The new technology monitors the hands of the driver to determine his readiness to get behind the wheel

The technologies for tracking the movements of the hands of abstract drivers expects how much time a person will need to take on the control of the car in an emergency.

When automakers settled all the legal aspects of the use of third-level autonomous control systems, the vehicles will start independently deliver people to the destination. This technology will allow the driver to be distracted from the road to write a text message or watch a video.

In emergency situations, such cars will still rely on a person, so it is important for them to know how quickly he will be able to respond and take control over himself. To solve this problem, researchers from the University of California have developed a special surveillance system.

The team took an existing program to track the movements of the entire body, and adapted it to monitor the location of the wrists and the driver’s elbows, as well as the passenger, if available. Then they developed and used machine learning algorithms to teach the algorithm to interact with unmanned control systems.

During the tests, the technology determined the position of each of the eight key joints with an accuracy of 95%, but gave a failure when the driver closed parts of his body or there was not typical clothing with many patterns, which was not presented in 8500 images analyzed.

According to the team, most of the problems can be solved by placing the camera in more convenient locations and expanding a set of training photos.

Nevertheless, the person’s response still plays a key role in the security issue, so in order for drivers to notice and interpret information on the dashboard, Bosch is developing a new generation

To develop the channel, your support is important to us, subscribe to the channel and put like.