ROBART I was Bart Everett's thesis project at the Naval Postgraduate School in Monterey, CA (Everett, 1982a; 1982b) and one of the very first behavior-based autonomous robots ever built. The navigation scheme provided a layered hierarchy of behaviors (see Table below) that looked ahead for a clear path (high-level), reactively avoided nearby obstacles (intermediate-level), and responded to actual impacts (low-level). A basic tenet of this strategy was the ability of certain high-level deliberative behaviors to influence or even disable the intermediate and low-level reactive behaviors, such as when docking with the recharging station, for example.
|Look ahead for encroaching obastacles|
Look for opening in forward hemispher
Home in on recharging station
|Seek clear path along new heading|
Follow adjacent wall in close proximity
|Veer away from close proximity|
Veer away from physical contact
ROBART I's assigned function was to patrol a home environment, following either a random or set pattern from room to room, checking for unwanted conditions such as fire, smoke, intrusion, etc. The security application was chosen because it demonstrated performance of a useful function and did not require an end-effector or vision system, significantly reducing the required system complexity. Provision was made for locating and connecting with a free-standing recharging station when battery voltage began running low. Patrols were made at random intervals, with the majority of time spent immobile in a passive intrusion-detection mode to conserve power.
A Synertek SYM-1 single-board computer formed the heart of the onboard electronics. Speech synthesis (to allow the system to announce any unwanted conditions detected in the course of a random patrol) was implemented through National Semiconductor's Digitalker DT1050 synthesizer chip. Two sets of vocabulary instructions were stored on EPROMs for a total vocabulary of 280 words. A fixed vocabulary was chosen over an unlimited vocabulary created through use of phonemes in light of the greatly decreased demand on the onboard microprocessor in terms of execution time and memory space.
The software maintained the robot in one of two modes of operation: Alert Mode or Passive Mode. In the Passive Mode, the majority of sensors were enabled, but a good deal of the interface and drive control circuitry was powered down to conserve the battery. The robot relied on optical motion detection, ultrasonic motion detection, and hearing to detect an intruder, while at the same time monitoring for vibration (earthquake), fire, smoke, toxic gas, and flooding (Everett, 1982a). Some of these inputs were hard-wired to cause an alert (switch from Passive Mode to Alert Mode), whereas others had to be evaluated first by software that could then trigger an alert if required. Either mode could be in effect while recharging, and recharging could be temporarily suspended if conditions so warranted.
Recharging was handled automatically. The 12-volt 20-amphour lead-acid battery gave about 6 hours of continuous service and then required 12 hours of charge. Roughly one hour of power was available to locate the charging station (by means of a visual homing beacon) after the battery monitor circuits detected a low condition. The homing beacon was activated by a coded signal sent out from an RF transmitter located atop the robot's head, and the recharging supply was activated only when a demand was sensed after connection. The robot could elect to seek out the recharging station before a low battery condition actually arose, such as between patrols.
The software employed in homing on the recharger and effecting a connection was able to deal with a multitude of problems that could arise to hinder the process. Provision was made to skirt around obstacles between the robot and the recharging station. If, as a result of a collision avoidance maneuver, the robot were oriented with respect to the charger so as to preclude a successful docking, the vehicle would back up and realign itself before continuing. The robot could also tell when a return from a forward-looking proximity detector was due to the presence of the recharging station, so the software would not try to steer the platform away.
A special near-infrared proximity sensor mounted on the head provided reliable detection of diffuse wall surfaces for ranges out to 6 feet. This sensor could be positioned at any angle up to 100 degrees either side of centerline by panning the head and was extremely useful in locating open doors and clear paths for travel. Excellent bearing information could be obtained, allowing this sensor to establish the location of the edge of a doorway, for example, to within 1 inch of arc at a distance of 5 feet.
The hallway navigation scheme employed on ROBART I was based in part on the concept of beacon tracking. The recharging station optical beacon was suitably positioned in a known location to assist the robot in entering the hallway. Once in the hallway, the robot would move parallel to the walls in a reflexive fashion, guided by numerous near-infrared proximity sensors. General orientation in the hallway could be determined by knowing which direction afforded a view of the beacon. With a priori knowledge of where the rooms were situated with respect to this hallway, the robot could proceed in a semi-intelligent fashion to any given room, simply by counting off the correct number of open doorways on the appropriate side of the hall.
ROBART I was purposely intended to be a crude and simplistic demonstration of technical feasibility and was built on an extremely limited budget using oversimplified approaches. This philosophy assumed that if the concept could be successfully demonstrated under such primitive conditions of implementation, a reasonable extrapolation would show promise indeed for a more sophisticated second-generation version. (Bart Everett had actually started work on this follow-on prototype, ROBART II, just before leaving the Naval Postgraduate School in 1982. As his interests shifted more in this direction, ROBART I was loaned to the Naval Surface Weapons Center in White Oak, MD, entrusted to the watchful care of an MIT AI Lab co-op student by the name of Anita Flynn--now a famous pioneer in the field of microrobotics.) All work with ROBART I ended in 1985, when the prototype was shipped to Vancouver, BC, for display in the Design 2000 exhibit at EXPO '86. ROBART I is now on display alongside ROBART II in the museum section of our laboratory at SSC San Diego, CA.