This paper presents a methodology of lane change motion planning based on spatio-temporal corridor for autonomous driving in multi-vehicle traffic environments. The spatio-temporal corridor is constructed based on the prediction results of surrounding vehicles. For lane change decision making, the target lane change space is determined by investigating the feasibility and space sufficiency using the spatio-temporal corridor. The set of lane crossing time which enables the safe lane change is calculated in the feasibility investigation process. The feasibility investigation secures the consistency of the decision making and motion planning. The lane change motion planning algorithm incorporates decoupled lateral and longitudinal dynamics. The lateral motion is planned based on a sampling method which refers to the lane crossing time set. Subsequently, the longitudinal motion is planned using Model Predictive Control (MPC), taking into account the results of the lateral motion planning. Simulation studies have been conducted to investigate the performance of the proposed lane change algorithm. The proposed algorithm has been implemented in our test vehicle and validated via autonomous driving tests. The vehicle test results show that the proposed algorithm plans the lane change motion safely with proper ride quality.

In this paper, we propose a Geometric Model-Free Approach with a Particle Filter (GMFA-PF) through the use of automotive LiDAR for real-time tracking of moving objects within an urban driving environment. GMFA-PF proved to be lightweight, capable of finishing the process within the sensing period of the LiDAR on a single CPU. The proposed GMFA-PF tracks and estimates moving objects without any assumptions on the geometry of the target. This approach enables efficient tracking of multiple object classes, with robustness to a sparse point cloud. Point cloud on moving objects is classified via the predicted Static Obstacle Map (STOM). A likelihood field is generated through the classified point cloud and is used in particle filtering to estimate the moving object’s pose, shape, and speed. Quantitative and qualitative comparisons - with Geometric Model-Based Tracking (MBT), Deep Neural Network (DNN), and GMFA - are performed for GMFA-PF using urban driving and scenario driving data gathered on an autonomous vehicle fitted with close-to-market sensors. The proposed approach shows robust tracking and accurate estimation performance in both sparse and dense point clouds; GMFA-PF achieves improved tracking performance in dense traffic and reduces yaw estimation delay compared to the others. Autonomous vehicles with GMFA-PF demonstrated auto-nomous driving on urban roads.

This paper presents a motion-planning framework for urban autonomous driving at uncontrolled intersections. The intention and future state of the target vehicles are predicted using information obtained from the environment sensors. The target state prediction module employs an Interacting Multiple Model (IMM) filter to infer the intention of targets. The prediction results of each model of the IMM filter are fused to predict the future state of targets. The proposed predictor uses the intelligent driver model based-driver behavior model to construct the local filter of IMM. The driving mode decision is realized as a state machine consisting of two phases, `Approach' and `Risk Management'. The risk management phase is composed of two sub-modes, `Cross' and `Yield'. The state transition conditions between phases and modes are defined by introducing the concepts of `Critical gap' and `Follow-up gap'. Based on the determined driving mode, the motion planning module consists of two sub-modules for each phase. The required deceleration determination for the approach phase is proposed to consider the occluded region in order to prevent inevitable collisions caused by fast approaches. The model predictive controller for the risk management phase is designed to determine the desired acceleration to guarantee safety and prevent unnecessary deceleration simultaneously. Both computer simulation studies and vehicle tests are conducted to evaluate the proposed framework. The results indicate that the proposed framework ensures the safety at uncontrolled intersections with a driving pattern similar to that of a driver.

