Computer scientists have been at the self-driving vehicle problem for longer than you might think. Early research into the automated logic required for autonomous cars was [published](http://dl.acm.org/citation.cfm?id=1624819) in the mid-70s, while the first fully robotic van came around in the early-80s courtesy of Ernst Dickmanns and his team at Bundeswehr University Munich. Efforts at Carnegie Mellon, meanwhile, were pushing the technology on the other side of that Atlantic. First came Terregator, in 1983 ([via IEEE Spectrum](http://spectrum.ieee.org/automaton/robotics/robotics-hardware/video-friday-rescue-quadruped-gesture-controlled-robot-arm-self-driving-van-1986)):

Terregator

A rugged testbed for outdoor, robotic navigation. It pioneered exploration, road following and mine mapping.

The great, great grandfather of self-driving cars.

From:

https://www.ri.cmu.edu/pub_files/pub1/champeny_bares_1991_1/champeny_bares_1991_1.pdf

The Terregator (Terrestrial Navigator) is a driverless outdoor vehicle developed for autonomous navigation research. Application areas for autonomous vehicle technology include undersea exploration, transportation, hazardous waste mapping, material handling, and exploration of planetary surfaces.
Terregator subsystems include locomotion, power, computation, controls, wireless telemetry (serial links and two channels of UHF video), orientation sensors, and navigation payloads. The Terregator is more capable, adaptable, and survivable than indoor pilotless vehicles. Its six-wheel drive provides superior locomotion to negotiate three-dimensional terrain, and its power and scale enable it to overcome obstacles and grades that pose entrapment, tipover, or pitfalls to lesser locomotors. The Terregator can subtend moves of millimeter resolution at speeds of zero to several miles per hour. The vehicle is modularized to facilitate fault diagnosis, component changeout and system evolution.
In research to date, the Terregator has deployed three kinds of sensors: video cameras, a sonar ring, and a scanning laser range finder. See Figure 1-1 on page 8. The cameras give reflectance information, the sonar measures distance, and the laser scanner senses both. Using these sensing modes, the Terregator has successfully navigated sidewalks and off- road areas, and has mapped a portion of a mine. The Terregator supports evolution into fuller navigation systems with path planning and mapping capabilities. The extensible options provided by an adaptable vehicle are invaluable to the research setting. This project is committed to making significant advancement towards an autonomous vehicle capable of mobile tasks in an outdoor environment.

Terregator - CMU - Field Robotics Circa 1983

Piloting city streets wasn't yet part of the plan. Then came NavLab, in 1986.

NavLab or Navigation Laboratory was the first self-driving car with people riding on board.  It was very slow, but for 1986 computing power, it was revolutionary. NavLab continued to lay the groundwork for Carnegie Mellon University's expertise in the field of autonomous vehicles.

https://en.wikipedia.org/wiki/Navlab

NavLab 1 (1986) : Carnegie Mellon : Robotics Institute History of Self-Driving Cars

Yeah, it's pretty quaint, but machine vision algorithms, in particular, were still young. In 1989, Carnegie Mellon pioneered [a neural network called ALVINN](http://repository.cmu.edu/cgi/viewcontent.cgi?article=2874&context=compsci) that could be employed in road following tasks in certain field conditions. It used machine learning to watch human drivers and adapt its own strategies. ALVINN would become the precursor to the self-driving technology of today.

Motherboard

video

Tech

The NavLab was slow and huge, but it provided data that would help pave the way for the self-driving world of today.

FYI.

This story is over 5 years old.

Carnegie Mellon's 1986 Self-Driving Van Was Adorable

FYI.

This story is over 5 years old.

Carnegie Mellon's 1986 Self-Driving Van Was Adorable

ONE EMAIL. ONE STORY. EVERY WEEK. SIGN UP FOR THE VICE NEWSLETTER.