datasheets.com EBN.com EDN.com EETimes.com Embedded.com PlanetAnalog.com TechOnline.com
Events
UBM Tech
UBM Tech

News & Analysis

#### Comment

kg5q

7/25/2012 4:23 AM EDT

thanks for the laugh, I was an FAE for Motorola back then and I remember when we ...

More...

dthayden

7/23/2012 12:13 PM EDT

My assessment was similar to yours. It struck me of how marketing would design ...

More...

# Whatever happened to fuzzy logic?

## 7/18/2012 11:22 AM EDT

I remember back in the 1980s getting quite excited about the application of fuzzy logic to control applications. I think there was a startup company but I certainly remember speaking on the telephone with Lotfi Zadeh for an article I was writing.

Lotfali Zadeh, is the father of fuzzy logic having done most of the mathematical groundwork. He is also a classic example of western migration to Silicon Valley. He was born in Azerbaijan of Russian and Iranian parents in 1921 and went on to be an outstanding mathematician, electrical engineer, computer scientist, artificial intelligence researcher and professor emeritus of computer science at the University of California Berkeley.

I also remember how in the article I was writing I tried to explain how a double inverted pendulum could be kept upright by applying a relatively simple fuzzy logic control algorithm to the movement of the trolley on which it was balanced. Latency meant other more conventional DSP control solutions on the hardware of the day were not up to the job.

Fuzzy logic is described as many-valued logic or probabilistic logic and it deals with reasoning that is approximate rather than fixed and exact.

So rather than having an air-conditioning system that works with temperatures sensed and calibrated to the nearest degree with lots of detailed math, fuzzy logic would just work with terms such as "cold" chilly, warm and hot.

I remember that programming was usually based on IF-THEN-ELSE rules-based statements along the lines of "IF room hot THEN start fan."

But I also remember what I saw as a potential weakness of fuzzy logic, the use of membership functions to define the fuzzy variables for the given application. These were usually in the form of pseudo-Gaussian distributions, usually simplified to overlapping triangular or trapezoidal distributions.

prabhakar_deosthali

7/18/2012 1:13 PM EDT

"Fuzzy Logic" the term has a tinge of nostalgia to me also as it reminds me my days as engineer when I was working on control applications for white goods - washing machine, fridge etc. That time the term had caught -up the imagination of marketing guys so much that it had become a key word to be used in commercials to show that Fuzzy logic base appliance were superior.

As the customers found out that there was no great difference in performance or the UI , that wave slowly faded .

pomartel

7/18/2012 4:00 PM EDT

I remember being interestred in FL early on, but it seems there was a certain amount of hype. Bob Pease did a few columns on FL, among them:
http://electronicdesign.com/article/embedded/what-s-all-this-ball-on-beam-balancing-stuff-anyho

briggsie

7/18/2012 4:08 PM EDT

I have always seen probability as a predictor of future events ("What are the chances that the Cubs will win the World Series?"). Fuzzy logic is a descriptor if current events ("Is that guy really bald, or just partly bald?"). Two different kinds of uncertainty. Two different processes to deal with them.

pmoyle

7/18/2012 4:15 PM EDT

I remember getting an FL dev kit from Mot for their HC05 back in those days...I'm moving again after a long time in the same house and just threw it away a couple weeks ago. Just had too much stuff piled up and, well, the 8051 may still be around, but days of the HC05 have come and gone.

kg5q

7/25/2012 4:23 AM EDT

thanks for the laugh, I was an FAE for Motorola back then and I remember when we had to promote this to customers, give out dev boards - or sell them. I dont recall any customer for micros ever caring about it at all. These days in the semi industry we would still be tracking the status that "design win" and your development board all the way to the landfill.

