Technology giant IBM has secured a patent for a cognitive system to manage the safety of self-driving vehicles.
The system has been developed by IBM researchers using their knowledge of biological cognition and behavior generation in the brain.
The system defines how to shift control of an autonomous vehicle between a human driver and a vehicle control processor in case of a potential emergency.
It features sensors and artificial intelligence to identify potential safety issues and control whether self-driving vehicles are operated autonomously or by giving control to a human driver.
If a self-driving vehicle is subjected to an operational glitch such as a faulty braking system, a burned-out headlight, poor visibility, bad road conditions, the system will decide whether the on-board self-driving vehicle control processor or a human driver is in a better position to handle that anomaly.
IBM noted that if the vehicle control processor is found to better handle the anomaly, the vehicle will be placed in autonomous mode.
IBM Research manager for computational neuroscience and multi-scale brain modeling and co-inventor on the patent James Kozloski said: “Self-driving vehicles hold great promise and potential, but protecting the safety of passengers and other drivers remains a top priority for vehicle developers and manufacturers.
“We are focused on finding new ways to leverage our understanding of the human brain and inventing systems that can help those enterprises improve the safety of autonomous vehicles on the road.”
Apart from the new system, IBM has earlier patented other inventions that are focused on helping self-driving vehicles better forecast and respond to actions of human drivers.
IBM is focusing more on the self-driving car arena. Last December, the company said it would collaborate with automaker BMW to explore the role that Watson can have in personalising the driving experience.
The collaboration aims to create more intuitive driver support systems for BMW’s cars of the future.