A Comprehensive Review of Endogenous EEG-Based BCIs for Dynamic Device Control

Abstract

Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) provide a novel approach for controlling external devices. BCI technologies can be important enabling technologies for people with severe mobility impairment. Endogenous paradigms, which depend on user-generated commands and do not need external stimuli, can provide intuitive control of external devices. This paper discusses BCIs to control various physical devices such as exoskeletons, wheelchairs, mobile robots, and robotic arms. These technologies must be able to navigate complex environments or execute fine motor movements. Brain control of these devices presents an intricate research problem that merges signal processing and classification techniques with control theory. In particular, obtaining strong classification performance for endogenous BCIs is challenging, and EEG decoder output signals can be unstable. These issues present myriad research questions that are discussed in this review paper. This review covers papers published until the end of 2021 that presented BCI-controlled dynamic devices. It discusses the devices controlled, EEG paradigms, shared control, stabilization of the EEG signal, traditional machine learning and deep learning techniques, and user experience. The paper concludes with a discussion of open questions and avenues for future work.

Keywords: brain–computer interface (BCI); brain–machine interface (BMI); control; electroencephalogram (EEG); endogenous; motor imagery (MI).

Figure 1

A summary of the paper selection process formatted using the template available at [6].

Figure 2

A year-by-year breakdown of the reviewed literature.

Figure 3

A pie chart showing a breakdown of all the different BCI-controlled devices in the literature reviewed.

Figure 4

A taxonomy of the shared-control approaches proposed in the reviewed literature.

Figure 5

Comparing different false-alarm approaches. The blue bars show the BCI classifier output at the previous time step, and the orange bars show the decision made at the current time step. The example is for a two-class problem in which A denotes the classifier label for one mental state and B is the label for the other state. Each mental state was related to a different movement in the dynamic device. During “no action” phases, movement of the device was paused. In this example, it was assumed that at the start, the BCI classifier was outputting in class A for a long period (more than eight consecutive samples). Four different approaches are presented, namely those by Chae et al. [73], Hortal et al. [74], Ai et al. [54] and Zhuang et al. [52].

Figure 6

A pie chart illustrating the proportion of studies that used traditional machine learning and deep learning techniques.

Figure 7

A bar plot showing the features used in machine learning systems.

Figure 8

A bar plot showing the classifiers used in machine learning systems with indications of the features used with each classifier group.

Figure 9

A histogram showing ranges of the number of subjects included in the studies reviewed. For each range, the right-hand number was included and the left-hand number was excluded.