Posted inVehicles

GM seeks approval to deploy self-driving vehicles in 2019

The Cruise AV is built to operate safely on its own, with no driver, steering wheel, pedals or manual controls.

GM seeks approval to deploy self-driving vehicles in 2019
GM seeks approval to deploy self-driving vehicles in 2019

General Motors has filed a safety petition with the US department of transportation for its fourth-generation self-driving Cruise AV.

The company plans to deploy the first production-ready vehicle in 2019, built from the start to operate safely on its own, with no driver, steering wheel, pedals or manual controls.

The Cruise AV operates by sensing its environment and making driving decisions with three functions: perception, planning and controls.

The perception function uses sensors, including five Lidars, 16 cameras and 21 radars, to monitor the environment.

The sensors feed information to the computer that combines the sensor data with high-definition map data to localise the vehicle. Perception detects and classifies objects, determines their location and provides their speed and direction.

It builds a three-dimensional model of the world that keeps track of important objects.

The planning function determines the desired vehicle behaviour. It accounts for road rules and plans routes for the car to travel from trip origin to destination.

It chooses routes to optimize efficiency and safety and to route the car only on streets within its capabilities.

The controls function implements the final path from planning, converting its commands for the actuators that control the steering, throttle, brake and drive unit.

The self-driving vehicle has two data recording features, a conventional event data recorder (EDR) and a second robust data logging system.

The data logging system has self-diagnostics and stores data securely, protecting it against loss even in the event of a crash.

If a crash occurs, the data logging system stores predefined data from the vehicle.

The collected data includes information on sensors, vehicle actions, any degraded behaviour, malfunctions and other information useful for event reconstruction.