Autonomous Lane Research Articles

Human-like Decision Making for autonomous lane change driving: a hybrid inverse reinforcement learning with game-theoretical vehicle interaction model

The development of automated driving vehicles aims to provide safer, comfortable, and more efficient mobility options. However, the decision-making control of autonomous vehicles still embraces limitations on human performance mimicry. These limitations become particularly evident in complex and unfamiliar driving scenarios, where weak decisionmaking abilities and poor adaptation of vehicle behaviour are prominent issues. This paper proposes a game-theoretic decisionmaking algorithm for human-like driving in the vehicle lane change scenario. Firstly, an inverse reinforcement learning (IRL) model is used to quantitatively analyse the lane change trajectories of the natural driving dataset, establishing the human-like human cost function. Subsequently, joint safety, comfort to build the comprehensive decision cost function. Use the combined decision cost function to conduct a non-cooperative game of vehicle lane changing decision to solve the optimal decision of host vehicle lane changing. The host vehicle lane-changing decision problem is formulated as a Stackelberg game optimization problem. To verify the feasibility and effectiveness of the algorithm proposed in this study, a lane change test scenario has been established. Firstly, we analyse the human-like decision-making model derived by the maximum entropy inverse reinforcement learning algorithm to verify the effectiveness and robustness of the IRL algorithm. Secondly, the human-like game decisionmaking algorithm in this paper is validated by conducting an interactive lane-changing experiment with obstacle vehicles of different driving styles. The experimental results prove that the human-like driving decision-making model proposed in this study can make lane-changing behaviours in line with human driving patterns in lane-changing scenarios of expressway.

RRT-guided experience generation for reinforcement learning in autonomous lane keeping

Reinforcement Learning has emerged as a significant component of Machine Learning in the domain of highly automated driving, facilitating various tasks ranging from high-level navigation to control tasks such as trajectory tracking and lane keeping. However, the agent’s action choice during training is often constrained by a balance between exploitation and exploration, which can impede effective learning, especially in environments with sparse rewards. To address this challenge, researchers have explored combining RL with sampling-based exploration methods such as Rapidly-exploring Random Trees to aid in exploration. This paper investigates the effectiveness of classic exploration strategies in RL algorithms, particularly focusing on their ability to cover the state space and provide a quality experience pool for learning agents. The study centers on the lane-keeping problem of a dynamic vehicle model handled by RL, examining a scenario where reward shaping is omitted, leading to sparse rewards. The paper demonstrates how classic exploration techniques often cover only a small portion of the state space, hindering learning. By leveraging RRT to broaden the experience pool, the agent can learn a better policy, as exemplified by the dynamic vehicle model’s lane-following problem.

Fuzzy Logic-Based Autonomous Lane Changing Strategy for Intelligent Internet of Vehicles: A Trajectory Planning Approach

The autonomous lane change maneuver is a critical component in the advancement of intelligent transportation systems (ITS). To enhance safety and efficiency in dynamic traffic environments, this study introduces a novel autonomous lane change strategy leveraging a quintic polynomial function. To optimize the trajectory, we formulate an objective function that balances the time required for lane changes with the peak acceleration experienced during the maneuver. The proposed method addresses key challenges such as driver discomfort and prolonged lane change durations by considering the entire lane change process rather than just the initiation point. Utilizing a fifth-order polynomial for trajectory planning, the strategy ensures smooth and continuous vehicle movement, reducing the risk of collisions. The effectiveness of the method is validated through comprehensive simulations and real-world vehicle tests, demonstrating significant improvements in lane change performance. Despite its advantages, the model requires further refinement to address limitations in mixed traffic conditions. This research provides a foundation for developing intelligent vehicle systems that prioritize safety and adaptability.

On-board model predictive control for autonomous lane keeping with fuzzy preview distance: Design and experiment

This paper concerns with the development of computationally efficient lane keeping control method for the autonomous vehicles. To obtain autonomous lane keeping, model predictive control (MPC) scheme was intensively investigated in the previous studies owing to its inherent advantage of dealing with constrained multivariable systems. However, the tradeoff problem between the good tracking performance and the low computational complexity is inevitably raised in developing of MPC-based lane keeping technology. To alleviate the conflict between performance and cost, an on-board MPC with fuzzy preview distance is designed in this study. A linear system dynamics model is used in the MPC design to reduce the computational cost, and a fuzzy logic algorithm is developed to select an appropriate preview distance for enhancing the MPC performance. Further, hardware-in-the-loop test is adopted to explore the effectiveness and efficiency of the proposed control method. In comparison to the proportional-integral controller, the experimental results show that the MPC is more sensitive to the selective value of fixed preview distance. Since the significant impact of preview distance selection on the MPC-based lane keeping performance, the fuzzy logic algorithm is of the essence in terms of selecting the appropriate preview distance for MPC enhancement under different vehicle speed and road curvature. Eventually, experimental results validate that the proposed fuzzy preview distance algorithm can effectively improve the MPC-based lane keeping performance for autonomous vehicles subject to limited computational resource.

