Lane Change Assistance Research Articles

Research on the vehicle lane-changing decision-making system in complex traffic environments

In order to ensure the safety of vehicles changing lanes, there should be a certain degree of interaction and dynamics between vehicles on the way. In this paper, the problems of non-interactive road information and imprecise path planning are investigated. Through the research of the road condition decision-making system, autonomous lane-changing assistance system and intelligent traffic system, vehicle wireless networking technology, vehicle-road cooperation technology, and lane-changing decision-making and planning technology are used to increase the frequency of information interaction between vehicles and the external environment in order to realize information interaction between vehicles and collaborative driving. In this paper, simulation experiments of vehicle lane-changing are carried out by using MATLAB Simulink and compared with other research models. The results show that the lane change planning data based on the road condition decision system is more accurate, which leads to fast lane change driving in complex traffic scenarios.

Which partially automated driving function do drivers prefer? Results from two field studies on public highways

Partial driving automation consists of several subsystems that drivers need to trust to an appropriate level and interact with in a secure manner. To investigate whether drivers adapt their trust functional specific, how they experience the subsystems, and what their preferences are, we conducted two field studies with two partially automated (SAE level 2) vehicles and involving a total of 132 drivers. In both studies, participants drove on a public highway with support from partial driving automation systems for longitudinal control (adaptive cruise control, ACC) and lateral control (lane-keeping assistance, LA). Participants in Study 2 were additionally able to use a lane change assistance (LC) system. The drivers' trust generally increased over time and reflected in how much a participant used the automation (Study 1). Hereby, in both studies drivers had functional specific trust: in Study 1 drivers trusted the ACC more than the LA. In Study 2 drivers in addition had lower trust in the LC than in the LA and the ACC. In their thinking-aloud statements, drivers were more positive about ACC and more critical about LA but reported more interaction difficulties with the ACC (Study 1). In Study 2 participants on average preferred the ACC over the LA and the LA over the LC. The interview responses suggest that the lower preference was due to the perceived reliability (LA) and usefulness (LC). In summary, our results indicate that drivers adapt their trust functional specific when using partial driving automation and have an overall preference for ACC that persists despite a higher number of interaction problems.

Safe Data-Driven Lane Change Decision Using Machine Learning in Vehicular Networks

This research proposes a unique platform for lane change assistance for generating data-driven lane change (LC) decisions in vehicular networks. The goal is to reduce the frequency of emergency braking, the rate of vehicle collisions, and the amount of time spent in risky lanes. In order to analyze and mine the massive amounts of data, our platform uses effective Machine Learning (ML) techniques to forecast collisions and advise the driver to safely change lanes. From the unprocessed large data generated by the car sensors, kinematic information is retrieved, cleaned, and evaluated. Machine learning algorithms analyze this kinematic data and provide an action: either stay in lane or change lanes to the left or right. The model is trained using the ML techniques K-Nearest Neighbor, Artificial Neural Network, and Deep Reinforcement Learning based on a set of training data and focus on predicting driver actions. The proposed solution is validated via extensive simulations using a microscopic car-following mobility model, coupled with an accurate mathematical modelling. Performance analysis show that KNN yields up to best performance parameters. Finally, we draw conclusions for road safety stakeholders to adopt the safer technique to lane change maneuver.

Personalized Lane Change Planning and Control By Imitation Learning From Drivers

In this article, we propose a novel personalized planning and control approach for lane change assistance system which can efficiently learn a model prediction control (MPC)-based driver-specific lane-changing policy via end-to-end imitation learning from a few driver demonstrations. Specifically, we build a novel learnable predictive model of the vehicle-driver system and design an adaptable cost function for the MPC-based lane change controller. We then calculate the gradient of the imitation loss with respect to the personalization parameters of the model and cost function via differentiating the optimality conditions, and update those parameters to minimize the imitation loss in an end-to-end fashion. A semi-physical simulation on a driving simulator and a closed-loop test on a real vehicle are conducted to validate the learning ability and personalized control performance. The results show that 1) the proposed method can automatically implement both the generalized and the personalized lane change planning and control by learning from demonstration data; 2) the proposed controller can adapt to different driver-specific behaviors; and 3) the proposed approach outperforms the model-free learning approach in terms of imitation accuracy, interpretability, data efficiency, and generalized performance.

