Smart Road Markers, Chatting to Vehicles Over LoRa, Could Make Autonomous Vehicles Safer

Researchers from Western Michigan University and the Oak Ridge National Laboratory (ORNL) have come up with a new approach to improving the efficiency and safety of autonomous vehicles — by embedding chips in pavement markers for better lane line detection.

"We are working to make autonomous driving features accurate and safe in more remote areas," says ORNL researcher Ali Ekti of the work, in partnership with lead author Sachin Sharma and colleagues. "And we are doing it by converting a dummy piece of infrastructure into something with many more uses."

That "dummy" infrastructure: pavement markers, small blocks raised from the surface of the road and with reflectors inside to passively highlight lane markings by vehicle headlights at night. Keeping that basic functionality intact, the team sought to make the markers more useful to autonomous vehicle systems as well as human drivers — by embedding some smart technology within.

Dubbed a Chip-Enabled Raised Pavement Marker, or CERPM, the smart devices — fitted entirely inside an off-the-shelf pavement market which had been milled out to make room — are built around a Heltec Automation WiFi LoRa 32 development board, programmed using the Arduino IDE to transmit the marker's exact GPS coordinates and a unique identification tag. This is then received by another WiFi LoRa 32 board a Kia Niro Hybrid 2016-based autonomous research vehicle and processed by a Python program and the Robot Operating System (ROS).

The result: the vehicle receives a clear indication of the shape and driveable area of the road, even when its camera or LIDAR sensors are obscured and while reducing the computational load of the autonomous vehicle's computer system — and over a distance of up to 410 meters (around 1,345 feet), over four times their initial target. In field testing, the prototype markers worked in all weather conditions — though the issue of powering them over long periods of time remains unsolved.

"With the hindsight of 10 years of highly-funded development, we now know that software and cameras alone don’t provide an easy solution," says co-author Zachary Asher. "Perhaps a more patient approach, using infrastructure-based hardware in coordination with government transportation agencies, is the way to achieve zero-accident vehicles which actually use energy sustainably."

The team's work has been published in IEEE Sensors under closed-access terms, while an open-access copy is available through the US Department of Energy's Office of Scientific and Technical Information.

Main article image courtesy of Carlos Jones/ORNL.