Discretionary Lane-Change Decision and Control via Parameterized Soft Actor–Critic for Hybrid Action Space

This study focuses on a crucial task in the field of autonomous driving, autonomous lane change. Autonomous lane change plays a pivotal role in improving traffic flow, alleviating driver burden, and reducing the risk of traffic accidents. However, due to the complexity and uncertainty of lane-change scenarios, the functionality of autonomous lane change still faces challenges. In this research, we conducted autonomous lane-change simulations using both deep reinforcement learning (DRL) and model predictive control (MPC). Specifically, we used the parameterized soft actor–critic (PASAC) algorithm to train a DRL-based lane-change strategy to output both discrete lane-change decisions and continuous longitudinal vehicle acceleration. We also used MPC for lane selection based on the smallest predictive car-following costs for the different lanes. For the first time, we compared the performance of DRL and MPC in the context of lane-change decisions. The simulation results indicated that, under the same reward/cost function and traffic flow, both MPC and PASAC achieved a collision rate of 0%. PASAC demonstrated a comparable performance to MPC in terms of average rewards/costs and vehicle speeds.

Autonomous Lane Detection Car using Raspberry PI and Open CV

This research paper introduces an innovative method for real-time autonomous lane detection utilizing a Raspberry Pi embedded system and the OpenCV computer vision library. The primary objective is to improve vehicle navigation capabilities by precisely identifying lane boundaries from input video streams. The system's robust performance across diverse environmental conditions is achieved through the computational power of the Raspberry Pi platform and the flexibility of OpenCV. The methodology encompasses image preprocessing, lane detection algorithms, and seamless integration with the Raspberry Pi hardware. Through comprehensive experimental results, the proposed approach showcases its effectiveness and efficiency in autonomously detecting lanes. This research contributes to the development of safer and more reliable autonomous driving systems

Design and Implementation of a Hybrid Path Planning Approach for Autonomous Lane Change Manoeuvre

Design and Implementation of a Hybrid Path Planning Approach for Autonomous Lane Change Manoeuvre

Study on Anthropomorphic Lane Changing Decision Making for Smart Trucks Based on Driving Behavior

In order to improve the applicability of the lane change decision model to different styles of drivers, especially for trucks with less flexibility and stability of their own, safe and reasonable lane change decisions are more important. In this paper, based on the research of integrating personalized driver styles in automatic lane change control technology, a vehicle lane change decision model considering driver styles is established. Firstly, the HighD dataset is screened and the drivers are classified by driving style using principal component analysis and K-means (K-means) cluster analysis. Secondly, we propose a lane change decision model that takes into account the rationality and safety of lane change by learning human drivers' driving behavior experience through Long Short-Term Memory (LSTM) method, so as to improve drivers' acceptance and satisfaction of smart cars. Finally, the joint simulation by Simulink/CarSim/PreScan software proves that the lane change decision method based on the driver's style proposed in this study can realize the autonomous lane change task of smart cars.

Automated Speed and Lane Change decision-making Model using Support Vector Machine

One of the major obstacles that the auto industry must overcome is the rise of autonomous vehicles. The study of lane-changing is an important part of this problem. Previous studies on autonomous vehicle lane changes have predominantly focused on lane change path planning and path monitoring, with limited attention given to the autonomous vehicle's lane change decision-making process. This paper introduces a novel Lane Change Decision-Making Model for autonomous vehicles using the Support Vector Machine (SVM) method. The suggested model employs real-time sensor data to assess whether or not a lane change is possible, taking into account the proximity of other vehicles (cars, buses, motorbikes), and adjusting speed as necessary to ensure a seamless transition. Researching the various facets of lane changes in autonomous vehicles allows for decision-making that is grounded in utility, safety, and tolerance. The implementation of a support vector machine (SVM) technique with Bayesian parameter optimization is used to deal with the non-linearity and complexity of the process of autonomous lane change decision-making. Finally, we compare the suggested SVM model against a rule-based lane change model using the test data. The SVM-based strategy is shown to improve lane change decision-making in a comprehensive simulation exercise, which in turn improves the safety and efficiency of autonomous driving systems. The experiment also use a real vehicle to gauge the efficacy of the underlying decision-making model.

Optimized deep extreme learning machine for traffic prediction and autonomous vehicle lane change decision-making

Deep learning occupies a prominent position in the field of machine learning, where researchers have introduced autoencoder into extreme learning machine (ELM) to establish deep extreme learning machine (DELM), with the aim of enabling autonomous feature learning from data. This approach has found widespread applications in various domains, including finance and electrochemistry. However, the network accuracy of DELM is sensitive to the initial weighting and bias configurations, which can be negatively impacted by random initialization. To mitigate the adverse effects of such random initialization on network performance, this study employs two swarm intelligence optimization algorithms, particle swarm optimization (PSO) and harris hawks optimization (HHO), to optimize the input weights and biases of DELM. In addition, we apply the variational mode decomposition (VMD) technique to decompose the original data, enabling a deeper exploration of latent information within the data. Subsequently, two integrated models are constructed: VMD-HHO-DELM and VMD-PSO-DELM. We apply these models to address road traffic condition prediction and autonomous lane change decision-making problems, with a specific focus on the transportation domain. Through extensive experimentation on two real-world datasets, we observe that deep learning models based on swarm intelligence optimization algorithms exhibit excellent performance across various scenarios. In the context of road traffic condition prediction, our experiments reveal superior results under different time intervals and traffic volumes compared to traditional models, all while maintaining higher operational efficiency. For the autonomous lane change decision experiment, we establish a driver dissatisfaction model that aids in formulating more reasonable lane change decisions, thus reducing the frequency of abrupt lane changes.