Edge-Powered Assisted Driving For Connected Cars

Assisted driving for connected cars is one of the main applications that 5G-and-beyond networks shall support. In this work, we propose an assisted driving system leveraging the synergy between connected vehicles and the edge of the network infrastructure, in order to envision global traffic policies that can effectively drive local decisions. Local decisions concern individual vehicles, e.g., which vehicle should perform a lane-change manoeuvre and when; global decisions, instead, involve whole traffic flows. Such decisions are made at different time scales by different entities, which are integrated within an edge-based architecture and can share information. In particular, we leverage a queuing-based model and formulate an optimization problem to make global decisions on traffic flows. To cope with the problem complexity, we then develop an iterative, linear-time complexity algorithm called Bottleneck Hunting (BH). We show the performance of our solution using a realistic simulation framework, integrating a Python engine with ns-3 and SUMO, and considering two relevant services, namely, lane change assistance and navigation, in a real-world scenario. Results demonstrate that our solution leads to a reduction of the vehicles’ travel times by 66 percent in the case of lane change assistance and by 20 percent for navigation, compared to traditional, local-coordination approaches.

INTEGRATED RADAR AND COMMUNICATION SYSTEMS FOR HIGHLY AUTOMATED VEHICLES

The application of radar has spread to numerous civilian automotive purposes like adaptive cruise control, automotive emergency braking, blind spot detection, lane change assist, and so on. The need for ever-increasing rates in wireless communications has moved the frequency spectrum toward millimeter range, usually assigned to automotive radar. This has led to an integrated automotive radar and communication system, which results in limited electromagnetic pollution and lower cost, size, weight, and power. Improved massive multiple input, multiple output signal processing techniques are required as integration of these two systems will be based on large antenna arrays. Similar to the see-through technique of 3GPP Release 16, the authors have conducted a simulation experiment where data of multiple targets have been obtained with automotive radar and then sent to a gateway. From there, data are transmitted to a fifth-generation communication model. Final data obtained at a receiver of the communication system matches the original radar output, which proves that data have been successfully transferred from the radar system to the communication system, thus making it an integrated system. This system is very useful in the case of vehicle platooning.

DDPG-based controller of enhanced adaptive cruise control with lane-change assistance for an articulated vehicle

Traditional adaptive cruise control (ACC) would choose to follow when encountering low-speed cars in front, but this may lead to low driving efficiency. This paper proposes a controller of enhanced adaptive cruise control with lane-change assistance (LCACC) for an articulated vehicle. A two-layer hierarchical control structure is adopted in this study. The upper determines high-level commands, while the bottom consisting of two modified deep deterministic policy gradient (DDPG) networks, controls the steering wheel and throttle/brake, respectively, according to the commands made by the upper layer. The vehicle’s lateral and longitudinal control are decoupled and controlled by two modified DDPG networks. Through proper design of the state and reward function, the actions of the articulated vehicle such as steering and acceleration/braking are closer to those of humans, thus ensuring ride comfort. Compared with traditional ACC, the LCACC proposed in this study increases the driving efficiency of the articulated vehicle by an average of 16% when there is a low-speed lead car.

Challenges of Large-Scale Multi-Camera Datasets for Driver Monitoring Systems.

Tremendous advances in advanced driver assistance systems (ADAS) have been possible thanks to the emergence of deep neural networks (DNN) and Big Data (BD) technologies. Huge volumes of data can be managed and consumed as training material to create DNN models which feed functions such as lane keeping systems (LKS), automated emergency braking (AEB), lane change assistance (LCA), etc. In the ADAS/AD domain, these advances are only possible thanks to the creation and publication of large and complex datasets, which can be used by the scientific community to benchmark and leverage research and development activities. In particular, multi-modal datasets have the potential to feed DNN that fuse information from different sensors or input modalities, producing optimised models that exploit modality redundancy, correlation, complementariness and association. Creating such datasets pose a scientific and engineering challenge. The BD dimensions to cover are volume (large datasets), variety (wide range of scenarios and context), veracity (data labels are verified), visualization (data can be interpreted) and value (data is useful). In this paper, we explore the requirements and technical approach to build a multi-sensor, multi-modal dataset for video-based applications in the ADAS/AD domain. The Driver Monitoring Dataset (DMD) was created and partially released to foster research and development on driver monitoring systems (DMS), as it is a particular sub-case which receives less attention than exterior perception. Details on the preparation, construction, post-processing, labelling and publication of the dataset are presented in this paper, along with the announcement of a subsequent release of DMD material publicly available for the community.

