JLR aims to improve trust in self-driving vehicles
BY ROBBIE WALLIS | 29th Aug 2018
JAGUAR Land Rover (JLR) has developed self-driving pod vehicles equipped with ‘virtual eyes’, in an effort to understand the level of trust humans have with autonomous vehicles.
The pods are designed to help work out how much information should be shared with pedestrians and road users to develop a trust in the technology.
JLR has set up a fabricated street scene in which the behaviour of pedestrians is analysed while waiting to cross the road. The large virtual ‘eyes’ on the front of the vehicle can seek out pedestrians, appearing to ‘look’ at them, indicating it has identified the pedestrian and will avoid them.
Engineers then record the trust levels in the pedestrian before and after the pod makes ‘eye contact’ to figure out whether the pedestrian gains confidence in the pod’s ability to stop for them.
A team of cognitive psychologists have been called on to gauge how human confidence in autonomous technology is affected by vehicle behaviour. More than 500 test subjects have been involved in the trial.
According to JLR, previous studies have suggested as many as 63 per cent of pedestrians and cyclists have said they would feel less safe when sharing the road with an autonomous vehicle.
Like many of its previous trials in autonomous technology, the latest tests are a part of UK Autodrive, a government-funded project that aims to make autonomous vehicles a reality on UK roads.
Beginning in November 2015, UK Autodrive also strives to show how autonomous vehicles can solve challenges such as congestion, and provides insights for key groups such as investors and legislators. The trial is set to wrap up in October.
JLR future mobility research manager Pete Bennett said the study sought to decide whether it is valuable to give humans information about the decisions autonomous vehicles make.
“It’s second-nature to glance at the driver of the approaching vehicle before stepping into the road. Understanding how this translates in tomorrow’s more automated world is important,” he said.
“We want to know if it is beneficial to provide humans with information about a vehicle’s intentions or whether simply letting a pedestrian know it has been recognised is enough to improve confidence.”