Detection and tracking of moving objects (DATMO) in an urban environment using Light Detection and Ranging (LiDAR) is a major challenge for autonomous vehicles due to sparse point cloud, multiple moving directions, various traffic participants, and computational load. To address the complexity of this issue, this study presents a novel model-free approach for DATMO using 2D LiDAR implemented on autonomous vehicles. The approach has been used to classify moving points in the point cloud using the predicted Static Obstacle Map (SOM) generated via interaction between Geometric Model-Free Approach (GMFA) and SOM, and estimates the state of each moving object via GMFA. The motion of each point represented by the state of moving objects updates the SOM. The interaction between GMFA and SOM estimates the correspondence between consecutive point clouds in real-time. The proposed approach has been evaluated via RT range and labeled dataset. The accuracy of estimation of the yaw angle and the velocity of a moving vehicle has been quantitatively evaluated using the RT-range. The performance is significantly improved compared with the geometric model-based tracking (MBT). The estimation of the yaw angle, which has a significant effect on the cut-in/cut-out intention of the target vehicle, is shown to be remarkably improved. Based on the evaluation of the labeled dataset, false-positive and false-negative features are suppressed more than MBT.

This paper presents the collision preventive velocity planning algorithm to enhance safety when driving the occluded region in an urban environment. The accidents due to the pedestrian who appear from the occluded region occur frequently on complex urban roads. The collision preventive velocity planner has been proposed to reduce the potential risk caused by the occluded region of sensors. The point cloud of 2D Lidar is processed to construct the static obstacle map. A static obstacle boundary is defined to estimate the possible position of the pedestrian appearance based on the static obstacle map. The longitudinal motion planner determines the target states using the static obstacle boundary to prevent the inevitable collision with pedestrians coming from the occluded region. The target states are tracked by MPC based motion tracker to determine the desired acceleration. The collision prevention performance of the proposed algorithm has been validated by the Monte-Carlo simulation. The simulation results demonstrated that the proposed algorithm prevents the collision with pedestrian from the occluded region and improve the safety of urban autonomous driving.

The challenge lies in developing fully autonomous vehicles is to drive safely in inclement weather. Driving in inclement weather is often a risky task because reacting proactively and stabilizing the vehicle on low friction road is a challenging task unlike driving on high friction road. To tackle such issue, this paper presents a predictive motion framework to operate safely on low friction road without prior knowledge of tire-road friction coefficient. The proposed control algorithm consists of the instability detection algorithm and the longitudinal/lateral motion control algorithms. The instability detection algorithm (1) determines whether the vehicle is stable without knowing friction coefficient and (2) estimates the friction coefficient. The longitudinal and lateral motion control algorithms are separately but interdependently designed based on Model Predictive Control method to proactively control the vehicle with a forecast of vehicle motions. The potential of the proposed approach is shown through computer simulations with a high fidelity vehicle model. The results show that the proposed algorithm (1) successfully reduces speed to avoid path deviation and (2) detects the vehicle instability and stabilize the vehicle due to sudden friction changes.

This paper presents a human-centered risk assessment algorithm using vehicular communication for application to an automated driving vehicle. Vehicle-to-vehicle (V2V) wireless communication has been implemented and fused with a radar sensor to obtain the prediction of the remote vehicle's motion. Based on the predicted behavior of remote vehicles, a collision risk and a human reaction time are determined for a human-centered active safety control intervention moment. The human-centered risk assessment algorithm has been incorporated into a collision avoidance algorithm to monitor threat vehicles ahead and to find the best intervention point. Effects of the vehicular communication on a perception and a control performance are investigated. The performance of the proposed algorithm has been investigated via computer simulations and vehicle tests. It has been shown from both simulations and vehicle tests that the proposed human-centered risk assessment algorithm with V2V communication decides a proper active safety intervention moment by reducing the chances of over/underestimate of a conventional radar-only system.

This paper proposes a lane marking detection method for automated driving in complex urban roads to be used with map-matching localization algorithms. First, a LiDAR based lane detection and map matching algorithm is explained and a lane marking detection algorithm using AVM (Around View Monitor) cameras is presented. The AVM camera based lane marking detection algorithm includes camera calibration, bird-eye view conversion, and lane marking detection. The two lane detection methods are combined and implemented as a part of a map-matching localization algorithm on an autonomous test vehicle. Multiple experiments on various test routes, including complex situations like driver's license exam stations, were performed to verify the performance of the lane marking detection in the map-matching algorithm.

