Lane Keeping Assist System Research Articles

DESIGN AND IMPLEMENTAION OF SAFETY MEASURES CAUSE BY DROWSINESS DETECTION IN AUTOMOTIVE VEHICLE

Driver’s drowsiness is the major problem that causes road accidents. Unlike normal facial expression, drowsiness is defined to be a condition of exhaustion, where the expression of the face is different from usual. The important steps in detecting drowsiness are face detection and expression detection. When the detection occurs that time the hazard lights are activate automatically to warn other drivers that the vehicle is a temporary obstruction. Also we have proposed new safety method using Ultrasonic sensors. It is used to detect the obstacles in which by using transmitter and receiver signals. The barrier principle determines the distance from the sensor to the reflector (Retro-Reflective Sensor) or to an object (Through-Beam Sensor) in the measuring range. The distance measurement using ultrasonic sensors to detect obstacles and their distances. Once the obstacle has been detected and safe separation distance is reached, the vehicle will automatically get stopped and also shared control concept for lane keeping assist (LKA) systems of intelligent vehicles. The core idea is to combine system perception with robust control so that the proposed strategy can successfully share the control authority between human drivers and the LKA system. This shared control strategy is composed of two parts, namely an operational part and a tactical part. Two local optimal-based controllers with two predefined objectives (i.e., lane keeping and conflict management) are designed in the operational part. The control supervisor in the tactical part aims to provide a decision making signal which allows for a smooth transition between two local controllers. The control design is based on a human-in the-loop vehicle system to improve the mutual driver-automation understanding, thus reducing or avoiding the conflict. In particular, the control design is formulated as an LMI optimization which can be easily solved with numerical solvers. The effectiveness of the proposed shared control method is clearly demonstrated through various hardware experiments with human drivers. Its controls the steering and to go on the straight road.

A New Model-Free Shared Control for Lane-Keeping Assist System: Theory and Experimental Validation

A New Model-Free Shared Control for Lane-Keeping Assist System: Theory and Experimental Validation

Effects of Sim2Real Image Translation via DCLGAN on Lane Keeping Assist System in CARLA Simulator

Autonomous vehicle (AV) simulation using a virtual environment has the advantage of being able to test algorithms in various scenarios with reduced resources. However, there may exist a visual gap between the virtual environment and the real-world. In this paper, in order to mitigate this gap, we trained Dual Contrastive Learning Generative Adversarial Networks (DCLGAN) to realistically convert the image of the CARLA simulator and then evaluated the effect of the Sim2Real conversion focusing on the lane keeping assist system (LKAS). Moreover, in order to avoid the case where the lane is translated distortedly by DCLGAN, we found the optimal training hyperparameters using feature similarity (FSIM). After training, we built a system that connected the CARLA simulator with DCLGAN and AV in real-time. As for the result, we collected data and analyzed them using the following four methods. First, image reality was measured with Fréchet Inception Distance (FID), which we quantitatively verified to reflect the lane characteristics. The CARLA images that passed through DCLGAN had smaller FID values than the original images. Second, lane segmentation accuracy through ENet-SAD was improved by DCLGAN. Third, in the curved route, the case of using DCLGAN drove closer to the center of the lane and had a high success rate. Lastly, in the straight route, DCLGAN improved lane restoring ability after deviating from the center of the lane as much as in reality. Consequently, it convinced that the proposed method could be applicable to mitigate the gap of simulation toward real-world.

Personalized Ground Vehicle Lane-Keeping Assist System Design: An Adaptive Sliding Mode Control Formulation With L1+α Reachability

This paper proposes a personalized ground-vehicle lane-keeping assist system (LKA). To begin with, a control-oriented model unifying nonlinear vehicle-road dynamics and a linear driver lane-keeping steering angle model is derived. Subsequently, a novel LKA control strategy, alloying an L1+α -reachable adaptive sliding-mode controller and a shifted-logistic-function-based smooth parameter projection scheme, is formulated. Through a non-quadratic Lyapunov redesign, the sliding manifold is asymptotically reached, throughout which the trajectory of the switching function's value is confined inside the L1+α signal space. In addition, the suggested smooth projection operator can prevent the unbounded control parameter drift whilst maintaining the control command's smoothness. A simulation study employing the CarSim-Simulink joint platform and a cyber driver model is performed to evaluate the proposed personalized LKA adaptive controller and compare it with a linear-robust-control-based solution.

