Autonomous Vehicle Tower of Babble Growing

Ford Motor Standard Self-Driving Car Language to Communicate Intent under testing.

As automakers speedup their molting into mobility companies, they are outrunning the design, development, legal and social mores that have been come into play in the evolving business for the last century. The latest Michigan-sized potholes on the road to self-driving cars is the lack of standards governing the industry. Common practices are lacking, as are the unknown vehicles that ultimately will be salable.

NHTSA has asked SAE International to develop Autonomous vehicle safety testing protocols and guidelines. SAE formally announced this Automated Driving Systems (ADS) Safety Performance Testing Program at the end of August during CAR’s annual Management Briefing Seminar in Northern Michigan. The initiative establishes a network with SAE, government, industry and researchers to develop and create new standards for AV testing. (read AutoInformed.com on SAE to Administer Autonomous Testing Program)

This program is long, long overdue with Google and automakers such as Daimler, GM, Ford Motor and FCA – among others – are well underway to turning loose on the untrained public semi-automated and fully automated vehicles. Waymo – the Google driverless car will be in service in Arizona this fall. Apple is expanding its fleet of driverless vehicles in California.

So, it’s no surprise that Ford Motor is calling for a “Standard Self-Driving Car Language to Communicate Intent.” Think of this as more sophisticated turn signals – perhaps the most underused safety item on current cars – and brake lights. Only here the intent is to signal to pedestrians what the car is going to do and to the hapless passengers inside the Autonomous Vehicle, who are literally along for the ride.

Ford has already done work in this area that is now open to competitors through a memorandum of understanding that is intended to make it easy for all automakers to work together.

“Why is this the best approach?” asks John Shutko, Ford Human Factors Technical Specialist for Self-Driving Vehicles. “We want everyone to trust self-driving vehicles - no matter if they are riders in these vehicles themselves or pedestrians, cyclists, scooter users or other drivers sharing the road. Having one, universal communication interface people across geographies and age groups can understand is critical for the successful deployment of self-driving technology.”

That pedestrians, cyclists and scooter users should change their behavior to accommodate self-driving cars is not how this technology should be integrated in Ford’s view. But how to make self-driving vehicles blend with other road users?

Ford wants all self-driving vehicle developers, automakers and technology companies who are committed to deploying SAE level-4 vehicles that are one step short of full automation to share ideas to create an industry standard for communicating driving intent, whether it be driving, yielding or accelerating from a stop. Having a universal communication interface people across geographies and age groups can understand is critical for the successful deployment of self-driving technology in Ford’s view.

Self-driving Intent Interface

Last year, Ford used the Virginia Tech Transportation Institute (VTTI) to conduct a real-world study of the self-driving intent interface, a light-bar mounted to the top of a windshield of a Ford Transit Connect van.

Three different lighting scenarios, as well as a baseline condition where the lights were off, were tested to observe how pedestrians and other road users responded to the vehicle signaling its intent:

• Yielding: Two white lights moving side to side to indicate vehicle is about to come to a full stop
• Active driving mode: Solid white light to indicate vehicle intends to proceed on its current course, but allegedly can respond appropriately to objects and other road users during its travel
• Start-to-go: Rapidly blinking white light to indicate vehicle is beginning to accelerate from a stop

The initial design and then testing in virtual reality scenarios in Ford’s opinion confirmed the learn-ability of the initial signal.