Driver Behavior Modeling and Hidden Markov Models Sensitivity Analysi

The capability to estimate driver's intention leads to the development of Advanced Driver Assistance Systems (ADAS) that can assist the drivers in complex situations. Developing precise driver behavior models near intersections can considerably reduce the number of accidents at road intersections. In this work, the problem of driver behavior modeling near a road intersection is investigated using machine learning techniques: Support Vector Machines (SVMs), Hidden Markov Model (HMM) trained using Genetic Algorithm (GA) and Discrete HMM, based on the hybrid-state system (HSS) framework. In the HSS framework, the decisions of the driver are represented as a discrete-state system (DSS) and the vehicle dynamics are represented as a continuous-state system (CSS). The proposed SVM + HSS modeling technique utilizes statistical methods to extract features from the continuous observations of the vehicle and estimates the driver's intention at each time step using a multi-class SVM approach. In the other proposed technique, HMM-GA + HSS, the HMM models for driver behavior near intersections are trained using GA combined with Baum-Welch Algorithm. HMM is usually trained using Baum-Welch which is easily trapped at local maxima. GA solves this problem by searching the entire solution space. The continuous observations from the vehicle, such as acceleration, speed and yaw-rate, are used by the proposed technique to estimate the driver's intention at each time step. In the Discrete HMM approach, the vehicle's continuous observations including speed and yaw-rate, are used to estimate the driver's intention at each time step. The speed and yaw-rate are discretized in such a way that the important features about the driver's intention such as "go straight," "stop," "turn right," or "turn left" at the intersection, are abstractedly represented in the form of symbols. All models are trained and tested using naturalistic driving data obtained from the Ohio State University, in an experiment with a sensor-equipped vehicle that was driven in the streets of Columbus, OH. The proposed techniques show a promising accuracy in estimating the driver's intention when approaching an intersection.;The other part of this work is HMM sensitivity analysis. In this work, a new algorithm for sensitivity analysis of discrete hidden Markov model (HMM) is proposed. Sensitivity analysis is a general technique for investigating the robustness of the output of a system model. Sensitivity analysis of probabilistic networks has recently been studied extensively. This has resulted in the development of mathematical relations between a parameter and an output probability of interest and also methods for establishing the effects of parameter variations on decisions. Sensitivity analysis in hidden Markov models (HMM) has usually been performed by taking small perturbations in parameter values and re-computing the output probability of interest. As recent studies show, the sensitivity analysis of HMM can be performed using a functional relationship that describes how an output probability varies as the network's parameters of interest change. To derive this sensitivity function, existing Bayesian network algorithms have been employed for HMMs. These algorithms are computationally inefficient as the length of the observation sequence and the number of parameters increases. In this study, a simplified efficient matrix-based algorithm for computing the coefficients of the sensitivity function for all hidden states and all time steps is proposed and an example is presented.