Stanford Built an Autonomous Electric DeLorean Called MARTY

Stanford University engineering students have built a self-driving autonomous car. The students took a vintage 1981 DeLorean and redesigned it into an electric autonomous car. The car is capable of precise drifting at large angles.

The drifting feature was added to study how cars perform in extreme situations. The data collected will help in the development of autonomous safety protocols. The project was carried out under the tutelage of Stanford Professor Chris Gerdes. 

The car has been named MARTY. MARTY stands for Multiple Actuator Research Test bed for Yaw control. The name ‘Marty’ also pays homage to the Back to the Future films. The films released in the 80’s used a 1981 DeLorean as a time machine.  

The car was unveiled by Chris Gerdes and his students yesterday. Marty is actually a test bed for researching the physical limits of autonomous driving. The project was carried out in collaboration with the Revs Program at Stanford and Renovo Motors. Marty was released and added to Stanford’s research fleet. The car is already proving to be excellent for student driven research. 

According to Gerdes they wanted to design an automated vehicle which can avoid accidents through its actions. The law of physics will be the limitation of the car. But the software is being developed to manoeuvre the car within limits. The idea for the car was taken from the film Back to the Future.

“We want to design automated vehicles that can take any action necessary to avoid an accident,” Gerdes said. “The laws of physics will limit what the car can do, but we think the software should be capable of any possible maneuver within those limits. MARTY is another step in this direction, thanks to the passion and hard work of our students. Stanford builds great research by building great researchers.”

A student in Gerdes Dynamic Design Lab (DDL) thought about the types of research. The mechanical engineer and graduate student Jonathan Goh was responsible for the idea.  

According to Goh he focused on Electronic stability control or ESC in cars. The ESC is a feature in cars that ensures cars are safely handled. The ESC is responsible for applying brakes to certain wheels and even cutting engine power at times. 

Gerdes further shared some of the conclusions derived from their experiments. Gerdes found out at times sacrificing the stability of a car is necessary. In case of an accident to avoid collision and accidents sharp turns are necessary. Rally car drivers take sharp turns all the time.

“In our work developing autonomous driving algorithms, we’ve found that sometimes you need to sacrifice stability to turn sharply and avoid accidents,” Gerdes said. “The very best rally car drivers do this all this time, sacrificing stability so they can use all of the car’s capabilities to avoid obstacles and negotiate tight turns at speed. Their confidence in their ability to control the car opens up new possibilities for the car’s motion. Current control systems designed to assist a human driver, however, don’t allow this sort of maneuvering. We think that it is important to open up this design space to develop fully automated cars that are as safe as possible.”

They sacrifice the stability of the car to avoid obstacles. This way they can negotiate tight turns. The ability to control the car leads to more possibilities in the car’s motion. Autonomous control systems do not all such types of maneuvering. Gerdes and his team believe developing drifting automated cars can open up the design space. The cars can then find a way to be safe. 

“When you watch a pro driver drift a car, you think to yourself that this person really knows how to precisely control the path and angle of the car, despite how different it is from normal driving,” Goh said. “The wheels are pointed to the left even though the car is turning right, and you have to very quickly coordinate the throttle and steering in order to keep the car from spinning out or going the wrong way. Autonomous cars need to learn from this in order to truly be as good as the best drivers out there.”

Additionally in case of autonomous cars they have to handle all the operations. The biggest challenge the team is facing right now is programming Marty while creating an autonomous system.

The self-driving system needs to be safe for stability and fluidity. The coordination required while drifting is of a very high level. The car needs to be on the right path and angle for drifting and making sure it does not spin out of control. Self-driving cars need to learn the coordination involved in drifting to be as good as human drivers.

“The sublime awesomeness of riding in a DeLorean that does perfect, smoke-filled doughnuts by itself is a mind-bending experience that helps you appreciate that we really are living in the future,” Goh said.

The next step of the experiment will be to teach the self-driving cars how to race. The cars will learn all the tools necessary to navigate the cars. In MARTY all the controls of the car are managed by a central API system. The ultimate goal set for MARTY is to be able to drift alongside a professional driver. 


“The project moved quickly, and we were able to achieve real research results of our autonomous algorithms on MARTY’s very first test,” Gerdes said.

“Stanford is a world leader in autonomous vehicle research, so partnering with them is an amazing opportunity. Having brilliant, hard-working students embedded here in our facility, conducting research and collaborating on MARTY, is a great experience,” said Christopher Heiser, CEO and co-founder of Renovo Motors.

“Using our platform, the team built a working version of MARTY in a matter of months and moved into research very quickly after that. I think we’re demonstrating how collaboration between Silicon Valley and universities can really work.”

“A drift competition is the perfect blend of our two most important research questions – how to control the car precisely and how to design automated vehicles that interact with humans,” Gerdes said.

“While we aren’t picturing a future where every car produces clouds of white tire smoke during the daily commute, we do want automated vehicles that can decipher the subtle cues drivers give when driving and incorporate this feedback when planning motion. Drifting is a way to study these larger questions, with style.”

Originally posted in i4u News

Related Posts

About The Author