Robots Atlas>ROBOTS ATLAS
Neurotechnologia

Passive BCI

2011ActivePublished: 27 July 2026Updated: 27 July 2026Published
Key innovation
Uses spontaneous, involuntary brain activity (mental states) to enrich human-machine interaction, instead of requiring deliberate control commands as in classic (active/reactive) BCIs.
Category
Neurotechnologia
Abstraction level
Paradigm
Operation level
ApplicationSystemData
Use cases
Neuroadaptive technology (adapting UI/UX to the user's state)Cognitive-load and attention monitoringError-perception (ErrP) detection for system correctionPersonalizing human-machine interactionOperator safety (fatigue/vigilance monitoring)Neuroadaptive AI learning

How it works

1) The brain signal (most often EEG) is recorded continuously, without requiring deliberate actions from the user. 2) Neurophysiological features correlated with mental states are extracted (e.g. band power, event-related potentials, ErrP). 3) A machine-learning model classifies the user's mental state in real time (e.g. high/low cognitive load, attention, error detection). 4) The result is passed to the system, which adapts its behavior (a neuroadaptive loop), e.g. simplifying the interface under high load or correcting behavior after detecting error perception.

Problem solved

Classic (active/reactive) BCIs require deliberate effort and commands, which is tiring and has low throughput. Passive BCI lets systems understand the user's state without extra burden, enabling natural, adaptive interaction.

Components

EEG acquisitionSignal input

Continuous recording of the brain signal (electrodes + amplifier), without requiring deliberate user actions.

Official

Mental-state classifierState detection

A machine-learning model recognizing mental states (load, attention, ErrP) in real time from signal features.

Official

Neuroadaptive loopSystem adaptation

A mechanism that uses the detected mental state to adapt the behavior of the system/interface.

Official

Implementation

Reference implementations
Zander Labs — SAMANAI / Zypher EEG suite
Zander Labs
Implementation pitfalls
Low EEG SNR and artifactsHigh

The EEG signal is weak and noisy; artifacts (motion, blinks, EMG) reduce reliability.

Fix:Filtering, artifact removal, good electrodes/contact, noise-robust learning.
Inter-individual variability / calibrationMedium

EEG patterns differ across people and sessions, often requiring per-user calibration.

Fix:Transfer learning, adaptive models, larger datasets.

Evolution

Original paper · 2011 · Journal of Neural Engineering, 8(2):025005, 2011 · Thorsten O. Zander
Towards passive brain–computer interfaces: applying brain–computer interface technology to human–machine systems in general
Thorsten O. Zander, Christian Kothe
2011
Passive BCI defined (Zander & Kothe)
Inflection point

Thorsten O. Zander and Christian Kothe introduce the notion of passive BCI and the active/reactive/passive taxonomy.

2016
Commercialization of neuroadaptation (Zander Labs)

Zander Labs is founded, developing neuroadaptive technology based on passive BCI (the SAMANAI platform, the Zypher EEG suite).

Hyperparameters (configurable axes)

Target mental stateCritical

Which state is detected (load, attention, engagement, ErrP).

cognitive loadCognitive load.
ErrPError-related potential.
Signal modalityHigh

Source of the neurophysiological signal (most often EEG).

EEGMost common modality.
CalibrationMedium

Extent of per-user calibration vs user-independent models.

Computational complexity

Time complexity: O(kanaly × okno × cechy) na klasyfikacje. Space complexity: O(model klasyfikatora + bufor sygnalu).

Compute bottleneck

Signal quality and real-time classification

Low signal-to-noise ratio (SNR), artifacts (motion, blinks) and inter-individual variability make reliable real-time classification difficult.

Depends on
Jakosc EEG / artefaktyKalibracja / zmiennosc osobnicza

Execution paradigm

Primary mode
Dense

Continuous, passive signal processing; the output depends on the user's mental state.

Activation pattern
Input dependent
Routing mechanism

Continuous monitoring, no routing.

Parallelism

Parallelism level
Partially parallel

Channels and features can be processed in parallel; the control loop is sequential.

Scope
Inference
Constraints
!The neuroadaptive loop is inherently sequential and runs in real time.

Hardware requirements

Primary

Mental-state classification from EEG is lightweight and can run on CPU / embedded devices (local processing).