Recent technological advances in automated cars have brought them closer to regular use on the roads. Accordingly, research on the driver's perspective is increasing. However, previous studies have limitations in terms of the length of the study period and richness of the user's experience. In this paper, we conducted an ethnographic experiment to observe the interaction between humans and automated cars. Six participants rode in a prototype automated car on a real road one hour a day for six days under various weather conditions. We found that even after six days of utilizing it, participants did not fully trust the automated car. We identified nine distrust factors that strongly influenced their experiences in the automated car, classifying them according to Lee and See's classification of three trust categories: process, performance, and purpose. We also present serval ideas based on the study results.

This paper presents a map-matching-based vehicle localization algorithm for application to automated driving on urban road. Vehicle position estimation of centimeter-level with low-priced commercial sensor setup is one of the key issue in urban automated driving. The information fusion method of localization algorithm utilizes vehicle chassis sensor and Around View Monitoring (AVM) module with four fish-eyed cameras. The proposed localization algorithm consists of three sections: a lane detection, a position correction, and a localization filter. A lane information is extracted from AVM image around the vehicle. This lane information is possible to correct vehicle position by the iterative closest point (ICP) algorithm which estimates the rigid transformation between the lane map and lanes obtained by AVM in real-time. The corrected vehicle position by this transformation is fused with the information of vehicle sensors based on an extended Kalman filter (EKF). In order to achieve higher accuracy, the covariance of the ICP algorithm is estimated by using Haralick's method. The performance of proposed localization is verified through vehicle experiments on proving ground and actual urban road.

This paper presents a vehicle sensor and actuator fault detection algorithm for automated vehicles. The diagnostic system is designed to monitor steering wheel angle, yaw-rate, and wheel speed sensors and steering, throttle, and brake actuators used by the lateral and longitudinal controllers of the vehicle. Different combinations of the observer estimates, the sensor measurements, and the control commands are used to construct a bank of residuals. A fault in any of the vehicle sensors and actuators leads to increase of the unique subset of residuals. The adaptive threshold is used to enable exact identification of the abnormal increase of residual. The fault detection performance and its reliability of the proposed algorithm have been investigated via computer simulation studies and real-time vehicle tests. The enhancement of the fault detection allows for realization of autonomous driving vehicle which uses actuation by embedded computer.

This paper describes a method of lane map building and localization for automated driving using 2d laser rangefinder. Today's on-board sensors such as radar or camera do not reach a satisfying level of development from the point of view of robustness and availability. Thus, map data is often used as an additional data input to support these systems. An digital map is used as a powerful additional sensor. So we propose a lane map-based localization using a 2D Laser Rangefinder. The maps are created beforehand using a 2D LiDAR and RTK GPS. A pose estimation of vehicle was derived from a low-cost GPS and an iterative closest point(ICP) match of real-time sensor data to lane map. And the estimated pose was used as an observation inside a Kalman filter framework. The performance of the proposed localization algorithm is verified via vehicle tests in ITS proving ground. It has been shown through vehicle tests that good localization performance can be obtained. The proposed algorithm will be useful in the implementation of automated driving.

This paper presents the maximum tire-road friction coefficient estimation algorithm which considers about the effect of states. Tire force information is an important factor for active safety system. However, it is difficult to estimate due to the dependency on many states such as vehicle speed, tire pressure, and tire wear. In this paper, several experimental researches about the effect of states on the maximum friction coefficient and previous maximum tire-road friction coefficient estimation algorithms are reviewed and summarized. The influential states and the estimation method which doesn't require extra sensors were determined and combined. The proposed algorithm consists of two parts: an interacting multiple models (IMM) based maximum tire-road friction coefficient estimation and an updating sequence based on the effect of vehicle speed. To validate the algorithm, the closed-loop simulation with the advanced emergency braking system (AEBS) has been conducted. It has been shown that the proposed estimation algorithm could enhance the performance of AEBS algorithm.

