Baehoon Choi

Novel Range-Free Localization Based on Multidimensional Support Vector Regression Trained in the Primal Space

A novel range-free localization algorithm based on the multidimensional support vector regression (MSVR) is proposed in this paper. The range-free localization problem is formulated as a multidimensional regression problem, and a new MSVR training method is proposed to solve the regression problem. Unlike standard support vector regression, the proposed MSVR allows multiple outputs and localizes the sensors without resorting to multilateration. The training of the MSVR is formulated directly in primal space and it can be solved in two ways. First, it is formulated as a second-order cone programming and trained by convex optimization. Second, its own training method is developed based on the Newton-Raphson method. A simulation is conducted for both isotropic and anisotropic networks, and the proposed method exhibits excellent and robust performance in both isotropic and anisotropic networks.

Pedestrian/Vehicle Detection Using a 2.5-D Multi-Layer Laser Scanner

Laser scanners are widely used as the primary sensor for autonomous driving. When the commercialization of autonomous driving is considered, a 2.5-D multi-layer laser scanner is one of the best sensor options. In this paper, a new method is presented to detect pedestrians and vehicles using a 2.5-D multi-layer laser scanner. The proposed method consists of three steps: segmentation; feature extraction; and classification; this paper focuses on the last two steps. In feature extraction, new features for the multi-layer laser scanner are proposed to improve the classification performance. In classification, radial basis function additive kernel support vector machine is employed to reduce the computation time while maintaining the performance. The proposed method is implemented on a real vehicle, and its performance is tested in a real-world environment. The experiments indicate that the proposed method has good performance in many real-life situations.

Novel Collision Warning System using Neural Networks

Abstract Recently, there are many researches on active safety system of intelligent vehicle. To reduce the probability of collision caused by drivers inattention and mistakes, the active safety system gives warning or controls the vehicle toward avoiding collision. For the purpose, it is necessary to recognize and analyze circumstances around. In this paper, we will treat the problem about collision risk assessment. In general, it is difficult to calculate the collision risk before it happens. To consider the uncertainty of the situation, Monte Carlo simulation can be employed. However it takes long computation time and is not suitable for practice. In this paper, we apply neural networks to solve this problem. It efficiently computes the unseen data by training the results of Monte Carlo simulation. Furthermore, we propose the features affects the performance of the assessment. The proposed algorithm is verified by applications in various crash scenarios.Key Words : Collision Risk Assessment, Monte Calro Simulation, Neural Networks, Time-to-Collision(TTC)

Location Estimation and Obstacle tracking using Laser Scanner for Indoor Mobile Robots

This paper presents the method for location estimation with obstacle tracking method. A laser scanner is used to implement the system, and we assume that the map information is known. We matches the measurement of the laser scanner to estimate the location of the robot by using sequential monte carlo (SMC) method. After estimating the robot`s location, the pose of obstacles are detected and tracked, hence, we can predict the collision risk of them. Finally, we present the experiment results to verify the proposed method.

Robust object segmentation using a multi-layer laser scanner

The major problem in an advanced driver assistance system (ADAS) is the proper use of sensor measurements and recognition of the surrounding environment. To this end, there are several types of sensors to consider, one of which is the laser scanner. In this paper, we propose a method to segment the measurement of the surrounding environment as obtained by a multi-layer laser scanner. In the segmentation, a full set of measurements is decomposed into several segments, each representing a single object. Sometimes a ghost is detected due to the ground or fog, and the ghost has to be eliminated to ensure the stability of the system. The proposed method is implemented on a real vehicle, and its performance is tested in a real-world environment. The experiments show that the proposed method demonstrates good performance in many real-life situations.

Novel Intersection Type Recognition for Autonomous Vehicles Using a Multi-Layer Laser Scanner.

There are several types of intersections such as merge-roads, diverge-roads, plus-shape intersections and two types of T-shape junctions in urban roads. When an autonomous vehicle encounters new intersections, it is crucial to recognize the types of intersections for safe navigation. In this paper, a novel intersection type recognition method is proposed for an autonomous vehicle using a multi-layer laser scanner. The proposed method consists of two steps: (1) static local coordinate occupancy grid map (SLOGM) building and (2) intersection classification. In the first step, the SLOGM is built relative to the local coordinate using the dynamic binary Bayes filter. In the second step, the SLOGM is used as an attribute for the classification. The proposed method is applied to a real-world environment and its validity is demonstrated through experimentation.

Collision Risk Assessment for Pedestrians` Safety Using Neural Network

Abstract: This paper proposes a new collision risk assessment system for pedestrians’s safety. Monte Carlo Simulation (MCS) method is a one of the most popular method that rely on repeated random sampling to compute their result, and this method is also proper to get the results when it is unfeasible or impossible to compute an exact result. Nevertheless its advantages, it spends much time to calculate the result of some situation, we apply not only MCS but also Neural Networks in this problem. By Monte carlo method, we make some sample data for input of neural networks and by using this data, neural networks can be trained for computing collision probability of whole area where can be measured by sensors. By using this trained networks, we can estimate the collision probability at each positions and velocities with high speed and low error rate. Computer simulations will be shown the validity of our proposed method. Keywords: intelligent vehicle, monte carlo, neural networks, collision risk, monte carlo simulation

Rear-end Collision warning system using linear discriminant analysis

In this paper, we propose a Collision warning system for rear-end collision situation to avoid an accident. There are many complex situations in roadway. Therefore, we focus on a rear-end collision which is a common traffic accident wherein a vehicle crashes into the vehicle in front of it. The state of vehicles and the TTC are used to state features and LDA is used to project the state features into linear space which can indicate the possibility of collision. Computer simulation will be show the validity of our proposed method.

Prediction of Centerlane Violation for vehicle in opposite direction using Fuzzy Logic and Interacting Multiple Model

For intelligent vehicle technology, it is very important to recognize the states of around vehicles and assess the collision risk for safety driving of the vehicle. Specifically, it is very fatal the collision with the vehicle coming from opposite direction. In this paper, a centerlane violation prediction method is proposed. Only radar signal based prediction makes lots of false alarm cause of measurement noise and the false alarm can make more danger situation than the non-prediction situation. We proposed the novel prediction method using IMM algorithm and fuzzy logic to increase accuracy and get rid of false positive. Fuzzy logic adjusts the radar signal and the IMM algorithm appropriately. It is verified by the computer simulation that shows stable prediction result and fewer number of false alarm.

Multiclass Lagrangian support vector machine

A support vector machine (SVM) has been developed for two-class problems, although its application to multiclass problems is not straightforward. This paper proposes a new Lagrangian SVM (LSVM) for application to multiclass problems. The multiclass Lagrangian SVM is formulated as a single optimization problem considering all the classes together, and a training method tailored to the multiclass problem is presented. A multiclass output representation matrix is defined to simplify the optimization formulation and associated training method. The proposed method is applied to some benchmark datasets in repository, and its effectiveness is demonstrated via simulation.