The friendly looking digital eyes have a very important job – to assess how much information pedestrians need to know from self-driving cars in order to feel safe and protected around them. JLR has enlisted the help of a team of cognitive psychologists to help with this, and to see how much confidence humans place in auto-automobiles.
The tests are carried out in Aurrigo’s Urban Driving Laboratory in Coventry, while the behaviour of pedestrians is analysed as they wait to cross the fake road as the pods come towards them and stop.
The ‘eyes’ have been devised by a team of advanced engineers, working in Jaguar Land Rover’s Future Mobility division. The pods seek out the pedestrian - appearing to ‘look’ directly at them - signalling to road users that it has identified them and intends to give way. The trust levels of the pedestrian are recorded before and after the pods “look” at them.
David Keene, CEO of Aurrigo, commented: “Safety is at the heart of our autonomous technology and, our close working relationship with JLR, meant we could quickly accommodate ‘virtual eyes’ on to a number of our pods to facilitate this important study.
“The valuable information will be used as part of the UK Autodrive programme and will also shape future developments in how we bring self-driving vehicles on to the pavements, streets and roads of the UK and overseas.”
Pete Bennett, future mobility research manager at Jaguar Land Rover, said: “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.
“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.”
More than 500 test subjects have been studied interacting with the self-driving Aurrigo pods, which will help improve self-driving vehicles for the future.
To see the pods in action, click here https://www.youtube.com/watch?reload=9&v=Fis1Oem-rAs
