Unmanned Systems Technology 006 | ECA Inspector Mk2 USV | Antenna systems | Northwest UAV NW-44 | Unmanned ground vehicles | Navigation systems | Lunar X challenge

61 Unmanned ground vehicles | Insight Unmanned Systems Technology | February/March 2016 “Maps developed by other companies don’t always work in snow-covered landscapes,” says Ryan Eustice, associate professor at the University of Michigan’s College of Engineering. “The maps we created with Ford contain useful information about the 3D environment around the car, allowing the vehicle to localise itself even with a blanket of snow covering the ground.” The maps are created while driving in the test environment in favourable weather, with the software automatically tagging features such as traffic signs, trees and buildings. When the vehicle can’t see the ground, it detects above- ground landmarks to pinpoint itself on the map, and then subsequently uses the map to drive in bad weather. “The vehicle’s normal safety systems, like electronic stability control and traction control, which are often used on slippery winter roads, work with the autonomous driving software,” says Jim McBride, Ford’s technical leader for autonomous vehicles. “We eventually want our autonomous vehicles to detect deteriorating conditions, decide whether it’s safe to keep driving, and if so, for how long.” Ford is using Velodyne’s latest Lidar sensors – called Ultra PUCK Auto – on the current platform. It uses a solid-state laser to scan at a range of 200 m, further than previous systems, and reduce the size of the sensor so that two can be mounted on the wing mirrors, rather than four around the vehicle. The sensors are tightly integrated with the development and validation of Ford’s virtual driver software, as the positioning and the longer range can handle different driving scenarios. ”Adding the latest generation of computers and sensors, including the smaller and more affordable PUCK Autos, helps bring Ford ever closer to having a fully autonomous vehicle ready for production,” says McBride. These third-generation Brand Supplier Status Public Fleet Tesla in-house Autopilot, 12 Summoning General Motors Delphi L4 1 Audi Delphi L4 2 Volvo Bosch L4 1 Ford Google/Bosch L4 30 VW Delphi/Bosch L4 2 Mercedes-Benz Continental L4 5 Nissan NASA Autopilot 2 BMW Continental Autoparking 1 Honda in-house L4 1 Toyota Nippon Denso L4 1 Google in-house, L5 49 Google Lexus (Toyota) L4 24 Cruise Automation in-house Autopilot 2 Delphi in-house L4 1 Driverless car development The maps contain useful information about the 3D environment, allowing the vehicle to localise itself even with a blanket of snow on the ground Ford is testing its third-generation autonomous ground vehicles in difficult conditions such as snow as part of its advanced engineering project (Courtesy of Ford)