frequency fi: SSVEP n where f is the sampling frequency and N is the number of samples. s s By calculating the maximum correlation ρfn for each frequency f used for potential objects of interest, we are then able to predict the output class by finding argmax (ρf ) and matching the result to the object of interest with that frequency. n fn n Furthermore, we are able to return a list of predicted objects of interest in descending order of likelihood by matching each object to a list of descending maximum correlations ρf . n Motor imagery. To perform MI classification, we first band-pass filter the data between 8Hz - 30Hz, as that is the frequency range that includes the µ-band and β-band signals relevant to MI. The data is then transformed using the Common Spatial Pattern (CSP) algorithm. CSP is a linear transformation technique that applies a rotation to the data to orthogonalize the components where the over-timestep variance of the data differs the most across classes. We can then use the logvariance of each time series after rotation as features and perform QDA. Thereafter, we extract features by taking the normalized variance of this transformed data (called “CSP-space data”). We then perform Quadratic Discriminant Analysis (QDA) on this data. To calculate our calibration accuracy, we perform K-fold cross validation with KCV = 4, but we use the entire calibrate dataset to fit the classifier for deployment at task-time. Facial muscle tension results in a very significant high-variance signal across almost all channels that is very detectable using simple variance-based threshold filters without having to perform any frequency filters. Recall that we record three 500ms-long trials for each class (“Rest”, “Clench”). In short, for each of the calibration time-series, we take the variance of the channel with the median variance; call this variance m. Then, we just take the mid-point between the maximum m between the rest samples, and the minimum m between the clench samples, and have this be our threshold variance level. This paper is under CC 4.0 license. available on arxiv

NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities: Appendix 7

NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities: Appendix 5

EScholar Technologies

Too Long; Didn't Read

Make resilience your competitive advantage

NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities: Appendix 6

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

Smart Cards, IPv6 Packets, and the Future of Post-Quantum Security

Human-Centric Evaluation of NOIR in Real-world Tasks

Neural Signal Operated Intelligent Robots: Conclusion, Limitations, & Ethical Concerns

Decoding Human Intentions: NOIR's Performance and Learning Algorithms

NOIR: Neural Signal Operated Intelligent Robots: Acknowledgments & References

Smart Cards, IPv6 Packets, and the Future of Post-Quantum Security

Human-Centric Evaluation of NOIR in Real-world Tasks

Neural Signal Operated Intelligent Robots: Conclusion, Limitations, & Ethical Concerns

Decoding Human Intentions: NOIR's Performance and Learning Algorithms

NOIR: Neural Signal Operated Intelligent Robots: Acknowledgments & References

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps