Predicting Motor Intentions with Closed-Loop Brain-Computer Interfaces
We present two studies in which brain-computer interfaces (BCIs) used two related EEG signals, the readiness potential (RP) and the lateralized readiness potential (LRP), in order to predict and feed back motor intentions in real-time. In each of the studies, the experimental task was designed as a game that the subjects played against the BCI. In one of the experiments, subjects played a “duel” game against the BCI. They were challenged to perform spontaneous button presses but to withhold any movement when interrupted by a stop signal. This stop signal was controlled by the BCI that had been trained to predict movements by detecting the occurrence of RPs in the ongoing EEG. In the other experiment, participants played a “matching pennies” game. They won a point if they raised a different hand than the opponent at the end of a countdown and lost a point otherwise. The opponent was played by the BCI, who had been trained to predict from the LRP in the ongoing EEG which hand the subject would move at the end of the countdown. Hence, in both experiments a key feature of the BCI was its closed-loop nature, that is the ability to predict the motor intention in real-time and provide an immediate feedback of the prediction to the subject. In both experiments, prediction accuracies of the BCI were substantially higher compared to random predictions, thereby demonstrating the success of this approach. This allows researchers to use BCIs as research tools to address questions from cognitive neuroscience and provide new insights into the coupling of motor preparatory signals and the corresponding actions.
This work was supported by the Bernstein Focus: Neurotechnology from the German Federal Ministry of Education and Research (BMBF grant 01GQ0850), by the Bernstein Computational Neuroscience Program (BMBF grant 01GQ1001C), the Research Training Group “Sensory Computation in Neural Systems” (GRK 1589/1-2), the Collaborative Research Center “Volition and Cognitive Control: Mechanisms, Modulations, Dysfunctions” (SFB 940/1) and the German Research Foundation (DFG grants EXC 257 and KFO 247).
- 1.Allison BZ, Dunne S, Leeb R, Millán JDR, Nijholt A (2012) Towards practical brain-computer interfaces: bridging the gap from research to realworld applications. Springer Science & Business Media, HeidelbergGoogle Scholar
- 5.Blankertz B, Acqualagna L, Dähne S, Haufe S, Schultze-Kraft M, Sturm I, U2¢umlic M, Wenzel MA, Curio G, Müller K-R (2016) The Berlin brain-computer interface: progress beyond communication and control. Front Neurosci 10:530Google Scholar
- 7.Blankertz B, Dornhege G, Lemm S, Krauledat M, Curio G, Müller K-R (2006) The Berlin brain-computer interface: machine learning based detection of user specific brain states. J UCS 12(6):581–607Google Scholar
- 11.Brunia CH, Voorn FJ, Berger MP (1985). Movement related slow potentials. II. A contrast between finger and foot movements in left-handed subjects. Electroencephalogr Clin Neurophysiol 60:135–145Google Scholar
- 12.Brunner C, Birbaumer N, Blankertz B, Guger C, Kübler A, Mattia D, del R. Millán J, Miralles F, Nijholt A, Opisso E, Ramsey N, Salomon P, Müller-Putz GR (2015). BNCI Horizon 2020: towards a roadmap for the BCI community. Brain Comput Interfaces 2(1):1–10Google Scholar
- 17.Haufe S, Treder MS, Gugler MF, Sagebaum M, Curio G, Blankertz B (2011) EEG potentials predict upcoming emergency brakings during simulated driving. J Neural Eng 8(5):056001Google Scholar
- 19.Kohlmorgen J, Dornhege G, Braun M, Blankertz B, Müller K-R, Curio G, Hagemann K, Bruns A, Schrauf M, Kincses W (2007) Improving human performance in a real operating environment through real-time mental workload detection. In: Dornhege G, del R. Millán J, Hinterberger T, McFarland D, Müller K-R (eds) Toward brain-computer interfacing. MIT press, Cambridge, MA, pp 409–422Google Scholar
- 21.Libet B, Gleason CA, Wright EW, Pearl DK (1983) Time of conscious intention to act in relation to onset of cerebral activity (readiness-potential). The unconscious initiation of a freely voluntary act. Brain J Neurol 106(3):623–642Google Scholar
- 22.Maoz U, Ye S, Ross IB, Mamelak AN, Koch C (2012) Predicting action content on-line and in real time before action onset - an intracranial human study. In: Bartlett PL, Pereira FCN, Burges CJC, Bottou L, Weinberger KQ (eds) NIPS, pp 881–889Google Scholar
- 24.Naumann L, Schultze-Kraft M, Dähne S, Blankertz B (2017) Prediction of difficulty levels in video games from ongoing EEG. In: Gamberini L, Spagnolli A, Jacucci G, Blankertz B, Freeman J (eds) Symbiotic interaction, vol 9961. Springer International Publishing, Cham, pp 125–136Google Scholar
- 26.Schultze-Kraft M, Birman D, Rusconi M, Allefeld C, Görgen K, Dähne S, Blankertz B, Haynes J-D (2016a) The point of no return in vetoing self-initiated movements. Proc Nat Acad Sci 113(4):1080–1085Google Scholar
- 28.Wolpaw J, Wolpaw EW (2012) Brain-computer interfaces: principles and practice. OUP, USAGoogle Scholar