Lane changing assistance strategy based on an improved probabilistic model of dynamic occupancy grids

Lane changing assistance strategy based on an improved probabilistic model of dynamic occupancy grids

An insight into crash avoidance and overtaking advice systems for Autonomous Vehicles: A review, challenges and solutions

Emergence of communication technologies made the automotive industries across the globe to embrace Advanced Driver Assistance Systems (ADAS) by considerable investments to ensure accident-free travel, reduction of pollution, fuel conservation. ADAS achieves its goals by integrating complex subsystems such as obstacle avoidance, overtaking advice, lane changing assistance, planning shortest routes, parking assistance, automatic gear shifting, etc., using the emerging technologies. This article emphasizes the road safety aspect of the ADAS by exploring Crash Avoidance and Overtaking Advice (CAOA) subsystems. Existing studies have a noticeable lack of connectivity between various aspects of CAOA subsystems. This review deeply explores and connects CAOA subsystems like road geometries, road debris, obstacle avoidance algorithms powered by Artificial Intelligence (AI), overtaking advice systems, perception challenges of human drivers in various light and weather conditions, driver inattention and misjudgments, vehicle blind-spots, vehicle parameter analysis, performance of vision sensors, in-vehicle computers, driver–vehicle interactions, Vehicle to Infrastructure (V2I) technologies. This article emphasizes the three primary performance metrics of the ADAS, namely accuracy, response time and robustness. Finally, this article discusses a typical functional architecture and gaps identified in existing studies. This article is structured to assist like-minded researchers, who work on CAOA systems for road safety.

ADMT: Advanced Driver’s Movement Tracking System Using Spatio-Temporal Interest Points and Maneuver Anticipation Using Deep Neural Networks

Assistive driving is a complex engineering problem and is influenced by several factors such as the sporadic nature of the quality of the environment, the response of the driver, and the standard of the roads on which the vehicle is being driven. The authors track the driver's anticipation based on his head movements using Spatio-Temporal Interest Point (STIP) extraction and enhance the anticipation of action accuracy well before using the RNN-LSTM framework. This research tackles a fundamental problem of lane change assistance by developing a novel model called Advanced Driver's Movement Tracking (ADMT). ADMT uses customized convolution-based deep learning networks by using Recurrent Convolutional Neural Network (RCNN). STIP with eye gaze extraction and RCNN performed in ADMT on brain4cars dataset for driver movement tracking. Its performance is compared with the traditional machine learning and deep learning models, namely Support Vector Machines (SVM), Hidden Markov Model (HMM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and provided an increment of almost 12% in the prediction accuracy and 44% in the anticipation time. Furthermore, ADMT systems outperformed all of the models in terms of both the accuracy of the system and the previously mentioned time of anticipation that is discussed at length in the paper. Thus it assists the driver with additional anticipation time to access the typical reaction time for better preparedness to respond to undesired future behavior. The driver is then assured of a safe and assisted driving experience with the proposed system.

Intention-Based Lane Changing and Lane Keeping Haptic Guidance Steering System

Haptic guidance in a shared steering assistance system has drawn significant attention in intelligent vehicle fields, owing to its mutual communication ability for vehicle control. By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle. However, current haptic guidance steering systems demonstrate some deficiencies in assisting lane changing. This study explored a new steering interaction method, including the design and evaluation of an intention-based haptic shared steering system. Such an intention-based method can support both lane keeping and lane changing assistance, by detecting a driver's lane change intention. By using a deep learning-based method to model a driver's decision timing regarding lane crossing, an adaptive gain control method was proposed for realizing a steering control system. An intention consistency method was proposed to detect whether the driver and the system were acting towards the same target trajectories and to accurately capture the driver's intention. A driving simulator experiment was conducted to test the system performance. Participants were required to perform six trials with assistive methods and one trial without assistance. The results demonstrated that the supporting system decreased the lane departure risk in the lane keeping tasks and could support a fast and stable lane changing maneuver.

