 developed a system that driverless cars can use to help predict other people’s driving personalities. It’s just one of the industry’s latest attempts to increase the safety of these vehicles as more automakers push automated technology on future models. Family-Friendly Fun: Places to explore […] "'Pin It")
MIT Develops System to Determine People’s Driving Personalities
MIT researchers at the Computer Science and Artificial Intelligence Laboratory (CSAIL) developed a system that driverless cars can use to help predict other people’s driving personalities. It’s just one of the industry’s latest attempts to increase the safety of these vehicles as more automakers push automated technology on future models.
Family-Friendly Fun: Places to explore near Birch Run
Using SVO to establish an algorithm
The team used social value orientation (SVO) to create an algorithm that could help an AV predict other drivers’ behavior. Per MIT News, SVO has to do with the degree to which a person’s action is selfish or unselfish. The idea is that if an AV can think like a human, it will more accurately predict and respond to traffic scenarios to improve passenger safety.
Graduate student Wilko Schwarting expressed the challenges that the team sought to address with its new algorithm. “Working with and around humans means figuring out their intentions to better understand their behavior. People’s tendencies to be collaborative or competitive often spills over into how they behave as drivers.”
Photo: Pixabay
The categories of driving personalities
Per Jalopnik, the system interprets and categorizes drivers’ behavior into one of three categories: egoistic, cooperative, or altruistic. The team then investigated how certain drivers acted in merging and left-turn scenarios. For instance, cooperative and altruistic types tended to let other drivers merge into their lane, while egoistic ones did not.
MIT professor Daniela Rus articulated the experiment’s contribution to the industry. “By modeling driving personalities and incorporating the models mathematically using the SVO in the decision-making module of a robot car, this work opens the door to safer and more seamless road-sharing between human-driven and robot-driven cars.”
Service Smart: Know when it’s time for new tires
News Sources: MIT News, Jalopnik
Whitney Russell resides in Dayton, though her spirit can be found beach-bumming in Puerto Rico (the land of her half-Puerto Rican heritage). When not crafting car-related content, she can be found chasing after the most amazing toddler in the world, watching her “beaver” of a husband build amazing woodworking projects, hanging out with two crazy dogs, and visiting family and friends. She also enjoys traveling, crafting, and binge-watching period dramas when time allows. See more articles by Whitney.