The objective of this paper is to propose an original probabilistic threat assessment method to completely predict and avoid all possible kinds of collision in multi-vehicle traffics. The main concerns in risk assessment can be summarized as three requirements: 1) a description of a traffic situation containing the geometric description of the road, dynamic and static obstacle tracking, 2) a prediction of multiple traffics' reachable set under the reasonable behavior restriction, and 3) an assessment of collision risk which corresponds with driver sensitivity and can be applied to many complex situations without loss of generality. To fulfill these three requirements, the proposed algorithm for estimating the probability of collision occurrence of the ego vehicle follows the basic idea of the particle filtering and the collision probability can be numerically implemented and calculated. The overall performance of the proposed threat assessment algorithm is verified via vehicle tests in real road. It has been shown that the threat assessment performance for the given driving situations can be significantly enhanced by the proposed algorithm. And this enhancement of risk assessment performance led to capabilities improvement of driver assistance functions of ADASs.

This paper describes an integrated driver model for vehicle-driver closed-loop simulation at high speed maneuvering. The proposed driver model is developed to specialize in limit handling, in order to be used as a validation platform of chassis control system. Thus, the proposed driver model emulates human driver's driving characteristics such as, desired path selection from varying preview area, deceleration against losing maneuverability. In high-speed cornering, steering with excessive corner-entry speed causes lateral tire force saturation readily. Sequentially, the lateral tire force saturation induces lateral instability of a vehicle. Deceleration is the most effective manipulation which driver can do. The proposed driver model is designed to utilize capability of tire force tightly, while securing lateral stability of the vehicle. The proposed driver model has been validated via comparison with an expert driver's driving data, collected on the Korea International Circuit in Yeongam, Korea.

This paper describes a robust yaw stability control for commercial vehicles. In the case of commercial vehicles, parameter variations are relatively large, compared to those of passenger vehicles, due to large variations of load conditions. A feasible parameter variation region can be constructed by Monte Carlo method. The parameter variations in commercial vehicles can cause performance deterioration of a yaw stability controller, designed with nominal parameters. To guarantee the robust performance for a yaw stability controller against parameter variations, it is necessary to design a robust one. To design a robust yaw stability controller, the methods of stochastic root locus and parameter sensitivity reduction are adopted. Computer simulation study was conducted to evaluate the proposed controller. From simulation study, it is shown that the proposed robust yaw stability controller is effective against parameter variations in commercial vehicles.

Recently hydraulic power steering systems are commonly used for heavy duty vehicles. The hydraulic pump is driven by belt connected to engine crank shaft. The main disadvantage of this steering system is that energy loss occurs in the case of straight-line driving situation (few or no steering situation). This fact is directly connected to reducing fuel efficiency of heavy duty vehicle equipped the hydraulic power steering systems. To improve the fuel efficiency, it is necessary to consider application of EHPS (Electro Hydraulic Power Steering system) or MDPS (Motor Driven Power Steering system) which have been developed for passenger cars. This paper introduces the research about Hybrid Electro Power Steering (Hybrid EPS) system which combines EHPS and MDPS for heavy duty vehicles. Also the dynamic model and control strategy for the Hybrid EPS are proposed to improve the fuel efficiency by minimizing the energy consumption in steering system using robust design method called “Taguchi Method”.

This paper presents a time delay compensation algorithm for environmental sensors of automated driving systems. The time delay involved with the transmission of the measurements from the sensors to the processor cannot be negligible because it is responsible for estimation and control of the system. As the automotive environmental sensors such as laser scanner or radar perform measurements at a constant frequency, the measurement time latencies can be assumed to be constant. From this aspect, the constant time delay characteristics is analyzed via vehicle tests and compensated by forward estimation based coordinate transformation. The proposed compensation algorithm has been verified via test data based open loop simulation of Automated Driving Systems (ADS). It is shown that the proposed compensation enhances environment perception performance and driver's safety.

