Get the SoR Robotics Android App on Android Market for FREE. See this forum post for details.

0 Members and 1 Guest are viewing this topic.

You would take a multitude of fuzzy inputs, and then use them to generate a unique behavior, or a mood.Each fuzzy input is stored as a temporary variable, each variable is then used for pre determined things...Like this:Battery Level(40%)>>>Memory>>>Extend Solar panels(Output)>>>but if dark: return to charging station.This uses fuzzy logic, and multiple inputs to decide what to do when the battery is low.Fuzzy logic can be anything in between 1 and 0, but remember your robot will see fuzzy logic as an analog input

Fuzzy Logic is the act of using unrelated inputs to determine behaviors of your robot. Having your robot charge when battery is low is not fuzzy logic, it's a state machine based behavior and a good practice. Having your robot move in a certain way based on the reading of an unconnected ADC pin is fuzzy logic. Humans can be spontaneous and unpredictable. Robots are very predictable, they behave exactly how we program them. Fuzzy logic tries to add some spontaneity by making decisions by seemingly random input. Thus, the 'logic' the robot follows is hard to understand, or is somewhat 'fuzzy'. Hence fuzzy logic.

http://www.societyofrobots.com/programming_fuzzy_logic.shtmlBasically, instead of "if greater than this do that" you make an algorithm that gradually adjusts things.

Basically, instead of "if greater than this do that" you make an algorithm that gradually adjusts things.

Fuzzy logic is a form of multi-valued logic derived from fuzzy set theory to deal with reasoning that is approximate rather than precise. In contrast with "crisp logic", where binary sets have binary logic, fuzzy logic variables may have a truth value that ranges between 0 and 1 and is not constrained to the two truth values of classic propositional logic.[1] Furthermore, when linguistic variables are used, these degrees may be managed by specific functions.

Fuzzy logic is not randomness.

I know most people hate wikipedia, but I find the wikipedia description of fuzzy logic fairly accurate:QuoteFuzzy logic is a form of multi-valued logic derived from fuzzy set theory to deal with reasoning that is approximate rather than precise. In contrast with "crisp logic", where binary sets have binary logic, fuzzy logic variables may have a truth value that ranges between 0 and 1 and is not constrained to the two truth values of classic propositional logic.[1] Furthermore, when linguistic variables are used, these degrees may be managed by specific functions.Basically boolean logic can be seen as a subset of fuzzy logic that only deals with the extreme truth values as 0 and 1 and ignores the gray (fuzzy) area in between.

an algorithm that gradually adjusts things.

Fuzzy logic was never developed or intended for use on robots. Its use was for describing things that didnt fit a binary description.

So yes, robots can be fuzzy too

Well, the robot could go to the internet and check the online weather in it region, and that could be fuzzy, since the meteorologists used fuzzy logic to predict the weather?

So using fuzzy tables of available sensor data can also answer the weather question easily.Humans can do the same, just check the visual colours and temperatures to produce an answer, if the answer is different than the outcome then we chooses the alternative answer next time.

depends what you are trying to make 'fuzzy'. for exampleint read = analogRead(1);if(read > 700) //dance to the leftelse if(read > 300) //dance to the rightelse //sulk in the corner

A PID controller 'gradually adjusts things'. Is it fuzzy?