Ford calls for a standard self-driving car language
Ford announced that is looking for input and collaboration from all parties committed to deploying SAE Level 4 vehicles to create an industry standard for communicating driver intent, whether for driving, yielding, or accelerating from a stop. John Shutko, Ford Human Factors Technical Specialist for self-driving vehicles, said, “The work we’ve already done is now open to others through a memorandum of understanding that is intended to make it easy for us all to work together.”
Having a universal communication interface for people across geographies and age groups is important because, for successful deployment of self-driving technology, they need to be able to trust the technology, the company says.
Following initial design and testing via virtual reality scenarios, Ford completed a real-world study last year with Virginia Tech Transportation Institute to evaluate a self-driving intent interface consisting of a light bar mounted to the top of a windshield of a Ford Transit Connect van. The driver was concealed by a special seat suit to simulate a self-driving car. Three different lighting scenarios were tested, as well as a baseline condition where the lights were off, to observe how pedestrians and other road users responded to the vehicle signaling its intent.
The light bar shows intent to yield via two white lights moving from side to side to indicate the vehicle is about to come to a full stop. Active driving mode is shown by a solid white light to indicate the vehicle intends to proceed on its current course (although it can respond appropriately to objects and other road users). Start-to-go is revealed by a rapidly blinking white light to indicate the vehicle is beginning to accelerate from a stop.
The test results showed that the light signal interface did not encourage unsafe behavior by other road users. Additional study in the virtual reality space revealed that, with no prior explanation of what the different signals meant, it took about two exposures for participants to learn what a single signal meant and between five and 10 exposures to understand the meaning of all three lighting patterns. The signals also had a positive effect on people’s trust in self-driving vehicles.
Ford is now installing the self-driving intent interface on Fusion Hybrid self-driving development vehicles to be used by Argo AI in Miami-Dade County to observe reactions of pedestrians and other road users to the light bar. It is also conducting research in Europe to ensure that the signals are universally understood across regions and cultures.
In addition to the proposal to accelerate the industry coming together to work toward standardization, Ford said it continues to work with the International Organization of Standardization (ISO) and the Society of Automotive Engineers (SAE) to create a unified communication interface for self-driving vehicles. The goal is to reach agreement in three core areas—placement of the signals on a vehicle, design of the signals, and the color of the light signals. To help anyone interested in collaborating, Ford said it is open to sharing the scenarios developed for the virtual reality study.