Toyota Finds ‘Extreme’ Test Site for New Self-Driving Car

Toyota Research Institute (TRI) will test its Platform 2.1 autonomous driving system at California’s GoMentum Station. TRI said "GoMentum’s varied terrain, and real-life infrastructure including roads, bridges, tunnels, intersections and parking lots provide the environment needed to accelerate testing of" autonomous vehicles.

The Toyota Research Institute (TRI) has found a new location to put its Platform 2.1 autonomous driving system to the test. TRI has signed an agreement with California’s GoMentum Station, a site in Concord that has 20 miles of paved roads on a 5,000-acre former U.S. Navy weapons station.

Not only is the testing site close to TRI’s headquarters in Los Altos, Calif., the company says “GoMentum Station augments TRI’s public road testing with testing of extreme driving events that are unsafe to conduct on public roads. GoMentum’s varied terrain, and real-life infrastructure including roads, bridges, tunnels, intersections and parking lots provide the environment needed to accelerate testing of the ‘difficult miles’ needed to advance both Guardian and Chauffeur.”

Guardian and Chauffeur represent TRI’s two-prong approach to autonomous vehicles, both of which use a modified Lexus LS 600hL with two steering wheels. Guardian is essentially a driver-assist mode in which the human maintains control of the car, and the automated driving system operates in the background, monitoring for potential crash situations. It can intervene to protect vehicle occupants when needed.

Chauffeur mode is TRI’s research into a Level 4/Level 5 autonomous vehicle where the car drives itself. Both driving modes include a high-fidelity LIDAR system from startup Luminar and a much denser point cloud to better detect objects.

As for the two steering wheels, TRI said “this setup allows the research team to probe effective methods of transferring vehicle control between the human driver and the autonomous system in a range of challenging scenarios. It also helps with development of machine learning algorithms that can learn from expert human drivers and provide coaching to novice drivers.”

At CES 2017, TRI CEO Gill Pratt, winner of the 2017 Engelberger Robotics Awards for Leadership, said fully autonomous cars are “not even close.” One of the major issues is the hand-off of control between the autonomous driving system and the human. A car driving 65 MPH travels around 100 feet every second, Pratt said. To give a disengaged driver 15 seconds of warning in a car traveling at that speed, the car must spot trouble about 1500 feet away. That’s extremely hard to guarantee, and unlikely to be achieved soon.

To keep humans engaged in autonomous vehicles, Toyota unveiled at CES 2017 its Yui platform that uses artificial intelligence to measure one’s mood and engage in chitchat and more. Yui can also use light, sound, and even touch throughout the car’s cabin to relay critical information to the driver.

Toyota plans to start testing a car equipped with Yui on Japanese roads in 2020.

While some companies, such as Tesla, Uber, and Alphabet’s Waymo, are working on fully autonomous vehicles that they predict will be commonplace on roads soon, Toyota has taken a different approach.

“We believe that autonomy will be an increasingly important part of the automotive landscape, but drivers are likely to be a significant part for decades,” Jim Adler, managing director of Toyota AI Ventures and a RoboBusiness 2017 speaker, said. “We think the transition will be gradual, but it will happen.”

TRI launched in Silicon Valley in 2016, with two additional facilities opening in Massachusetts and Michigan.


About the Author

Steve Crowe · Steve Crowe is managing editor of Robotics Trends. Steve has been writing about technology since 2008. He lives in Belchertown, MA with his wife and daughter.
Contact Steve Crowe:  ·  View More by Steve Crowe.


Log in to leave a Comment

Editors’ Picks

10 Best Robots of CES 2018
Self-driving cars were the talk of Las Vegas during CES 2018. We recap...

Top 10 AI & Robot Stories of 2017
2018 is shaping up to be a massive year for automation. But first,...

Breaking Down Autonomous Systems
Future tech: Autonomous intelligence

Robots are Learning to Pick up Objects Like Babies
UC Berkeley has developed a technique that enables robots to complete tasks...