Impact of lane keeping assist system camera misalignment on driver behavior

This research investigated the impact of sensor camera misalignment on the quality of the lane keeping assistance, end user experience and driving performance. Testing was performed with 16 participants, both males and females, with an age range from 25 to 35. The Lane Keeping Assist System (LKAS) errors in lateral offset ranged from −0.66 m to 0.66 m and testing was performed on two roads. The results indicated that introducing an error in the LKAS system of 0.66 m caused the mean lane position of the vehicle to move in a similar direction by 0.1 m while some individuals showed as much as a 0.2 m change in their lateral position. Increases in error in the camera misalignment also increased the number of steering reversals indicating that the drivers worked harder to stay in their lane.

Development and Testing of a Methodology for the Assessment of Acceptability of LKA Systems

In recent years, driving simulators have been widely used by automotive manufacturers and researchers in human-in-the-loop experiments, because they can reduce time and prototyping costs, and provide unlimited parametrization, more safety, and higher repeatability. Simulators play an important role in studies about driver behavior in operating conditions or with unstable vehicles. The aim of the research is to study the effects that the force feedback (f.f.b.), provided to steering wheel by a lane-keeping-assist (LKA) system, has on a driver’s response in simulators. The steering’s force feedback system is tested by reproducing the conditions of criticality of the LKA system in order to minimize the distance required to recover the driving stability as a function of set f.f.b. intensity and speed. The results, obtained in three specific criticality conditions, show that the behaviour of the LKA system, reproduced in the simulator, is not immediately understood by the driver and, sometimes, it is in opposition with the interventions performed by the driver to ensure driving safety. The results also compare the performance of the subjects, either overall and classified into subgroups, with reference to the perception of the LKA system, evaluated by means of a questionnaire. The proposed experimental methodology is to be regarded as a contribution for the integration of acceptance tests in the evaluation of automation systems.

Hardware simulation of lane keeping assist based on sensor fusion

PurposeSafety is one of the most crucial factors in transportation due to so many factors, including human-error, that might result in various small to fatal accidents. This is why lane keeping assist (LKA) is an important system that needs to be developed. LKA will prevent the vehicle from moving to another lane because the driver is negligent to maintain the direction of the vehicle.Design/methodology/approachIn this study, LKA works using camera and ultrasonic sensors. The data coming from these two types of sensors are then fused to determine how should the car reacts to some certain situation so that it stays on the lane. The sensor fusion method was used to further ensure the car's safety.FindingsThe results of the hardware simulation show that LKA can successfully avoid the car from getting off the lane with safety index of 95% for high-speed mode and 100% for medium and low-speed mode; meanwhile on the use of ultrasonic sensor, the speed of the car is adjusted to the distance of the car's side disturbance.Originality/valueThis research has succeeded in simulating a sensor fusion–based LKA system.

A scenario- and platform-aware design flow for image-based control systems

Image-based control (IBC) systems are increasingly being used in various domains including autonomous driving. The key challenge in IBC is to deal with high computation demand while guaranteeing performance and safety requirements such as stability. While modern industrial heterogeneous platforms, such as NVIDIA Drive, offer the necessary compute power, application development on these platforms with performance and safety guarantees is still challenging. Alternative time-predictable platforms are not yet in widespread use.A typical design flow for IBC systems consists of three distinct elements: (i) mapping tasks onto platform resources; (ii) timing analysis, consisting of task-level worst-case execution time (WCET) analysis and application-level analysis to obtain worst-case performance bounds on aspects such as latency and throughput; (iii) controller design using the obtained performance bounds, ensuring performance and safety. While such a three-step design process is modular in nature, it usually leads to over-dimensioned systems with sub-optimal performance, because task- and/or application-level timing bounds are pessimistic.We present a scenario- and platform-aware design flow for IBC systems that exploits frequently occurring workload scenarios to optimize performance. For industrial platforms, where tight task-level WCET bounds are difficult to obtain, we moreover propose to use frequently occurring task execution times instead of WCET estimates to obtain tight application-level temporal bounds. During controller design, we then optimize performance and guarantee stability by identifying appropriate system scenarios and by designing a switched controller that switches between those scenarios. We illustrate our method considering a predictable multiprocessor system-on-chip platform - CompSOC. We validate the proposed method using hardware-in-the-loop (HiL) experiments with an industrial heterogeneous multiprocessor platform - NVIDIA Drive PX2 - considering a lane keeping assist system (LKAS). We obtain an improved control performance compared to state-of-the-art IBC design.

