| Home Toys Article - June99 - [HTI Home Page] |
Read All About It News Announcements - Updated Hourly [Click Message To Learn More] |
|
PC-linked personal robots could be capable of performing numerous domestic and business functions and duties. This is a new concept of a peripheral for the PC system, a personal robot. A significant system cost reduction is now possible due to recently introduced low price, high bandwidth radio frequency (RF) data communication devices. |
In the early '80's, several manufacturers attempted to establish a personal robot industry. Sadly, none of them survive today in their original form. All were victims of too small a market and offerings that were too expensive for their extremely limited utility to be considered of value. It is now 1999, and things are much different. The computing power of the personal computer (PC) today compared to then is simply staggering. This is doubly true since we are paying essentially the same gross dollar amount for the one to two magnitudes of increased CPU clock speeds. This capability is frequently underutilized both in application requirements and percentage of time used during the day. Perhaps with this availability of supermicro (16 or 32 bit bus architecture), if not super mini-computer (32, 64, sometimes 128 bit bus) capability, it is time to revisit the feasibility of a cost-effective, truly utilitarian personal robot. To say it simply, with mainframe computing power of the early '80's costing only a few hundred dollars today, the PC personal robot with true utility, is now possible.
|
During the last fifteen years or so, the personal robot industry has polarized into two camps. One is the domain of the self funded hobbyist and experimenter, and the other the academic researcher. Both of these groups have focused on the extremes of personal robotics. The hobbyist has focused on the low level issues of reactive behaviors. And the researcher has focused on esoteric, highly advanced and experimental sensor systems, and various approaches to Artificial Intelligence.
At present there are several existing autonomous robot manufacturers. Some are small "garage" operations that provide engineering services. They make dumb mobile robot bases for use by hobbyists and experimenters selling for $200-300 each. One low end vacuuming robot (vacbot), using tactile sensing only, will pull a 110vac vacuum around a room in its trailer for only $800 or so. A traditional vacuum cleaner company has a prototype vacbot for a retail someday of $800 to $1,000. Another robotics' firm has a sensor rich, base platform with no intrinsic RF link to a host computer, little developed software and sells for $1,900. Recently, toybot pricing has reached a new high of over $2,500 each for a reactive-only platform. High end, research robots (researchbots) will set you back a minimum of $5,000 and still have little baseline utility outside the laboratory. An industrial class fully autonomous floor cleaning robot sells for over $80,000 but still requires a very structured environment to be useful. This is the basic layout of the personal robot industry.
Now let us look into the cause of this polarization into two camps. A significant difference between the low end hobbyist robots and the researchbots is the behavior known as "cognizant navigation."
As you can see, most present mobile robot suppliers either build big, smart and expensive products, or small, dumb, and inexpensive. There are virtually no utilitarian, user-friendly personal robots presently available for less than ten to twenty thousand dollars. The robot manufacturers selling small robots sell them to individual experimenters and hobbyists for a few hundred dollars. The manufacturers selling large, industrial grade robots sell to primarily universities, colleges, and other well funded research organizations for a few tens of thousands of dollars. Why this huge discrepancy? It all goes back to the fundamental need for a personal robot to have cognizant navigation.
Avoiding unexpected obstacles is a key requirement for utility in a personal robot. Virtually none of the consumer oriented personal robots designed, built, and sold to date have had this basic capability needed in a dynamic home environment. Simple room-to-room errand running, efficient vacuuming, security patrolling, etc. all require this ability. For a personal robot to be useful and provide timely, beneficial services to humans, the robot must have enough intelligence to find it's way, for example, to the back bedroom from the kitchen in spite of unanticipated obstacles such as dropped toys, etc.
PC-linked personal robots could be capable of performing numerous domestic and business functions and duties. This is a new concept of a peripheral for the PC system, a personal robot. A significant system cost reduction is now possible due to recently introduced low price, high bandwidth radio frequency (RF) data communication devices. Linking the home PC with the household robot with robust RF communication capability is unique in the history of personal robot design, manufacture, and marketing.
Several baseline technological hardware and software requirements must be met. There must be enough sensor information of the right kind to not hit typical obstacles such as walls, furniture, and people. There must also be enough sensor information to avoid smaller obstacles such as toys. Furthermore, the brain must be able to react to quick local changes without sacrificing the ability to give the robot tasks to complete. The robot must also have a memory of where it is within the world and be able to repeatedly find locations within that world even if there are unexpected obstacles. (Hobbybots generally fail this test.) This means that there must be enough processing power and RAM to accomplish this while still having enough battery life to stay active for many hours. These important capabilities are the basic, required foundation for useful robots in a human environment. Until the CareBot, almost all consumer robots have fallen short in one or more of these areas.
Most low end toybots and hobbybots are limited by their sensors. Mobile robot sensors such as bump switches, feelers, and whiskers have the problem that they cannot sense their environment without physical contact with the world. Fixed single sonar and infrared distance (IR) range finders are an improvement, but they give very little information about the surrounding world. They may help avoid running into an obstacle directly in front of the robot in one direction, but they aren't very useful in helping the robot navigate.
Even having many different kinds of these sensors does not necessarily solve the problem. The robot must be able to assess the current space around the robot to allow robust navigation, and to do that the robot must have enough information of the right kind, not just many arbitrary sensors. Expensive research robot manufacturers understand this need, and solve this problem through an array of multiple sonar and IR sensors or even more expensive machine vision systems. These high end researchbots routinely use one to two Pentiums at 300 to 400Mhz to achieve cognizant navigation.
As we have discussed, cognizant navigation is much more than simple reactive,
bump-turn mobile robot behavior. The robot may reach the goal, but isn't "aware"
that it is attempting to reach the goal at some level. Line followers may be
"aware" that they are trying to reach a goal, but they have problems when
reacting to new situations. This is due to the brittleness of their complex if-then
architecture. Since life tends to not be structured around simplistic if-then scenarios,
getting the hobbybot or toybot to do anything useful has eluded most of those who have
tried.Here is the additional layer of complexity: The word "aware" implies the robot remembering where it is, where it was, and where it is "supposed" to be going. Cognizant means to be aware or have conscious knowledge. Humanlike short term and long memory management (desired event retention) is the key. This requires the power of the Personal Computer. Your existing PC has the raw computing power, memory, and data storage needed for robust personal robot cognizant navigation, scheduling of areas to be vacuumed, and much, much more.
This goal awareness and ability to return to seeking a predetermined goal is one important attribute that separates the toybots, and most, if not all, hobbybots, from the $30,000 to $100,000 multi-Pentium researchbots. Gecko Systems changed the rules with its leading edge GeckoBrain software. This is why they call it the first Personal Computer Robot. No other commercially available personal computer based, utilitarian robot has ever achieved this high level, extremely difficult, degree of cognizant navigation. The Fuzzy Hybrid Architecture of the GeckoBrain makes this possible.
Home automation will now have an opportunity to have the mobility and ease of interface to the home computer that it has long desired.
Checkout http://www.geckosystems.com for more info.
