Hybrid Solution Combining Kalman Filtering with Takagi–Sugeno Fuzzy Inference System for Online Car-Following Model Calibration (original) (raw)
Related papers
Sensors
The transition to intelligent transportation systems (ITSs) is necessary to improve traffic flow in urban areas and reduce traffic congestion. Traffic modeling simplifies the understanding of the traffic paradigm and helps researchers to estimate traffic behavior and identify appropriate solutions for traffic control. One of the most used traffic models is the car-following model, which aims to control the movement of a vehicle based on the behavior of the vehicle ahead while ensuring collision avoidance. Differences between the simulated and observed model are present because the modeling process is affected by uncertainties. Furthermore, the measurement of traffic parameters also introduces uncertainties through measurement errors. To ensure that a simulation model fully replicates the observed model, it is necessary to have a calibration process that applies the appropriate compensation values to the simulation model parameters to reduce the differences compared to the observed m...
Fuzzy model for estimation of passenger car unit
WSEAS Transactions on Information Science and …, 2008
In most of the developing countries including India mixed traffic condition prevail on roads and highways. There is a wide variation in the static and the dynamic characteristics of different types of traffic. The only way of accounting for this non-uniformity for any traffic analysis in traffic stream is to convert all vehicles into a common unit and the most accepted unit for this purpose is passenger car unit (PCU). PCU value for a vehicle is not constant but varies with traffic and roadway condition around. A number of factors have been identifies affecting PCU values. The current study aims at developing a fuzzy based model for the estimation of PCU values for bus. Fuzzy based model is of importance because of a number of independent affecting factors. Results of developed fuzzy MATLAB based model are compared with the quoted results and are found with high degree of correlation.
Fuzzy models and observers for freeway traffic state tracking
Proceedings of the 2010 American Control Conference, 2010
Traffic state estimation is a prerequisite for traffic surveillance and control. For macroscopic traffic flow models several estimation methods have been investigated, including extended and unscented Kalman filters and particle filters. In this paper we propose a fuzzy observer for the continuous time version of the macroscopic traffic flow model METANET. In order to design the observer, we first derive a dynamic Takagi-Sugeno fuzzy model that exactly represents the traffic model of a segment of a highway stretch. The fuzzy observer is designed based on the fuzzy model and applied to the traffic model. The simulation results are promising for the future development of fuzzy observers for a highway stretch or a whole traffic network.
A New Method for Calibrating Gazis-Herman-Rothery Car-Following Model
Lecture Notes in Computer Science, 2016
Traffic simulation at the microscopic level utilizes carfollowing model to describe vehicle interactions on a vehicular lane. The most widely used car-following model is the Gazis-Herman-Rothery model, which contains two coefficients: m and l. The coefficients should be determined in calibration tests where the involved vehicles are tracked for their positions, velocities, and accelerations. The existing calibration methods are costly. This study proposes a calibration method using computer vision. Two computer vision algorithms are evaluated, namely, multilayer and Eigen background subtraction. The vehicle movement is tracked on a perspective plane and then is projected to an orthogonal plane. From the verification tests, we determine that the multilayer algorithm has 96.6 % accuracy for the vehicle position and 88.9 % for the velocity. The Eigen algorithm has 92.9 % accuracy for the vehicle position and 84.3 % for the velocity. The estimated model coefficients is 0.4 for m and 1.2 for l. These values are within the range of the most reliable coefficients according to many literatures.
A Parallel Genetic Algorithm-Based TSK-Fuzzy System for Dynamic Car-Following Modeling
2009
This paper presents the application of Parallel Genetic Algorithm (PGA)-based Takagi Sugeno Kang (TSK)-Fuzzy approach for dynamic car-following modeling in the traffic simulation software. It differs from the usual car-following model significantly as the proposed model provides a more dynamic car movement and realistic headway by considering the driver progressive level factor. These two advantages could make further traffic analysis become more accurate. The proposed model is used for the tire-road slippage index determination which influences the car's speed. Since the car interact with each other on the road and the driver progressive level is different, three interaction variables, that are current car speed, distance to the car ahead and driver progressive level, are defined and an indication of their influence on the tire-road slippage index is analysed. PGA is included in the TSK-Fuzzy system to determine the optimum parameters in the Fuzzy sets and Fuzzy rules so as to improve the accuracy of the tire-road slippage index estimation. A set of data in a size of 38 x 4 and 22 x 4 were used for training and testing the performance of the model. The study shows that TSK-Fuzzy system combined with PGA is effective and accurate in estimating the tire-road slippage index.
Modeling of traffic congestion on urban road network using fuzzy inference system
Traffic congestion is a complex issue which most of metro cities are experiencing. The degree of congestion on urban links is not always measured & treated uniformly as it is not well defined phenomenon. The traditionalapproaches are unable to represent realistic& true traffic condition and leads to deviation in congestion measurement because of various factors such as imprecision of the measurement, the traveller's perception of acceptability, variation in sample data, and the analyst's uncertainty about causal relations. To overcome this, fuzzy inference approach is proposed in which, three input parameter i.e. speed reduction rate, proportion of time traveling at very low speed (below 5 kmph) compared with total travel time and traffic volume to roadway capacity ratio are combined to get single output in term of congestion index. The proposed model is demonstrated by considering real time traffic data on major road network of Nagpur city, India. This study allows the process to combine different measures and also to incorporate the uncertainty in the individual measures so that the composite picture of congestion can be reproduced with greater accuracy & low error margin.