Approximation-Aware Design of an Image-Based Control System

Image-based control (IBC) systems are common in many modern applications. In such systems, image-based sensing imposes massive compute workload, making them challenging to implement on embedded platforms. Approximate image processing is a way to handle this challenge. In essence, approximation reduces the workload at the cost of additional sensor noise. In this work, we propose an approximation-aware design approach for optimizing the energy, memory and performance of an IBC system, making it suitable for embedded implementation. First, we perform compute- and data-centric approximations and evaluate its impact on the energy efficiency, memory utilization and closed-loop quality-of-control (QoC) of the IBC system. We observe that the workload reductions due to approximations allow mapping these lighter approximated IBC tasks to embedded platforms with lower power consumption while still ensuring proper system functionality. Therefore, we explore the interplay between approximations and platform mappings to improve the energy-efficiency of IBC systems. Further, an IBC system operates under several environmental scenarios e.g., weather conditions. We evaluate the sensitivity of the IBC system to our approximation-aware design approach when operated under different scenarios and perform a failure probability (FP) analysis using Monte-Carlo simulations to analyze the robustness of the approximate system. Finally, we design an optimal approximation-aware controller that models the approximation error as sensor noise and show QoC improvements. We demonstrate the effectiveness of our approach using a concrete case-study of a lane keeping assist system (LKAS) using a heterogeneous NVIDIA AGX Xavier embedded platform in a hardware-in-the-loop (HiL) framework. We show energy and memory reduction of up to 92% and 88% respectively, for 44% QoC improvements with respect to the accurate implementation. We show that our approximation-aware design approach has an FP (per km) $\leq 9.6\times 10^{-6}$ %.

Driver-Automation Cooperation Oriented Approach for Shared Control of Lane Keeping Assist Systems

This paper presents a novel shared control concept for lane keeping assist (LKA) systems of intelligent vehicles. The core idea is to combine system perception with robust control so that the proposed strategy can successfully share the control authority between human drivers and the LKA system. This shared control strategy is composed of two parts, namely an operational part and a tactical part. Two local optimal-based controllers with two predefined objectives (i.e., lane keeping and conflict management) are designed in the operational part. The control supervisor in the tactical part aims to provide a decision-making signal which allows for a smooth transition between two local controllers. The control design is based on a human-in-the-loop vehicle system to improve the mutual driver-automation understanding, thus reducing or avoiding the conflict. The closed-loop stability of the whole driver-vehicle system can be rigorously guaranteed using the Lyapunov stability argument. In particular, the control design is formulated as an LMI optimization which can be easily solved with numerical solvers. The effectiveness of the proposed shared control method is clearly demonstrated through various hardware experiments with human drivers.

Research on lane-keeping control strategy for bus

Owing to the frequent occurrence of commercial vehicle lane departure, a novel lane departure warning (LDW) system based on driver behaviour characteristics and a lane-keeping assist system (LKAS) based on electro-hydraulic steering system for buses are presented in this paper. Considering the differences between driver behaviour characteristics, a newly designed dynamic warning algorithm is proposed to predict the lane departure risk. Then, for the LKAS control, a simulation model of the electro-hydraulic steering system for buses is introduced for the active-steering-assist control and a multi-mode active control algorithm is designed for the lane keeping. To verify the effectiveness of the proposed control strategy, the co-simulation softwares of TruckSim, AMESim and MATLAB/Simulink are employed for the experiment validation. After extended simulation, it is found that the proposed LDW algorithm demonstrates an effective lane departure detection, and when the imminent lane departure is detected, the multi-mode active control algorithm can rapidly make adjustments to avoid the bus departing from the original lane.

Research on lane-keeping control strategy for bus

Owing to the frequent occurrence of commercial vehicle lane departure, a novel lane departure warning (LDW) system based on driver behaviour characteristics and a lane-keeping assist system (LKAS) based on electro-hydraulic steering system for buses are presented in this paper. Considering the differences between driver behaviour characteristics, a newly designed dynamic warning algorithm is proposed to predict the lane departure risk. Then, for the LKAS control, a simulation model of the electro-hydraulic steering system for buses is introduced for the active-steering-assist control and a multi-mode active control algorithm is designed for the lane keeping. To verify the effectiveness of the proposed control strategy, the co-simulation softwares of TruckSim, AMESim and MATLAB/Simulink are employed for the experiment validation. After extended simulation, it is found that the proposed LDW algorithm demonstrates an effective lane departure detection, and when the imminent lane departure is detected, the multi-mode active control algorithm can rapidly make adjustments to avoid the bus departing from the original lane.

Development of the Lane Keeping Control System Using State-Varying Surface for Vulnerable Road Users

This paper proposes a new Lane Keeping Assist (LKA) system based on the integrated control strategy with AFS and BTV. To be specific, the steering controller calculates the gear ratio of AFS to align with the target lane whereas the braking controller determines differential brake pressure using Sliding Mode Control (SMC) theory according to the state-varying sliding surface with Fuzzy model. In recent years, auto industries have produced the lane keeping applications to prevent lane departure caused by drivers’ distractions or drowsiness. To also prevent wrist injury in drivers while steering, current LKA systems limit the output values of steering-wheel assist torque. This limiting mechanism, however, can cause a problem that cannot follow a road curvature when an older driver overexerts an inappropriate control effort. A new LKA system of the AFS and BTV integrated controller has since been drafted to solve this problem, and validated its performance in regards to the test conditions given with various driver models.

