Nissan’s Brain-to-Vehicle Technology Connects Our Brains With Vehicles
Technologies such as Nissan’s Brain-to-Vehicle (B2V) and EEG driving technology are redefining the future of mobility by establishing a direct connection between drivers’ brain signals and their vehicles. Since its introduction in 2018, the B2V system has undergone significant advancements. EEG driving technology
Unlike traditional autonomous driving systems, which aim to eliminate the need for human input, B2V seeks to augment the driving experience by predicting the driver’s intentions between 0.2 and 0.8 seconds before an action occurs. This allows vehicles to react more swiftly than human reflexes, fostering a more responsive, intuitive, and safer journey. It accomplishes this through real-time electroencephalogram (EEG) data, artificial intelligence (AI) algorithms, and wearable neurotechnology.
Central to B2V are three technological pillars: lightweight, wireless brain-sensing devices; advanced EEG signal processing that decodes driver intentions in real time; and shared control frameworks that synchronize vehicle responses with neural activity. By integrating these elements, Nissan is pioneering a new paradigm in mobility, where vehicles adapt dynamically to the driver's mental state for safer, smarter, and more adaptive transport ecosystems.
Nissan is also exploring how human cognitive performance can enhance semi-autonomous driving systems. In a recent initiative, the company invited commercial airline pilots to test its ProPILOT Assist 2.0 technology. This advanced driver-assist system enables hands-free highway driving under specific conditions. Pilots praised the system’s intuitive control and situational awareness, likening its design to cockpit ergonomics and aviation-grade responsiveness. Their feedback is helping Nissan further refine driver-monitoring features and shared control interfaces, reinforcing the company’s commitment to human-centred innovation in the next generation of mobility solutions.
How Nissan’s B2V System Enhances Driver Response Times
It takes between 0.2 and 0.4 seconds for a command from the brain to travel through the nervous system and trigger muscle activation. However, even before this command is sent, the brain begins preparing the movement, which starts approximately 0.2 to 0.6 seconds earlier. This means that a driver’s intention to act, such as braking or turning, can be detected up to one second in advance through neural activity patterns captured via EEG technology.
By identifying this pre-motor brain activity, Nissan’s B2V system can initiate vehicle responses before the driver physically reacts. At highway speeds—around 100 km/h (62 mph)—this level of anticipation could reduce braking distance by nearly 27 meters, which is often the crucial difference between a safe stop and a collision. In addition to braking, the system can foresee steering inputs and other manoeuvres, enhancing real-time driving precision and responsiveness. Nissan envisions this as a shift from reactive vehicle behaviour toward proactive, adaptive driver-assist systems that continuously adjust based on the driver’s mental and cognitive state, for a safer, more personalised driving experience.
A key feature of B2V technology is its foundation in shared control, a concept in which the driver and vehicle collaborate rather than compete. Unlike fully autonomous systems designed to replace the driver with automated decision-making, shared control maintains the driver’s agency while augmenting their actions with real-time support. This human-centric model enhances safety and comfort, allowing the vehicle to assist based on the driver’s intentions without removing them from the loop.
Nissan’s Executive Vice-President, Daniele Schillaci, emphasised this vision: "Through Nissan Intelligent Mobility, we are moving people to a better world by delivering more autonomy, electrification, and connectivity". Supporting this transformative outlook, Dr. Lucian Gheorghe, Senior Innovation Researcher at Nissan Intelligent Mobility, highlighted: "The possible applications of this technology are incredible. This research will be a catalyst for innovation within our vehicles in the coming years".
The principles of brain function and their relationship to behaviour form the scientific foundation of Nissan’s B2V technology. First showcased at the Consumer Electronics Show (CES, 2018)—the world’s largest trade show for consumer electronics—this innovation marked a significant milestone in neurotechnology integration within the automotive sector. Nissan’s advance is the first milestone in collaboration with Bitbrain, the Swiss Federal Institute of Technology, and the Canadian National Research Council. Together, these partnerships combine expertise in brain-computer interfaces (BCIs), wearable EEG systems, and cognitive neuroscience, advancing the practical application of brain-based sensing to revolutionise driver-vehicle interactions.
The B2V project is built on four foundational pillars that blend neuroscience, engineering, and human-centred design to redefine the driving experience:
- Wearable, wireless EEG technology: Development of a lightweight and ergonomic EEG device that measures brain activity without disrupting the driver’s natural movements. Designed for real-world usability, this sensor system operates comfortably over long durations and functions reliably in dynamic driving environments.
- Real-time brain activity analysis: Advanced signal processing algorithms are used to interpret EEG data in real time. This enables the system to anticipate driver actions, such as braking, turning, or accelerating, up to one second before they are physically executed, enhancing both response time and situational awareness.
