The Ohio State University College of Engineering is working to create a zero-emission truck – The Daily Barometer

Oregon State University students and faculty are currently working with Daimler Truck North America on SuperTruck 3, which aims to create a zero-emissions hydrogen-based truck using artificial intelligence.

The project was announced in January, and designs for the project are scheduled to be revealed in 2027. This will be the third Daimler SuperTruck project.

The goal of this project is to create a “proof-of-concept truck,” said Devin Crowley, a Ph.D. in artificial intelligence and robotics. student at Ohio State University who was funded by Daimler, who worked on the SuperTruck 3 project. The truck itself will not be mass-produced, but the truck’s technology could be used in the future.

Trucks are steered by a control unit that decides how much power to distribute to the truck when going up or down a hill, when turning, or when accelerating or slowing down. Previous consoles were hand-written by someone.

“Because it’s basically hand-tuned, it’s never going to be absolutely perfect, and it’s a lot of work to design it,” Crowley said of the controller he was trying to improve. “The approach I’m putting forward is a learning controller to do the same logic, but learning.”

Crowley states that the downside of the old controller is that it is not very efficient, and the controller takes longer to research what to do in a given situation. There are “lookup tables” that the controller can refer to, but Crowley’s design would take less time and would be less work for an actual person.

Using artificial intelligence, Crowley is also trying to make the controller have the ability to know its path before it starts driving so it can prepare for the maneuvers it needs to make. These controllers will also be cheaper and more optimized than engineered ones.

Alan Fern, a professor at Ohio State University’s College of Engineering, also helped work on the project, describing the idea of ​​a learning controller as “reinforcement learning.”

“Basically, we are training the controller to turn handles in a simulation of a fuel cell truck in order to optimize the performance metric of interest (such as efficiency),” Verne said in an email. “After several thousand or even millions of simulation experiences used for learning, the improved controller can then be tested in the real world.”

A hydrogen-based fuel cell is a technology that relies on hydrogen when batteries or other renewable energy sources don’t get the job done on their own.

The battery also has regenerative braking, which means that when the truck is going downhill, it regenerates energy, making it last longer before needing the assistance of a hydrogen-based fuel cell.

The hydrogen-based fuel cell and renewable battery will work together in the truck to meet the terrain and road conditions on which the truck will be driven. This makes the truck more efficient than its predecessors.

“As hydrogen production technology improves, this could be a great way to allow for a robust power grid that relies largely on renewables,” Verne said. “But hydrogen is produced as a backup when renewable energy sources are not enough.”

According to Verne, since the purpose of this project is to develop a proof of concept for the truck, AI technology may or may not be used in the future depending on the results of the project.