Sensor Reduction for Driver-Automation Shared Steering Control via an Adaptive Authority Allocation Strategy

This paper presents a new shared control method for lane keeping assist (LKA) systems of intelligent vehicles. The proposed method allows the LKA system to effectively share the control authority with a human driver by avoiding or minimizing the conflict situations between these two driving actors. To realize the shared control scheme, the unpredictable driver-automation interaction is explicitly taken into account in the control design via a fictive driver activity variable. This latter is judiciously introduced into the driver–road–vehicle system to represent the driver's need for assistance in accordance with his/her real-time driving activity. Using Lyapunov stability arguments, Takagi–Sugeno fuzzy model-based design conditions are derived to handle not only the time-varying driver activity variable, but also a large variation range of vehicle speed. Both simulation and hardware experiments are presented to demonstrate that the proposed control strategy together with a linear matrix inequality design formulation provide an effective tool to deal with the challenging shared steering control issue. In particular, a fuzzy output feedback control scheme is exploited to achieve the shared control goal without at least two important vehicle sensors. These physical sensors are widely employed in previous works to measure the lateral speed and the steering rate for the control design and real-time implementation. The successful results of this idea of sensor-reduction control has an obvious interest from practical viewpoint.

Optimal Lane Finder using Sensor Fusion Techniques to Prevent Road Accidents

Objectives: Most of the accidents could be avoided or prevented through simple measures like speed limit, precautions for the driver’s safety and discipline among road users. Most of the accidents occur on highways, especially when changing lanes. This paper focuses on reducing such accidents by using Lane Keeping Assist System (LKAS). Methods: This LKAS is based on the concept of neural network model, which has a high complexity and high cost design for functional implementation. Findings: Though this system has more advantages, it cannot be implemented in all range of cars. In order to overcome this, a cost affordable, safety alert system suitable for all range of cars is proposed using low cost and low power consumption open source device, in which vehicles are incorporated with sensors which helps in notifying when the vehicle is overtake and makes it easier for people to control the movements of vehicle. Application/Improvement: It helps to indicate the unconditional changes of vehicle between the lanes and also reduce the accidents. Apart from this, fading and blinking of front head lights automated whenever approaching in opposite direction.

生活道路における歩行者等とのすれ違い回避時のドライバーの運転操作および車両挙動

Recently, car manufacturers are developing automobile active safety systems to prevent traffic accident. Active safety systems include automated driving system, AEB (Automatic Electric Brakes), ESC (Electric Stability Control), LAKS (Lane Keeping Assist System), IPAS (Intelligent Parking Assist System). It is important for the system to make drivers understand the system easily and operate appropriately. Driver’s acceptability of the system will increase when the system functions in the same way as a driver. It is necessary to research driving behavior to emerge the systems that enable us to use comfortably and unmistakably. In this paper, we study behavior of a vehicle when the vehicle passes a pedestrian on the local street. We measured some quantities of vehicle behavior such as trajectory, acceleration, steering angle using a vehicle on the test course which simulates the local street. In the experiments, the subjects are chosen with various driving record and frequency of driving. As a result, it is revealed that characteristics of vehicle behavior depend on driver‘s skill and frequency.

Haptic Shared Control in Steering Operation Based on Cooperative Status Between a Driver and a Driver Assistance System

Haptic shared control is expected to achieve a smooth collaboration between humans and automated systems, because haptics facilitate mutual communication. A methodology for sharing a given task is important to achieve effective shared control. Therefore, the appropriate cooperative relationship between a human operator and automated system should be considered. This paper proposes a methodology to evaluate the cooperative status between the operator and the automated system in the haptic shared control of a steering operation using a pseudo-power pair of torque from each agent and the vehicle lateral velocity as each agent's contribution to vehicle motion. This method allows us to estimate cooperative status based on two axes: the initiative holder and the intent consistency between the two agents. A control method for a lane-keeping assist system (LKAS) that enables drivers to change lanes smoothly is proposed based on the estimated cooperative status. A gain-tuning control method based on the estimated cooperative status is proposed to decrease the assistance system's pseudo-power when intent inconsistency occurs. A method for switching the followed lane to match the driver's and assistance system's intentions is also proposed. A user study using a driving simulator is conducted to demonstrate the effectiveness of the proposed methods. The results demonstrate that the proposed methods facilitate smooth driver-initiated lane changes without significantly affecting the driver's torque or steering wheel angle while significantly improve lane-keeping performance.