Adaptive shared control strategy for lane changing assistance system via multi-mode switching

To address the lateral control issue between the automatic controller and the driver for lane changing assistance system, we present a novel multi-mode adaptive shared control strategy in optimal control framework. Different from traditional approaches that achieve shared control through adjusting control authority allocation, we aim at designing a human-friendly adaptive shared control scheme which can provide the driver with assistance in accordance with driving demands via multi-mode switching. Three control modes are proposed: 1. minimum-lateral error mode; 2. minimum-lateral acceleration mode; 3. minimum-interference mode. Meanwhile, we develop a hybrid model based on hidden markov model (HMM) and support vector machine (SVM) to recognize the optimum control mode. Mathematically, the shared control scheme is described as an optimal control problem, which is then addressed by using the improved Radau pseudospectral method (RPM). Numerical analysis and the driver-in-the-loop (DIL) tests show that the proposed shared control strategy has the advantage of ensuring driving safety while reducing driver’s workload.

Minimizing Deadline Misses and Total Run-time with Load Balancing for a Connected Car Systems in Fog Computing

Cloud computing helps in providing the applications with a few number of resources that are used to unload the tasks. But there are certain applications like coordinated lane change assistance which are helpful in cars that connects to internet has strict time constraints, and it may not be possible to get the job done just by unloading the tasks to the cloud. Fog computing helps in reducing the latency i.e the computation is now done in local fog servers instead of remote datacentres and these fog servers are connected to the nearby distance to clients. To achieve better timing performance in fog computing load balancing in these fog servers is to be performed in an efficient manner.The challenges in the proposed application includes the number of tasks are high, client mobility and heterogeneous nature of fog servers. We use mobility patterns of connected cars and load balancing is done periodically among fog servers. The task model presented here in this paper solves scheduling problem and this is done at the server level and not on the device level. And at last, we present an optimization problem formulation for balancing the load and for reducing the misses in deadline, also the time required for running the task in these cars will be minimized with the help of fog computing. It also performs better than somecommon algorithms such as active monitoring, weighted round robin and throttled load balancer.

VANET-Assisted Interference Mitigation for Millimeter-Wave Automotive Radar Sensors

As key sensors of the ADAS, mmWave radars have been widely used for fulfilling tasks including adaptive cruise control, lane-changing assistance and collision avoidance. However, the interference generated by mmWave radars mounted on close-by vehicles, if not managed well, could seriously degrade the radars’ performance, giving rise to a safety hazard. In this work, we study interference mitigation for the off-the-shelf 77 GHz FMCW mmWave radars. We review several state-of-the-art ideas for suppressing co-channel interference, based on which we introduce a VANET-assisted radar interference mitigation scheme, which is shown to be effective in an environment with dense traffic. Specifically, a TDMA based MAC protocol is devised that enables the coordination among vehicles on efficient multiple access of radar spectrum. Numerical results corroborate the performance gain of the proposed approach compared to the existing random frequency hopping approaches.

A Novel Approach to Integrate Human-in-the-Loop Testing in the Development Chain of Automated Driving: The Example of Automated Lane Change

Abstract For market introduction of advanced driver assistant (ADAS) and automated driving (AD) systems on full vehicle level, testing and validation is one of the biggest challenges. The present study describes a novel approach that integrates a driving simulator in a virtual development process aiming to reduce time and effort for system development. The approach is demonstrated on a specific automated lane change assist (LCA) system. To this end, the LCA function and the corresponding human machine interface (HMI) are developed and implemented in the driving simulator. The core of the approach is a driving simulator-based testing method which proposes a novel two stage testing concept and involves multiple test drivers. The method provides better insight into the overall system performance and, moreover, detects potentials for improvements dedicated for the ADAS functionalities as well as for the design of the HMI system. Using this method, a driving simulator study with 20 volunteer drivers is conducted to evaluate the LCA system with respect to driver acceptance and user friendliness. The results of the study will be used for the parametrization and fine tuning of the LCA function as well as for the HMI improvement.

