Autonomous Vehicles Could Be Made Human Friendly: Study
Update: 01 Jan 2022 15:14 STI
London [UK]Jan. 1 (ANI): Automated vehicles could be made more pedestrian-friendly, recent research shows.
The research has been published in the “Computational Brain & Behavior Journal”.
Scientists led by the University of Leeds who are studying how to better understand human behavior in traffic said neuroscientific theories of how the brain makes decisions can be used in automated vehicle technology to improve safety and make it more user-friendly.
The researchers investigated whether a decision-making model called drift-diffusion could predict when pedestrians would cross a road in front of approaching cars, and if it could be used in scenarios where the car gives way to pedestrian, with or without explicit signals. This prediction capability will allow the autonomous vehicle to communicate more effectively with pedestrians, in terms of its movements in traffic and any external signals such as flashing lights, to maximize traffic flow and reduce uncertainty.
Drift diffusion models assume that people make decisions after accumulating sensory evidence up to a threshold at which the decision is made.
Professor Gustav Markkula, University of Leeds Institute for Transport Studies and lead author of the study, said: ‘When making the decision to cross, pedestrians seem to add up from many different sources. evidence, not only related to the distance and vehicle speed, but also using the vehicle’s communication signals in terms of deceleration and headlight flashing. “
“When a vehicle gives way, pedestrians often feel quite uncertain as to whether the car is actually giving way, and often end up waiting until the car is almost completely stopped before starting to cross. Our model clearly shows this state of confirmed uncertainty, which means that it can be used to help design the behavior of automated vehicles around pedestrians to limit uncertainty, which in turn can improve both safety road and traffic flow. It is exciting to see that these theories from cognitive neuroscience can be applied in this type of real world context and find applied use, ”he added.
To test their model, the team used virtual reality to place trial participants in different road crossing scenarios in the University of Leeds’ unique Highly Immersive Kinematic Experimental Research (HIKER) pedestrian simulator. The movements of the study participants were followed in great detail while walking freely inside a stereoscopic 3D virtual scene, showing a road with oncoming vehicles. The participant’s task was to cross the road as soon as he felt safe.
Different scenarios were tested with the approaching vehicle keeping the same speed or decelerating to let the pedestrian cross, sometimes also flashing the headlights, which is a signal commonly used to express intentions in the UK.
As their model predicted, the researchers found that participants behaved as if they were deciding when to cross by summing up, over time, sensory data from vehicle distance, speed, acceleration, as well as communication clues. This meant that their drift-diffusion model could predict if and when pedestrians would be likely to start crossing the road.
Professor Markkula said: “These findings may help better understand human behavior in traffic, which is needed both to improve road safety and to develop automated vehicles that can coexist with human road users. Safe and human-acceptable interaction with pedestrians is a major challenge for developers of automated vehicles, and a better understanding of pedestrian behavior will be key to enable this. “
Lead author Dr Jami Pekkanen, who conducted the research at the University of Leeds, said: “The prediction of pedestrian decisions and uncertainty can be used to optimize when and how the vehicle should decelerate and signal to communicate that it is safe to walk through, saving both time and effort. “(ANI)