Uncrewed Systems Technology 048 | Kodiak Driver | 5G focus | Tiburon USV | Skypersonic Skycopter and Skyrover | CES 2023 | Limbach L 2400 DX and L 550 EFG | NXInnovation NX 100 Enviro | Solar power focus | Protegimus Protection

12 February/March 2023 | Uncrewed Systems Technology Platformone Researchers at the EPFL in Switzerland have developed algorithms to allow people to take over control of driverless cars more easily (writes Nick Flaherty). The team has used haptic shared control on the steering wheel to create a different way for the vehicle to interact with the driver. Working with steering systems supplier JTEKT, in Japan, it has road-tested the system, which integrates different modes of human- robot interaction. One issue that has arisen with driverless cars is the handover from autonomous operation to driver control. Research has shown that placing too much control of a vehicle in the hands of automation can do more harm than good, as disengagement by human drivers can increase the risk of accidents. “Current vehicles on the market are either manual or automatics, and there is no clear way of making their control a truly shared experience,” said Jurg Schiffmann, head of the EPFL’s Laboratory for Applied Mechanical Design in the School of Engineering. “That is dangerous, because it tends to lead to driver over-reliance on automation. “This research was based on the idea that automation systems should adapt to human drivers, not vice versa,” said EPFL PhD student and JTEKT researcher Tomohiro Nakade, who is also the lead author on a recent paper published in the Communications Engineering journal describing the system. “In automation in general, when humans are just monitoring a system but not actively involved, they lose the ability to react,” said Robert Fuchs, a former EPFL PhD student who is now an r&d general manager at JTEKT. “That’s why we wanted to actively improve driver engagement through automation.” Rather than using a camera, the haptic approach uses data from the sensors in the car’s steering column. It also encourages continuous engagement between the driver and automation system, as opposed to current automated systems, which are typically switched either on or off. That means the software-based system can be integrated into standard mass-produced cars without any special equipment. As the driver operates the vehicle, the systemmoves between four different interaction modes depending on the evolving situation on the road. For example, the car might switch from collaboration to competition mode to take over control to avoid a sudden threat of a collision. Still within the same control framework, the system integrates an ‘inclusion’ function. This re-computes the vehicle’s trajectory whenever the driver intervenes, for example by turning the steering wheel, rather than perceiving it as an override and switching off. To test the system, the researchers developed experiments involving a simulated virtual driver and a human driver using a detached power steering system, a full driving simulator, and field tests with a modified test vehicle. The field tests were carried out with the participation of five drivers on a JTEKT test course in Japan, by connecting the researchers’ system to a standard car via an external controller. Driverless vehicles Easier driver takeover The EPFL’s haptic approach uses data from the sensors in the car’s steering column