For the generic assessment and the total management of collision risks in urban driving situations, it is important to estimate and represent the target vehicles' behavior such as yaw rate, absolute velocity and acceleration which are state of the target vehicle. To achieve this, this paper presents a compensation of wireless communication delay for integrated risk management of automated vehicle. Recent developments in vehicle onboard computers and wireless communications devices, also known as dedicated short-range communication (DSRC) devices allow the exchange of information between vehicles (inter-vehicle communications). In an application of vehicle to vehicle (V2V) communication, the most important issue is to handle delay which has a negative impact on safety issue since communication networks generally introduce delays. To cope with this problem, the inter-vehicle communication system is firstly modelled by reflecting signal characteristic. To compensate the communication delay, state augmented estimation algorithm is used based on extended Kalman filters (EKF). The performance of the proposed estimation algorithm is verified via real time simulations.

For advanced features of next generation vehicles, the real-time programs in automotive embedded systems are dramatically increasing. For such large volume program codes, this paper proposes a novel framework to use high-density and low-cost nonvolatile memory, i.e., NAND flash memory, as a low-cost means of storing and executing hard real-time programs. Regarding this, one challenge is that NAND flash memory allows only 2 KB page-based read operations not per-byte random accesses, which requires RAM as working storage for code executions. This paper proposes two solutions, i.e., partitioned RAM solution and shared RAM solution, that minimize the RAM size required to deterministically guarantee the deadlines of all the hard real-time tasks. The proposed solutions are verified with the actual real-time programs for unmanned autonomous driving. To the best of our knowledge, this is the first work that allows us to use NAND flash memory for hard real-time program executions with the minimal usage of RAM.

This paper presents a probabilistic and holistic prediction algorithm for vehicle states using multisensor fushion. Three concerns are mainly considered in this paper, i.e, reliable and reasonable information fusion, extension of predicted states, and real-time evaluation of prediction uncertainties. The main idea of this paper is that a state-prediction problem can be solved as a multistage optimal estimation problem based on the current vehicle motion, a road geometry description in the current body-fixed frame, a path-following behavior model, and the error covariance of each. The prediction algorithm consists of two sequential parts. The first part is estimation, which contains a vehicle filter that estimates the current vehicle states, and a road geometry filter, which approximates the road geometry. The second part is prediction, which consists of a path-following model that generates the future desired yaw rate, which acts as a virtual measurement, and a vehicle predictor, which predicts the future vehicle states by a maximum-likelihood filtering method. The prediction performance of the proposed method has been investigated via vehicle tests. Moreover, its applicability to integrated vehicle safety system (IVSS) has been validated via computer simulation studies. It is shown that the state-prediction performance can be significantly enhanced by the proposed prediction algorithm compared with conventional methods. The enhancement of the prediction performance allows for the improvement of driver assistance functions of an IVSS by providing accurate predictions about the future driving environment.

This paper has been focused on the design of throttle and brake controller for vehicle speed control. The control goals of the speed control are reduction of the effects of model uncertainty and external disturbance caused by the nonlinearity of the servo-level dynamics and the unpredictable driving resistance such as inclination of road and aero dynamic drag force. The tracking performance also should be guaranteed. To that end, a model free approach has been proposed in this paper. The proposed controller uses modified linear longitudinal vehicle model with reasonable assumptions to derive throttle and brake control law and a few parameters in the vehicle model has been defined to represent the system delay and variation of the vehicle parameters during driving. Since the defined parameters named vehicle characteristic variables(VCVs) vary depending on the vehicle states, an adaptation algorithm has been developed to estimate the VCVs. The error dynamics of the vehicle acceleration and VCVs have been analyzed to prove the stability of the proposed algorithm. The tracking performance of the model free cruise controller has been verified by simulation. The results not only show good tracking performance but also verify that the MFCC considerably reduces the effects of model uncertainty and external disturbance using adaptation algorithm.