- Shared control strategies: Implement cooperative control systems where the driver and vehicle contribute to driving decisions. Rather than replacing the driver, B2V enhances its control by integrating neural signals into the vehicle’s response mechanisms. This approach offers a balanced alternative to full autonomy, fostering trust, comfort, and improved safety through seamless human–machine interaction.
- System integration and validation: Rigorous testing of B2V components in simulated environments and real-world trials ensures that the technology performs reliably under varied traffic conditions. These validations are crucial for scaling the solution to practical, everyday use across diverse driving contexts.
Minimalist EEG Technology Optimised for Automotive Applications
Bitbrain, in collaboration with Nissan, has developed a wearable, minimalist EEG system tailored for use in dynamic driving environments. Equipped with dry sensors, this cutting-edge neurotechnology is designed to monitor brain activity associated with driver movement, without requiring conductive gels or complex setup procedures.
This next-generation EEG system offers several key advantages. It operates without electrolytic conductive substances, streamlining the setup process and making it more user-friendly. Its lightweight and ergonomic design prioritises long-term comfort, allowing drivers to maintain natural behaviour without distraction. Moreover, the device is engineered for high-fidelity signal capture in real-world settings, offering a more discreet and technologically refined solution than conventional EEG systems. The headset can typically be deployed in under two minutes and supports continuous operation for up to eight hours. It transmits brain activity data wirelessly via Bluetooth to the vehicle’s onboard systems, enabling real-time interpretation of the driver’s cognitive state. By seamlessly integrating into everyday driving scenarios, this wearable EEG platform marks a significant leap toward scalable, real-world brain-to-vehicle communication, bringing the concept of mind-responsive mobility closer to mainstream adoption.
Requirements for EEG System Optimization
To ensure the effectiveness of the B2V project, the EEG system was engineered to meet three critical performance criteria:
- User Acceptability: The headset needed to be comfortable for prolonged use, with an ergonomic and aesthetically pleasing design. Minimising the number of sensors was essential to avoid overburdening the user while maintaining full system functionality. This balance enhances wearability and ensures the EEG device integrates seamlessly into daily driving routines.
- Resistance to Motion Artifacts: Because natural head and body movements during driving can introduce noise into EEG signals, the system was designed to be fully wireless, thereby eliminating interference caused by cables. Additionally, it features advanced active shielding to suppress noise from non-neuronal sources, ensuring the integrity and accuracy of brain activity recordings even under dynamic conditions.
- Reliable Measurement of Brain Processes: The EEG system had to accurately detect critical neural signatures such as movement-related cortical potentials (MRCPs) and motor event-related (de) synchronisation (ERD/ERS). Particular attention was given to achieving high signal quality with dry electrode technology, a challenging but essential factor for real-time decoding of driver intent.
This video shows an example of using this neurotechnology in an intermediate prototype.
The development of this wearable EEG technology is a clear advance for this project and, more generally, for applying these technologies outside lab settings. This technology captures the natural behaviour of the driver. It records EEG with unprecedented precision and reliability, which are both required to capture the motor and cognitive brain processes involved in driving a vehicle.
The new minimal EEG is a considerable advance towards reliable brain measurement devices adapted to daily life applications.
Brain-computer interface to anticipate movement
The brain-computer interface (BCI) developed for B2V technology decodes neural signals to anticipate the driver’s intended actions before they are physically executed. This system is grounded in detecting preparatory brain activity—neural signals that emerge in the motor cortex shortly before voluntary movement. Two primary EEG correlates are key to this process: MRCPs and ERD/ERS patterns.
To analyse these signals, researchers typically aggregate multiple repetitions of the same movement to create a Grand Average, which reveals consistent patterns of neural preparation.
For example, the following picture shows how EEG recordings from the corresponding motor region demonstrate clear pre-motor potentials and oscillatory changes preceding the movement onset when a person initiates movement, such as stepping forward with the correct leg.
A compelling illustration of this mechanism comes from a separate clinical context involving a stroke patient. In this case, electromyographic (EMG) data from the arm (yellow line) was paired with real-time BCI decoding of brain activity (green line). The decoded neural signals consistently anticipated the muscular activation, underscoring the BCI’s capacity to predict actions before they occur.
By leveraging these neurophysiological markers, B2V technology enhances vehicle responsiveness, enabling systems to react to driver intentions preemptively. This capability holds substantial promise for reducing reaction times, thereby advancing the safety and adaptability of future intelligent transport systems.
Adapting the Driving System to the Driver
While earlier examples demonstrate the promise of B2V technology, achieving real-time EEG decoding of movement anticipation in naturalistic driving conditions remains a significant technical challenge. Several key factors contribute to this complexity:
- Low signal-to-noise ratio: In real-world settings, decoding must rely on brain activity from single movements rather than averaged signals across multiple repetitions, as is often done in controlled laboratory experiments. This reliance results in EEG data that is inherently noisier and less stable, complicating accurate signal interpretation.
