Self Driving Cars Being Taught to 'See' in Canada

February 26, 2020, Kitchener, Ontario

Posted by: Robert Deutschmann, Personal Injury Lawyer

Self driving cars are becoming more common on global roadways however, they continue to struggle to ‘learn’ how to react in some climactic conditions that are common in the northern hemisphere. Snow in particular is very confusing for the computer interfaces to decipher.

In response to the problem a team of researchers at the University of Waterloo have equipped an new car – the Autonomoose – with 8 camera and la laser to capture thousands of images to capture and ‘learn’ how to better navigate snowy and icy conditions.

This special customized Canadian car is the first one in the world to create a data set for winter driving which is being fed into the AI to teach the car how to navigate the conditions. For areas that suffer winter conditions this is crucial to any success of self driving cars.

They have been driving around Waterloo Region for the last couple of years collecting the imagers of winter roads covered in snow, of snow falling, of ice on roads and winter driving in general. The data being collected is open source and is being widely shared so that companies and other universities can also continue research and innovation in the field.

According to the researchers the drives are very bumpy in the car in bad weather. On the track the car automatically brakes and steering wheel spins as it encounters the bad conditions. This of course teaches the car what not to do! Anyone who has driven on poor roads knows that any sudden moves like braking or wild steering changes will cause the car to go out of control quickly. Researchers know that as the car makes the mistakes it will learn how to react properly.

Researchers predict that all season autonomous vehicles are a long way off.

From the website:

The Autonomoose is a Lincoln MKZ hybrid that has been equipped with a full suite of radar, sonar, lidar, inertial, and vision sensors. Based on SAE International standards for automotive driving, the Autonomoose vehicle has powerful embedded computers in order to run a complete autonomous driving system. Researchers are currently working on custom autonomy software.

Specific Autonmoose projects include:

• Improving self-driving in all whether conditions that are specific to Canada.
  • Simultaneous localization and mapping (SLAM) in all weather conditions.
  • Autonomous maneuvering under extreme conditions.
• Optimize self-driving for fuel efficiency and reduced emissions.
  • Power-management controllers for autonomous driving.
• Provide methods to design safe, robust, computer-based controls for self-driving vehicles.
  • Feature-oriented engineering (FOE).
  • Runtime monitoring and reconfiguration infrastructure for autonomous driving.
  • Fault-tolerant electric/electronic (E/E) architectures for autonomous vehicles.
  • Functional safety for software and components of autonomous vehicle systems.

You can read more about the Autonomoose and the research going on at the university of Waterloo here. Image courtesy of the University of Waterloo website.

About Deutschmann Law

Deutschmann Law serves South-Western Ontario with offices in Kitchener-Waterloo, Cambridge, Woodstock, Brantford, Stratford and Ayr. The law practice of Robert Deutschmann focuses almost exclusively in personal injury and disability insurance matters. For more information, please visit www.deutschmannlaw.com or call us at 1-519-742-7774.

It is important that you review your accident benefit file with one of our experienced personal injury / car accident lawyers to ensure that you obtain access to all your benefits which include, but are limited to, things like physiotherapy, income replacement benefits, vocational retraining and home modifications.