EREBUS

7/18/2012 4:18 PM EDT

Fuzzy Logic was just a method of using hysteresis combined with overlapping state values to smoothen the transfer of state transitions. The only thing Fuzzy about it was that people thought it was something new.

selinz

7/18/2012 4:58 PM EDT

Thanks, pomartel. That Bob Pease article is awesome! Here is a snippet:
When I do get this working really well, I'll send a videotape to Dr. Li and Dr. Ji - just to show them how a beam balancer can work well. They claimed they got their best results because they didn't use any models. Mine runs well because I was able to use simple models: a rolling ball is a double integrator. They claimed their Fuzzy Logic was able to triumph over the nonlinearities of a tilted beam. Well, the approximation that sine of tilt angle = tilt is only nonlinear by a few percent. They still can't servo the ball to any place on the beam as fast as my PID2 controller.

I would have loved to see Mr. Pease and Mr. Li in a room showing off their respective contraptions!

Brutus_II

7/18/2012 5:15 PM EDT

Fuzzy logic is alive and well in space exploration in that is lends itself to building reliable control systems that function in the presence of uncertainty or ambiguity. A prime example would be in the unmanned surface exploration of Mars of supporting autonomous maneuvering since radio communication involves lengthy delays. Without exact knowledge of where rocks, boulders, and crevices are, rule-based fuzzy logic controllers consisting of a finite set of control rules which are processed by applying what is referred to as approximate reasoning, i.e. general terms such as large, deep, very deep etc., are the best current solution for collision avoidance next to actually having a human pilot at the controls.

peter.clarke

7/19/2012 7:38 AM EDT

Thanks Brutus

Good to know all that coverage of fuzzy logic back in the day helped with space exploration.

Dr.WiFi

7/18/2012 5:20 PM EDT

Back in 1991 I was part of a venture funded fabless semiconductor startup company - American NeuraLogix located in Orlando Florida. The company focused on developing semiconductor products e.g. Fuzzy logic controllers, Fuzzy Pattern generator and Neural Networks. The products worked well...but the market needed time to adapt to this new technology.The company eventually exited through acquistion.

peter.clarke

7/19/2012 7:40 AM EDT

I think that was the startup of which I was thinking.

Who acquired them?

Max the Magnificent

7/18/2012 5:29 PM EDT

I'm currently reading a great book on Fuzzy Logic -- I'm still in the early part of the book, but I love all of the history and background -- I'll report back further when I finish the little scamp

Ovidiu.Carnu

7/18/2012 5:36 PM EDT

I heard of fuzzy logic in high school in Romania when a professor from the local university came and gave an introductory class about it. It seemed so interesting and the guy was so convinced that this is the future. After that in my first year of undergrad was part of the (mandatory) Special Math class. The math behind it is interesting and elegant at least at level I studied it.
It is fascinating how all this revolutionary ideas that were all the rage not long ago were completely forgotten: neural networks, chaos theory, fuzzy logic. This was supposed to be the future but we still do things the same as 50 years ago.

Sparky_Watt

7/19/2012 6:19 PM EDT

The fundamental problem with fuzzy logic is that it comes up with a simple solution, but it is processor intensive and it isn't anywhere near optimal.

R G.Neale

7/18/2012 8:46 PM EDT

I have a modern home-use blood pressure measuring machine (don't ask) made by Omron in Germany. On page 11 of the instruction manual the is a line that reads.

Inflation: Fuzzy-Logic controlled by electric pump.

So in answer to your question Fuzzy-logic is alive and well saving lives.

peter.clarke

7/19/2012 4:00 AM EDT

That line reads backwards?

Shouldn't it be "electric pump controlled by fuzzy logic"

Or is fuzzy logic alive and well and providing marketing services and a warm cosy feeling -- as in the fuzzy logic washing machine.

R G.Neale

7/19/2012 5:37 PM EDT

Yes Peter I think that is what was intended. It looks as though the actual line of text that I quoted has suffered from a word-for-word translation from the original German.

