Jaguar Land Rover says its big-budget autonomous all-terrain driving research project aims to make the self-driving car viable in the widest range of on- and off-road environments and weather conditions.
Next-generation sensing technologies will be the eyes of future all-terrain autonomous cars as artificial intelligence takes capability to the next level, research head Tony Harper says as JLR gives a world-first demonstration of an off-road connected convoy using car-to-car communication.
Harper says JLR’s autonomy research aims to help both the driven and autonomous car travel safely through any terrain or driving situation.
“We don’t want to limit future highly automated and fully autonomous technologies to tarmac,” he says in a statement.
“When the driver turns off the road, we want this support and assistance to continue. In the future, if you enjoy the benefits of autonomous lane keeping on a motorway at the start of your journey, we want to ensure you can use this all the way to your destination, even if this is via a rough track or gravel road.”
Harper says the technology will account for everything from road construction, a snow-covered road in the mountains or a muddy forest track.
“This advanced capability would be available to both the driver and the autonomous car, with the driver able to let the car take control if they were unsure how best to tackle an obstacle or hazard ahead,” he says.
To reach this level of autonomous all-terrain capability, JLR researchers are developing next-generation sensing technologies that will be the eyes of the autonomous car. Sensors, always active, will see better than the driver and ultimately give a vehicle the high levels of artificial intelligence required for the car to think for itself and plan the route it should take, on any surface.
JLR surface identification and 3D path-sensing research combines camera, ultrasonic, radar and LIDAR sensors to give the car a 360-degree view of the world around it, with sensors so advanced the car could determine surface characteristics, down to the width of a tire, even in rain and falling snow, to plan its route.
“The key enabler for autonomous driving on any terrain is to give the car the ability to sense and predict the 3D path it is going to drive through,” Harper says.
“This means being able to scan and analyze both the surface to be driven on, as well as any hazards above and to the sides of the path ahead. This might include car park barriers, tree roots and boulders or overhanging branches, as well as the materials and topography to be driven on.”
Ultrasonic sensors can identify surface conditions by scanning up to 16.4 ft. (5 m) ahead of the car to allow terrain response settings to automatically change before the car drives from tarmac to snow or from grass to sand.
Overhanging branches also would need to be identified to determine if the route ahead is clear. Overhead-clearance assist uses stereo-camera technology to scan ahead for overhead obstructions.
The driver will be able to program the system with the vehicle’s height, which can include roof boxes or bicycles, and the car will warn the driver with a simple message in the infotainment touchscreen if there is insufficient clearance.
Sensors could determine the roughness of the way ahead and adjust vehicle speed. The speed-control system uses cameras to sense bumpy terrain, including uneven and undulating surfaces and washboard roads, potholes and even standing water. It would then predict the potential impact of these surfaces on the car’s ride and adjust the speed to keep passengers comfortable.
In the world’s first off-road demonstration, JLR connected two Range Rover Sports together using innovative dedicated short-range communications technology to create an off-road connected convoy.
The wireless vehicle-to-vehicle (V2V) communications system shares information including vehicle location, wheel slip, changes to suspension height and wheel articulation, as well as all-terrain progress control and terrain-response settings instantly between the two vehicles.
Harper says the V2V system can seamlessly link a convoy of vehicles in any off-road environment.
“If a vehicle has stopped, other vehicles in the convoy will be alerted,” he says. “If the wheels of one drop into a hole, or perhaps slip on a difficult boulder, this information is transmitted to all of the other vehicles. In the future, a convoy of autonomous vehicles would use this information to automatically adjust their settings or even change their route to help them tackle the obstacle.”
JLR says the autonomous cars could even act as tour guides.
“For the ultimate safari experience, cars following in convoy would be told by the lead car where to slow down and stop for their passengers to take the best photographs,” Harper says.