Shared Steering Torque Control for Lane Change Assistance: A Stochastic Game-Theoretic Approach

The challenging issue of “human–machine copilot” opens up a new frontier to enhancing driving safety. However, driver–machine conflicts and uncertain driver/external disturbances are significant problems in cooperative steering systems, which degrade the system's path-tracking ability and reduce driving safety. This paper proposes a novel stochastic game-based shared control framework to model the steering torque interaction between the driver and the intelligent electric power steering (IEPS) system. A six-order driver–vehicle dynamic system, including driver/external uncertainty, is established for path-tracking. Then, the affine linear-quadratic-based path-tracking problem is proposed to model the maneuvers of the driver and IEPS. Particularly, the feedback Nash and Stackelberg frameworks to the affine-quadratic problem are derived by stochastic dynamic programming. Two cases of copilot lane change driving scenarios are studied via computer simulation. The intrinsic relation between the stochastic Nash and Stackelberg strategies is investigated based on the results. And the steering-in-the-loop experiment reveals the potential of the proposed shared control framework in handling driver–IEPS conflicts and uncertain driver/external turbulence. Finally, the copiloting experiments with a human driver further demonstrate the rationality of the game-based pattern between both the agents.

Personalized Lane-Change Assistance System With Driver Behavior Identification

An in-depth study on driving habits and personalized driving-assistance systems is conducive to the realization of vehicle safety and intelligent driving. In this paper, we present a personalized vehicle lane-change assistance system integrated with a driver-behavior identification strategy. First, the driver-behavior data-acquisition system is designed and established. Based on this, the input data of different kinds of drivers along with vehicle signals are collected under typical working conditions. The drivers are classified utilizing factor analysis and a fuzzy c-means clustering algorithm, and the identification of driver behavior is realized using a backpropagation neural network optimized by a particle swarm optimization algorithm. Then, personalized warning, planning, and control systems are designed for lane changing. The proposed personalized lane-change assistance system can provide more personalized recommendations to the drivers, increasing the potential for more widespread acceptance and use of advanced driver-assistance system. Finally, the correctness of the proposed personalized lane-change system is evaluated by conducting computer simulations and a driver-in-the-loop- simulation under various conditions. And the results show that the lane-change assistance system based on driver behavior can meet the driving needs of different drivers without sacrificing safety.

The Study of Location Specific Lane Change Impacts on Traffic Delay using Extended Cell Transmission Model

This paper comprehensively evaluates the influence of location specific lane change executions on delay and queue length. The extended macroscopic Cell Transmission Model (CTM) based lane change model has been developed by adopting the formulations of diverging and merging in one-way traffic flow. The extended CTM model uses a pre-determined lane change rate and traffic parameters including free flow speed, jam density, cell length and time-step while the inflow parameters were generated form real traffic data collected in Bandar Sunway, Malaysia. The results demonstrate that the lane change maneuver approaching the exit of intersection incurs the highest delay. From real observation, drivers have high tendency to perform mandatory lane changing compared with discretionary lane change in urban arterials. The results can be further used to develop lane change assistance model to improve the traffic flows.

Scenario Model Predictive Control for Lane Change Assistance and Autonomous Driving on Highways

This paper presents a novel design of control algorithms for lane change assistance and autonomous driving on highways, based on recent results in Scenario Model Predictive Control (SCMPC). The basic idea is to account for the uncertainty in the traffic environment by a small number of future scenarios, which is intuitive and computationally efficient. These scenarios can be generated by any model-based or data-based approach. The paper discusses the SCMPC design procedure, which is simple and can be generalized to other control challenges in automated driving, as well as the controller's robustness properties. Experimental results demonstrate the effectiveness of the SCMPC algorithm and its performance in lane change situations on highways.