PasqualinoAxel

7/19/2012 4:06 AM EDT

According to some pubblications there are still lots of fuzzy-logic based applications. For example, the MASSIVE 3D animation system for generating crowds uses fuzzy logic for artificial intelligence. This program was used extensivly in the making of the Lord of the Rings trilogy as well as The Lion, The Witch and the Wardrobe films.
More on http://www.calvin.edu/~pribeiro/othrlnks/Fuzzy/apps.htm

elektroniker

7/19/2012 7:08 AM EDT

Look up Togai InfraLogic some time. Don't know how active they are at present.

DaveR1234

7/19/2012 7:51 AM EDT

I recall a camera advertising using fuzzy logic in their auto-focus system -- a marketing SNAFU.

Wilton.Helm

7/19/2012 10:05 AM EDT

It is actually gratifying to see that fuzzy logic is all buttons dead. Like Bob Pease, I recognized early on that it was all hype and no substance. Marketing is always looking for buzz words that make consumers think their new product is better. Fuzzy logic was nothing more than a fancy name for a collection of well known techniques, starting with piecewise linear interpolation, buried behind a fancy front end methodology! The problem is, that methodology hid the nature of what was actually going, deceiving the gullible that it was something new, and preventing them from actually analyzing the resulting equations and algorithm which might have allowed them to optimize them (assuming they were capable). Or to state it differently, our industry is always looking for a "magic bullet" that can make a mindless tech able to do what an engineer can do. Fuzzy logic was supposed to take both the math and thinking out of complex control systems. But once again it turns out that there is no successful substitute for a human who understands the problem, actually thinking about it--which is another point Bob Pease would have strongly agreed with, were he still part of our community.

dthayden

7/23/2012 12:13 PM EDT

My assessment was similar to yours. It struck me of how marketing would design systems if given the task, more trial and error than structured design based on an understanding of the system.

daleste

7/19/2012 10:55 AM EDT

My understanding of fuzzy logic is that it was a way to have a controller that did not have enough horse power, do the job. Since almost all of the devices today have more than enough power to do the job, fuzzy logic doesn't have much of a use.

utilitus

7/19/2012 3:11 PM EDT

In grad school at Berkeley in the mid '80s, I was in Prof. Zadeh's Expert and Knowledge-Based Systems seminar for a few years, and he never once mentioned FL unless someone brought it up. In private, he would actively promote its' application to IR (i.e., search), even if it didn't quite fit. At one time (I'm too busy to check), there were at least two proper academic journals dedicated to FL, and now decades later there is at least an institutional echo of the movement in the Berkeley Initiative in Soft Computing (http://www-bisc.cs.berkeley.edu/BISCProgram/default.htm), which seems a bit like the Hair Club for Persians. Prof. Zadeh was a great guy, in the cosmopolitan/humanitarian/uber-nerd tradition.

Murat Terzi

7/19/2012 4:00 PM EDT

Fuzy logic based control could not extend various aplication areas due to uncertainty. With new dsp based cpus you need more certainty not uncertainty...

DrQuine

7/19/2012 10:53 PM EDT

Examples of consumer applications of fuzzy logic often seemed to be better served with linear or analog solutions (in the winter, the cooler the house is, the harder you run the furnace and the air blowers). Deciding between low, medium, and high seemed artificial. Some examples do survive (dishwashers offer light, normal, and heavy wash options). Certainly the observations about computing power are also quite relevant - the fuzzy logic decisions typically are trivial compared with the computing power that is running idle.

HashimRaza.Khan

7/20/2012 12:58 AM EDT

Sometime back I stumbled upon an article by Daniel Abramovitch at HP/Agilent. His presentation provides an interesting viewpoint of FL

http://dabramovitch.com/pubs/fuzzy_acc_talk_2e.pdf

peter.clarke

7/20/2012 5:51 AM EDT

I particularly liked this line from Abramovitch:

"It comes down to sample rate versus computational complexity."

http://www.lulu.com/spotlight/poconoarmchairreview

7/20/2012 10:04 PM EDT

Fuzzy logic. It's how some companies can report billions in trading losses and have their stock go up. You know, it's better than having a store-front, cash-only, antique business! It's even better than faking your own death! Or paying someone to go to prison for you!