Technology

High-resolution tactile sensing and data analytics platform, fueling the future of autonomous vehicles and smart cities

Our data services are based on Tactile Mobility’s technology platform comprising two advanced software modules, an in-vehicle embedded software and a cloud module, which can be provided as standalone solutions or combined together to reinforce each other.

From data to powerful insights

Diagram

TACTILE SOFTWARE PROCESSOR

Residing on one of the vehicle’s computers (ECUs)*, this embedded module runs proprietary algorithms and AI to generate real-time actionable insights about the vehicle-road dynamics based on raw data ingested from multiple, existing, non-visual sensors. * Or on an aftermarket device connected to the vehicle CANBus/OBD.

IN REAL-TIME, THE PROCESSOR DOES THE FOLLOWING:

Ingestion
Ingestion
High-bandwidth data is aggregated and ingested from multiple non-visual sensors that already exist on the vehicle, such as wheel speed from all four wheels, wheel angle, RPM, position of the gas paddle, the torque of the brake paddle, and more.
Fusion
Fusion
The ingested data is fused into a unified signal, representing in real-time the dynamics between the vehicle and the road, each in their current state.
Noise Cleaning
Noise Cleaning
Any noise created by the sensors is cleaned using signal processing methodologies, exposing the unified signal and preparing it for processing.
Processing
Processing
The clean signal is analyzed to generate actionable insight, or as we call it: Virtual Sensors, through proprietary algorithms and AI. These virtual sensors include grip level, vehicle weight, engine efficiency, tire health, and much more.
Feedback
Feedback
Data from the virtual sensors are fed back into the vehicle computer, giving better context for improved driving decisions.

Tactile Mapping Cloud Module

Datasets from each vehicle are uploaded to the cloud and continuously crunched, using big data methodologies and machine learning. These analyses generate and continuously update two mathematical models, describing the critical factors that impact vehicle-road dynamics:

VehicleDNATM

Represents the unique attributes of each vehicle’s engine efficiency, braking efficiency, tire health, weight, fuel consumption, and more.
Data is downloaded back to each relevant vehicle, ensuring that the embedded software has the most updated and accurate context available, for improved ongoing calculations and performance. It is also commercialized with customers such as Fleet Managers and Operators.

SurfaceDNATM

Models road features, such as grades, banking, curvature, normalized grip levels, and location of hazards such as bumps, cracks, and potholes.
Data is downloaded to vehicles roaming the specific area, enabling them to prime the embedded software with insight on the road ahead, improving safety and user experience reaction time. This model is also specifically invaluable for third-parties such as mapping companies, road authorities, municipalities, fleet managers and owners, OEMs, and insurers.