A team of scientists from the University of Maryland recently came up with a take on the hyperdimensional computing theory that could give robots memories and reflexes. This could break the stalemate we seem to be at with autonomous vehicles and other real-world robots, and lead to more human-like AI models.

The solution

The Maryland team came up with a theoretical method by which hyperdimensional computing – a hypervector-based alternative to computations based on Booleans and numbers – could replace current deep learning methods for processing sensory information.

A.I. is yet to prove the safety of self-driving cars.

“Shortly following the accident, we informed the National Highway Traffic Safety Administration and the National Transportation Safety Board that the vehicle’s logs showed that Autopilot was first engaged by the driver just 10 seconds prior to the accident, and then the driver immediately removed his hands from the wheel,” a Tesla spokesperson told The Register in an emailed statement. “Autopilot had not been used at any other time during that drive. We are deeply saddened by this accident and our thoughts are with everyone affected by this tragedy.”

To navigate dynamic environments, autonomous vehicles (AVs) should be able to process all information available to them and use it to generate effective driving strategies. Researchers at the University of California, Berkeley, have recently proposed a social perception scheme for planning the behavior of autonomous cars, which could help to develop AVs that are better equipped to deal with uncertainty in their surrounding environment.

“My research has focused on how to design human-like driving behaviors for autonomous cars,” Liting Sun, one of the researchers who carried out the study, told TechXplore. “Our goal is to build AVs that do not only understand human behavior, but also perform in a similar way in multiple aspects, including perception, reasoning and action.”

Sun and her colleagues observed that human drivers tend to treat other vehicles as dynamic obstacles, often inferring additional information from their behavior on the road. This information is generally occluded environment information or physically undetectable social information.