Notes on the history of robotics at USC, by Prof. Bekey

I think it is fair to say that I started robotics at USC by lifting myself by my bootstraps. I became interested in the field about 1980 and started searching for ways to make robotics at USC a reality, but my own research had been in other areas (like system identification and biomedical engineering). There were two events that helped us start robotics at USC. I recruited Barry Soroka, who joined us as an Assistant Professor in 1981. He had worked on robot manipulators at Stanford University. I learned a lot from him (He is now with the Computer Science Department at California Polytechnic University in Pomona). The second event was that I obtained an NSF grant to purchase our first robot: A PUMA 560 industrial manipulator (about 1982?) Such manipulators are familiar because we see them on TV helping to assemble automobiles (bringing a door into position, for example) or using a welding torch to weld part of the body together. With this machine Barry and I started the first robotics lab at USC. We ambitiously called it "The USC Robotics Institute", after the successful major activity at Carnegie-Mellon University. The Provost gave use a small start-up fund and we were in business.

About this time we began teaching courses called "Introduction to Robotics", which were concerned almost entirely with the mathematical description and control of multi-jointed experiments as part of the course. All they could do was to pick up an item at a given location and move it to another location, sometimes stacking two blocks on top of each other. These little robots were controlled by very easily Apple II computers.

Our stock of robots increased rapidly thereafter, as a result of several gifts. A Northrop Corp. laboratory was being closed and we received several large industrial manipulators. There was no space for them, so they were stored at Central Receiving for years. At this time we had 3 or 4 graduate students working in the lab.

An interesting aspect of our robotics program in the late 1980s was due to the arrival of Prof. Margo Apsotolos in the Dance Department. Margo had written her dissertation at Stanford on programming manipulators to move gracefully to music. Imagine a large (say 8 foot long) arm with its "shoulder" fasted to the ground, and the arm (including elbow, wrist and "hand") would move in graceful curves. Margo then developed "robot choreography" where human dancers would move with and around several wiggling robot arms. Several such performance were give at USC.

The "Robotics Institute" merge into a major computer vision program directed by Prof. Ram Nevatia; the combined program was called Institute for Robotics and Intelligent Systems (IRIS), but the robotics lab operated quite independently.

During the period from about 1985-90 I became interested in building hands for robots that were not just simple grippers, but that resembled five fingered human hands. A colleague in the former Yugoslavia had build a 5-fingered hand, but it lacked computer control and sensors. We obtained the hand, connected it to a computer, and used it in a number of research projects. I received several grants to study robot hands, including their potential use a s prostheses for people who may have lost their hand in an accident. Our laboratory had several robot manipulators. My first PhD student in robotics graduated in 1986, to be followed by 10 others between 1987 and 2000.

In the late 1980s and early 90s we became interested in mobile robots. Since commercial mobile robots were very expensive, and we had no funding for such proposes, my students and I build several interesting machines. "Rodney" was a six legged walking machine (the name was inspired by Prof. Mataric's major professor, Rodney Brooks at MIT). The unique aspect of this robot was that we developed the software to enable it to learn to walk, using a simulated form of evolution. We did not program the sequence in which the robot should move its legs, so it would fall down frequently, until it learned to walk with a "tripod gait", also used by insects. In this gait the robot (and insects) move the front and rear legs on one side and the center leg on the other side at the same time, thus keeping a "tripod" of support at all times and remaining stable. We also build Marvin (named after one of the pioneers of robotics, Prof. Marvin Minsky of MIT). This was a converted toy car, which learned to roam about the lab without running into anything.

From the handful of students who worked with us in the mid 1980s, by 1990 we had some 10-15 students participating in robotics work at various levels, including several very bright undergraduates.

Once we moved from manipulators and robot hands to mobile robots, there was no turning back. We built a number of other robots, including one more walking machine (actually designed by our Assistant Professor Gaurav Sukhatme as part of his PhD research). We also began struggling with robot helicopters in the early 1990s and actually won a national competition among universities designing and building autonomous flying machines.

In the late 1980s Prof. Michael Arbib joined us from Univ. of Mass, where he had directed a "Laboratory for Perceptual Robotics". His arrival broadened our course offerings as well as our research.

By about 1996 we were achieving some recognition for our research, since we presented many papers at national and international robotics competitions. We had some 20 students in the program. I was successful in a number of research proposals, so that we had between $250,000 and $500,000 of research funding per year. In 1996 I was appointed Associate Dean of the School of Engineering. I accepted the position on the condition that I would be authorized to recruit another faculty member in robotics. We began a nationwide search in the fall of 1996 and Prof. Mataric joined us in the fall of 1997. Dr. Sukhatme, who completed his PhD work in 1997, was a Research Assistant Professor from 1997 to 2000, when he was named Assistant Professor.