This paper presents a probabilistic vehicle states prediction algorithm by using multi-sensor fusion. The system inputs come in two main varieties: 1) vehicle sensor signal, such as steering angle, longitudinal velocity, longitudinal acceleration and yaw rate and 2) vision sensor signal, such as curvature, slope and distance to lane mark. From these inputs, the algorithm presents the time series prediction of future vehicle states and the corresponding covariance matrixes for the pre-defined future time horizon. The probabilistic states prediction algorithm consists of two sequential parts. The first part is the estimation part which contains a vehicle filter which estimates current vehicle states and a road filter which approximates the road geometry. The second part is prediction part which consists of a path following model generating future desired yaw rate which acts as a virtual measurement and a vehicle predictor which predicts future vehicle states by maximum likelihood filtering method. The proposed algorithm has been investigated via test data based closed loop simulation with Smart Cruise Control (SCC) system. Compared to two kind of existing path prediction methods; a fixed yaw rate assumption based method and a lane keeping assumption based method, it has been shown that the states prediction performance can be significantly enhanced by the proposed prediction algorithm. And this enhancement of prediction performance led to capabilities improvement of driver assistance functions of SCC by providing accurate predictions about the future driving environment.

This paper deals with lateral disturbance compensation algorithm for an application to a Motor Driven Power Steering (MDPS) based driving assistant system. The lateral disturbance such as wind force and load from bank angle reduces the driver refinement and increases the possibility of an accident. In order to reduce the maneuvering effort of the driver in the disturbing situation, the lateral disturbance compensation algorithm has been proposed. The characteristics of the compensation system including a human driver model and the steering system have been mathematically analyzed. The control strategy using the motor overlay torque as a control input which improves the human steering behavior under the lateral disturbance has been proposed. A numerical simulation of the proposed algorithm has been conducted by full vehicle model and lateral driver model which represents steering behavior of human driver. The human torque and lateral deviation under the lateral disturbance are confirmed to be reduced by the simulation results.

This paper presents an algorithm for side crash prevention systems using a combined steering torque overlay and differential braking control. This system prevents lane changes when a driver attempts to lane change despite existence of a neighboring vehicle in the blind spot. For this purpose, the system needs some technologies for detecting a vehicle in blind spot, judging driver's lane change intention and controlling a vehicle to avoid side crash. In this paper, we focus on judging driver's intention and controlling a vehicle. The proposed system was evaluated via human driver model-in the loop simulation.

This paper describes development of coordinated control of tractive and braking forces using high wheel slip in order to enhance turning performance of electric vehicle equipped with in-wheel motors. In the case of conventional vehicle, turning radius is definitely limited by kinematic features with respect to wheel base, maximum steering angle and track width of the vehicle. Military and special purpose vehicles are required to overcome turning radius limitation in order to conduct urgent and emergency tasks and avoid enemies rapidly. The control purpose is achieved by minimizing lateral tire force of rear wheels using excessive wheel slip condition. It is possible for the vehicle to turn around central turning point using the proposed algorithm. The center turning point is defined based on the driver's intention. The coordinated control algorithm consists of three parts: an upper level controller that computes the desired net force and moment in order to make one point turning motion, a lower level controller distributes tractive and brake input torques of each wheel for excessive slip control and sensor/estimator provides vehicle information to controllers. Computer simulations have been conducted to evaluate performance of the proposed control algorithm. It has been shown from simulation results that turning performance can be significantly improved.

This paper presents an environment-detection-and-mapping algorithm for autonomous driving that is provided in real time and for both rural and off-road environments. Environment-detection-and-mapping algorithms have been designed to consist of two parts: 1) lane, pedestrian-crossing, and speed-bump detection algorithms using cameras and 2) obstacle detection algorithm using LIDARs. The lane detection algorithm returns lane positions using one camera and the vision module “VisLab Embedded Lane Detector (VELD),” and the pedestrian-crossing and speed-bump detection algorithms return the position of pedestrian crossings and speed bumps. The obstacle detection algorithm organizes data from LIDARs and generates a local obstacle position map. The designed algorithms have been implemented on a passenger car using six LIDARs, three cameras, and real-time devices, including personal computers (PCs). Vehicle tests have been conducted, and test results have shown that the vehicle can reach the desired goal with the proposed algorithm.