What are Mobile Robots in Artificial Intelligence? Brief Explanation

The hand–eye systems described earlier might be thought of as “robots,” but they could not move about from their fixed base. Up to this time, very little work had been done on mobile robots even though they figured prominently in science fiction. I have already mentioned Grey Walter’s “tortoises,” which were early versions of autonomous mobile robots. In the early 1960s researchers at the Johns Hopkins University Applied Physics Laboratory built a mobile robot they called “The Beast.” (See Fig. 12.1.) Controlled by on-board electronics and guided by sonar sensors, photocells, and a “wallplate-feeling” arm, it could wander the white-walled corridors looking for dark-colored power plugs. Upon finding one, and if its batteries were low, it would plug itself in and recharge its batteries. The system is described in a book by Hans Moravec.1 Beginning in the mid-1960s, several groups began working on mobile robots. These included the AI Labs at SRI and at Stanford. I’ll begin with an extended description of the SRI robot project for it provided the stimulus for the invention and integration of several important AI technologies.

Shakey, the SRI Robot

In November 1963, Charles Rosen, the leader of neural-network research at SRI, wrote a memo in which he proposed development of a mobile “automaton” that would combine the pattern-recognition and memory capabilities of neural networks with higher level AI programs – such as were being developed at MIT, Stanford, CMU, and elsewhere. Rosen had previously attended a summer course at UCLA on LISP given by Bertram Raphael, who was finishing his Ph.D. (on SIR) at MIT. Rosen and I and others in his group immediately began thinking about mobile robots. We also enlisted Marvin Minsky as a consultant to help us.

Minsky spent two weeks at SRI during August 1964. We made the first of many trips to the ARPA office (in the Pentagon at that time) to generate interest in supporting mobile robot research at SRI. We also talked with Ruth Davis, the director of the Department of Defense Research and Engineering (DDR&E) – the office in charge of all Defense Department research. We wrote a proposal in April 1964 to DDR&E for “Research in Intelligent Automata (Phase I)” that would, we claimed, “ultimately lead to the development of machines that will perform tasks that are presently considered to require human intelligence.”2 The proposal, along with several trips and discussions culminated, in November 1964, in a “work statement” issued by the then-director of ARPA’s Information Processing Techniques Office, Ivan Sutherland

In the meantime, Bertram Raphael completed his MIT Ph.D. degree in 1964 and took up a position at UC Berkeley for an academic year. In April 1965, he accepted our offer to join SRI to provide our group with needed AI expertise. After several research proposal drafts and discussions with people in the relevant offices in the Defense Department (complicated by the fact that Ivan Sutherland left ARPA during this time), SRI was finally awarded a rather large (for the time) contract based essentially on Sutherland’s work statement. The “start-work” date on the project, which was administered for ARPA by the Rome Air Development Center (RADC) in Rome, New York, was March

17, 1966. (Coincidentally, just before joining SRI in 1961, I had just finished a three-year stint of duty as an Air Force Lieutenant at RADC working on statistical signal-processing techniques for radar systems.) Ruth Davis played a prominent role in getting ARPA and RADC to move forward on getting the project started. 

The “knitting together” of several disparate AI technologies was one of the primary challenges and one of the major contributions of SRI’s automaton project.4 One of the tasks was the actual construction of a robot vehicle whose activities would be controlled by a suite of programs. Because of various engineering idiosyncrasies, the vehicle shook when it came to an abrupt stop. We soon called it “Shakey,” even though one of the researchers thought that sobriquet too disrespectful. [Shakey was inducted into the “Robot Hall of Fame” (along with C-3PO among others) in 2004.5 It was also named as the fifth-best robot ever (out of 50) by Wired Magazine in January 2006. Wired’s numbers 2 and 4 were fictional, “Spirit” and ”Opportunity” (the Mars robots) were number 3, and “Stanley” (winner of the 2005 DARPA “Grand Challenge”) was named “the #1 Robot of All Time.” Shakey is now exhibited at the Computer History Museum in Mountain View, California.]6 Shakey had an on-board television camera for capturing images of its environment, a laser range finder (triangulating, not time-of-flight) for sensing its distance from walls and other objects, and cat-whisker-like bump detectors. Shakey’s environment was a collection of “rooms” connected by doorways but otherwise separated by low walls that we could conveniently see over but Shakey could not. Some of the rooms contained large objects. 

The size of Shakey can be discerned from inspection of Fig. 12.4. Most of the programs that we developed to control Shakey were run on a DEC PDP-10 computer. Between the PDP-10 and the mobile vehicle itself were a PDP-15 peripheral computer (for handling the lower level communications and commands to on-board hardware) and a two-way radio and video link. The PDP-10 programs were organized in what we called a “three-layer” hierarchy. Programs in the lowest level drove all of the motors and captured sensory information. Programs in the intermediate level supervised primitive actions, such as moving to a designated position, and also processed visual images from Shakey’s TV camera. Planning more complex actions, requiring the execution of a sequence of intermediate-level actions, was done by programs in the highest level of the hierarchy. The Shakey project involved the integration of several new inventions in search techniques, in robust control of actions, in planning and learning, and in vision. Many ofthese ideas are widely used today. The next few subsections describe them.