Fuzzy logic originally introduced by Lotfi Zadeh in 1965, is a form of many-valued logic where the values of the actual variables may be any real number between 0 and 1 inclusively. Fuzzy logic-based models turn out to be very useful in areas like weather forecasting, product pricing, robotics, power engineering, image recognition, telematics, and optimization.
A brief intro to fuzzy logic
Traditional logic operating with true values (1) or false values (0). In contrast, fuzzy logic allows in addition to 0 and 1 values any other real number values in between, therefore supporting a concept of “partial truths”. For example, instead of just saying that the water is cold or hot, in fuzzy logic, it is eligible to deal with a temperature gradient of water (warmer, colder, and so on).
To continue with the water temperature example, suppose that one needs to explain temperature treatment above and below certain values. Again, it could be done by increasing the amount of included linguistic terms, for example, one could say warm or very hot.
The corresponding example of the fuzzy set diagram is shown in the figure above. It represents the overlapping sets and the fact that temperature may have a membership grade of more than one set. The universe of discourse is the range of all the operating sets. Obviously this is a rather simple example, but even this case already demonstrates how successfully fuzzy logic could accommodate uncertainty.
Fuzzy logic turns out to be a very fruitful mathematics theory, that advanced a wide range of applications such as consumer electronics, industrial automation, and optimization. The fuzzy logic system architecture is shown in the figure below. The Fuzzification module transforms system input/crisp numbers into the fuzzy sets. Rule base includes rules and if-then conditions in order to control the decision-making system.
The intelligence module helps to determine the degree of match between the rules and fuzzy input. Based on the matching degree, it determines which rules need implement according to the given input. Defuzzifier module on its turn responsible for transforming the obtained fuzzy set into a crisp value.
Fuzzy logic in telematics and transportation
As being mentioned above, due to its ability to deal with uncertainty, fuzzy logic could successfully be utilized in many real-world applications, and telematics, as well as transportation, are not exceptions. For instance, it was used for driver behavior control: S. Ghaemi with colleagues managed to demonstrate a hierarchical fuzzy system for humans in a driver-vehicle-environment system to model takeover by different drivers. The proposed method also provides a basis for modeling individual driver behavior characteristics that may be tuned and used in automatically guided vehicles.
The fuzzy logic approach being also used for car hacking identification. In [F. Martinelli et al, 2017] authors proposed a method that able to detect four different types of attacks targeting the CAN protocol adopting fuzzy algorithms. Another telematics application is the evaluation of the driver’s eco-driving skills based on the fuzzy logic model [M. Stokic et al, 2019]. It was shown that the proposed fuzzy logic model with some slight modifications could be employed as a general evaluation system of drivers in transport and logistics companies.
Fuzzy logic provides fruitful features to telematics, but it should be pointed out that such solutions are not alternative-less. For instance, an innovative telematics platform may utilize other advanced algorithms and solutions, allowing efficient driver behavior control.
Those are just a few examples out of cohort success cases of applying fuzzy logic-based models in telematics and transportation. Given the continuous rise of such cases, it is possible to observe the implementation of such models into commercial solutions in the nearest future.
- M. Stokic et al., Evaluation of driver’s eco-driving skills based on the fuzzy logic model, 2019
- J. Harris, An Introduction to Fuzzy Logic Applications, 2000
- R. Massoud et al, A Fuzzy Logic Module to Estimate a Driver’s Fuel Consumption for Reality-Enhanced Serious Games, 2018
- S. Ghaemi et al, Driver’s Behavior Modeling Using Fuzzy Logic, 2010
- H. Singh et al., Real-Life Applications of Fuzzy Logic, 2013.