Skip to content
This is NOT an official site of the Government of Canada. Click here for the official AI registry.

Helpful Places

Government of Canada – DTPR AI Register

Back to your search

AI-Assisted Driver Intention Prediction for Road Safety

Safety & Security · Research & Development

What it collects

Biometric
Anonymized data
  • Driver gaze direction and eye movements captured by eye-tracking sensors to infer where the driver is looking and what they may intend to do. The register confirms no personal information is collected.

Government of Canada AI Register — 2526-NRC-CNRC-024

About a measurement
Anonymized data
  • Sensor readings from the external driving environment — such as object positions, lane markings, traffic signals, and road conditions — used to align with driver gaze for multi-modal cross-calibration.

Government of Canada AI Register — 2526-NRC-CNRC-024

Run by
National Research Council Canada (NRC)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Not stated by the Helpful Places.

What it is for

Safety & SecurityResearch & Development

This system, developed by the National Research Council Canada in partnership with the University of Western Ontario, aligns driver gaze movements with changes in the surrounding environment to predict what a driver intends to do next. It is designed to augment advanced driver assistance systems (ADAS) by extending their ability to anticipate driver actions before they occur. Currently in development, the system does not collect personal information and is not yet deployed to the public.

What it collects and what happens to it

Data taken in

Biometric
Anonymized data
  • Driver gaze direction and eye movements captured by eye-tracking sensors to infer where the driver is looking and what they may intend to do. The register confirms no personal information is collected.

Government of Canada AI Register — 2526-NRC-CNRC-024

About a measurement
Anonymized data
  • Sensor readings from the external driving environment — such as object positions, lane markings, traffic signals, and road conditions — used to align with driver gaze for multi-modal cross-calibration.

Government of Canada AI Register — 2526-NRC-CNRC-024

Processing

Classification & Prediction
  • Multi-modal data alignment and cross-calibration model that classifies and predicts driver intentionality from aligned gaze and environmental sensor streams.

Government of Canada AI Register — 2526-NRC-CNRC-024

What it does

Sensing (Perceptive AI)
Human decides
  • Senses driver gaze movements and external environment changes through multi-modal sensors (e.g. eye-tracking, cameras) to extract structured signals for downstream prediction.

Government of Canada AI Register — 2526-NRC-CNRC-024

Deciding (Analytical AI)
Human decides
  • Predicts driver intentionality and forthcoming actions by scoring aligned multi-modal data inputs — providing advisory outputs to ADAS rather than binding decisions.

Government of Canada AI Register — 2526-NRC-CNRC-024

Outputs

A recommendation or prediction
Anonymized data
  • Predicted driver intentionality and anticipated actions provided as advisory outputs to an ADAS, which may use them to alert the driver or trigger safety responses. The prediction broadens the ADAS time horizon.

Government of Canada AI Register — 2526-NRC-CNRC-024

Run by

National Research Council Canada (NRC)
  • Federal research and technology organisation accountable for the development and deployment of this AI system. Co-developed with the University of Western Ontario.

Government of Canada AI Register — 2526-NRC-CNRC-024

Built by

Not stated by the Helpful Places.

Kept for

Not stated by the Helpful Places.

Shared with

Not stated by the Helpful Places.

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data
Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data
Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data
The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides
This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes
This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous
This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

  • Right to Be Informed of AI UseThe register states that AI use is not disclosed to users. As this system is in development with no public deployment and no personal information collected, formal notification mechanisms are not yet established. Prospective users should be informed when the system transitions to production deployment.
  • Right to Algorithmic TransparencyThis system is a research-stage AI developed by the National Research Council Canada. Information about the system's logic and operation may be accessible through the Government of Canada's AI Register. No formal transparency channel for end-users has been described at this stage of development.

Risks and safeguards

  • Physical harmIncorrect predictions of driver intent could, if integrated into an active ADAS, trigger inappropriate safety interventions or fail to alert a driver in a genuine hazard scenario.Safeguard: The system is currently advisory only, feeding predictions to an ADAS that retains human oversight. It is in development and not yet deployed to the public. The long-term design intent is to alert drivers or support safety actions rather than autonomously actuate vehicle controls.