- Continuous intention monitoring: Unlike laboratory tasks with predefined timing, real-life driving lacks prior knowledge of when the driver intends to act, such as braking, accelerating, or turning. Therefore, the system must continuously monitor neural activity in real time, which diminishes detection precision due to the unpredictability of cognitive events.
- High inter- and intra-individual variability: Neural signatures of movement intention vary significantly between individuals and even within the same individual across different contexts or emotional states. This variability poses a significant hurdle for generalizing decoding algorithms across users or scenarios.
Overcoming these obstacles is crucial for developing reliable, safe, personalized EEG-based driver assistance systems. Addressing them requires robust signal processing techniques, customized machine learning models, and continuous system calibration to ensure adaptability to dynamic human behavior.
Machine Learning and Calibration: Teaching the System to Anticipate Movement
To get the better of the inherent challenges of real-time intention decoding, B2V systems incorporate advanced machine learning (ML) and artificial intelligence (AI) algorithms rooted in signal processing techniques. These systems must undergo a calibration phase tailored to each individual to achieve accurate, personalized predictions.
During calibration, the driver engages in natural driving behaviors—such as steering, braking, or accelerating—while their electroencephalogram (EEG) signals and corresponding physical movements are recorded in parallel. This data is used to train the BCI, enabling the system to decode the driver’s intention approximately 0.5 seconds, sometimes up to 1 second, before the actual motor action occurs.
This calibration is often performed for practical implementation using a driving simulator replicating real-world scenarios in a controlled setting. Nissan adopted this method during its B2V demonstrations at CES 2018, where participants first completed a guided calibration sequence. Their brain activity and behavioral responses (e.g., braking or turning) were captured as they followed instructions within the simulator. Once the system confirmed sufficient and high-quality data had been collected, participants were permitted to operate the simulator with direct BCI-assisted control. This individualized calibration process is essential for optimizing the performance of automatic learning models, allowing them to anticipate driver intentions with high reliability and responsiveness.
Other B2V projects around the world
Nissan is not the only automotive manufacturer interested in the brain to vehicle concept, using EEG systems in their vehicles. Several leading carmakers actively integrate EEG-based neurotechnology into their research and development pipelines to improve driver safety, cognition, and user experience.
In collaboration with King’s College London, Ford conducted a groundbreaking study comparing the cognitive performance of professional racing drivers and everyday motorists using EEG and virtual reality environments. The results showed that professional drivers demonstrated up to 40% greater focus and more efficient distraction filtering. Moreover, when novice drivers engaged in mental training exercises—including mindfulness and visualisation—their cognitive performance improved significantly, narrowing the gap with professionals.
Hyundai Mobis took a significant step forward in 2022 by unveiling its Smart Cabin Controller, a biometric monitoring system that integrates EEG, heart rate, and 3D posture analysis. This system detects signs of drowsiness, stress, and other physiological anomalies in real time, adjusting environmental settings or engaging autonomous driving protocols as needed. It aims to create adaptive, health-centred in-car environments that improve safety and well-being.
Audi has been utilising EEG systems within the 25th Hour project to evaluate the user experience in autonomous vehicles. Aware of the rapid transformation in mobility, Audi anticipates that time spent in cars will increasingly be used for productivity or relaxation. Using a futuristic simulation of an autonomous vehicle, Audi studied millennial user expectations, focusing on creating environments conducive to cognitive efficiency. EEG data revealed varying levels of cognitive demand depending on the type of stimuli presented, such as the driver’s view, relaxation space, or productivity zones.
Meanwhile, Mercedes-Benz introduced its BCI concept in the futuristic VISION AVTR. This system utilizes non-invasive electrodes on the back of the driver’s head to monitor neural responses. After a short calibration, the interface allows the driver to interact with the vehicle, such as selecting navigation options or adjusting interior settings, by focusing on the visual elements displayed on the dashboard. This hands-free interaction removes the need for speech or physical input, pushing the boundaries of intuitive vehicle control.
In another notable example, SEAT, in partnership with Bitbrain and Ogilvy, presented the “Neuroconfigurator” at the Paris Motor Show. This innovative project used minimalist EEG headsets to capture the emotional and cognitive reactions of over 8,000 participants as they were exposed to different vehicle features. The data enabled SEAT to analyse consumer preferences, create personalised driver profiles, and explore emotion-driven design adaptations, all performed autonomously by users without needing technician assistance.
Conclusion
Nowadays, there are many innovations to improve the interaction between humans and vehicles, and there is no doubt that the use of brain information opens a wide field for research and future potential applications. These applications include technologies for detecting and evaluating driver behaviour, adapting driving styles in real time, and creating a more engaging, responsive driving experience. The global brain-to-vehicle technologies are already here, and the question is whether humans will relinquish control of their cars in the future or share control. What we know is that we will move beyond manual driving very soon.