Safe autonomous lane changes and impact on traffic flow in a connected vehicle environment

Despite the recent advancements in autonomous vehicle technologies, performing safe lane changes and merging in dense traffic environments remains an open challenge. One important question is how to find a space to merge into without placing any vehicle in a collision-prone situation. Moreover, what is the traffic flow impact of doing so? To tackle this issue, we start by adopting a safety definition based on a worst-case braking scenario. We then propose a decentralized controller-agnostic cooperative approach for lane changes that relies only on Vehicle-to-Vehicle communications and guarantees safety. In our method, the merging vehicle operates as having two possible leaders, one in its own lane and one in the destination lane, till the lane change maneuver is completed. Furthermore, the future following vehicle in the destination lane cooperates by acting as if the merging vehicle has already changed lanes. The merging vehicle only performs the lane change maneuver when the gaps are safe. Vehicle-level simulations are used to evaluate the approach in detail for a single lane change maneuver. Then, the method’s impact on highway safety and traffic flow is assessed using microscopic traffic simulations based on the commercial software VISSIM. We simulate three types of vehicles: adaptive cruise control equipped vehicles, autonomous vehicles, and connected and autonomous vehicles. The various simulations allow us to identify which improvements are brought by cooperative lane changes. Results indicate that connected and autonomous vehicles can achieve almost zero collision risk in congested and uncongested scenarios while improving traffic flow by 26% in the congested case. However, energy consumption increases significantly in the uncongested scenario. Moreover, our method outperforms an existing cooperative lane-changing method regarding safety and traffic flow. Our simulations with mixed traffic suggest that the proposed method is advantageous only at high penetrations of autonomous vehicles or in congested situations.

Modeling and Analysis of Driving Behaviour for Heterogeneous Traffic Flow Considering Market Penetration under Capacity Constraints

Based on analytical and simulation methods, this paper discusses the path choice behavior of mixed traffic flow with autonomous vehicles, advanced traveler information systems (ATIS) vehicles and ordinary vehicles, aiming to promote the development of autonomous vehicles. Firstly, a bi-level programming model of mixed traffic flow assignments constrained by link capacity is established to minimize travel time. Subsequently, the algorithm based on the incremental allocation method and method of successive averages is proposed to solve the model. Through a numerical example, the road network capacity under different modes is obtained, the impact of market penetration on travel time is analyzed, and the state and characteristics of single equilibrium flow and mixed equilibrium flow are explored. Analysis results show that the road network can be maximized based on saving travel time when all vehicles are autonomous, especially when the autonomous lane is adopted. The travel time can be shortened by increasing the market penetration of autonomous vehicles and ATIS vehicles, while the former is more effective. However, the popularization of autonomous vehicles cannot be realized in the short term; the market penetration of autonomous vehicles and ATIS vehicles can be set to 0.2 and 0.6, respectively, during the introduction period.

Optimal Lane Change Path Planning Based on the NSGA-II and TOPSIS Algorithms

Among so many autonomous driving technologies, autonomous lane changing is an important application scenario, which has been gaining increasing amounts of attention from both industry and academic communities because it can effectively reduce traffic congestion and improve road safety. However, most of the existing researchers transform the multi-objective optimization problem of lane changing trajectory into a single objective problem, but how to determine the weight of the objective function is relatively fuzzy. Therefore, an optimization method based on the combination of the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), which provides a new idea for solving the multi-objective optimization problem of lane change trajectory algorithm, is proposed in this paper. Firstly, considering the constraints of lane changing and combining with the collision detection algorithm, the feasible lane changing trajectory cluster is obtained based on the quintic polynomial. In order to ensure the comfort, stability and high efficiency of the lane changing process, the NSGA-II Algorithm is used to optimize the longitudinal displacement and time of lane changing. The continuous ordered weighted averaging (COWA) operator is introduced to calculate the weights of three objective optimization functions. Finally, the TOPSIS Algorithm is applied to obtain the optimal lane change trajectory. The simulations are conducted, and the results demonstrate that the proposed method can generate a satisfactory trajectory for automatic lane changing actions.

Lane-Changing Strategy Based on a Novel Sliding Mode Control Approach for Connected Automated Vehicles

Safe and efficient autonomous lane changing is a key step of connected automated vehicles (CAVs), which can greatly reduce the traffic accident rate and relieve the traffic pressure. Aiming at the requirements of the smoothness and efficiency of the lane-changing trajectory of CAVs, it is necessary to design the lane changing controller to integrate the sensing, decision-making, and control tasks in the driving process. Firstly, based on the vehicle dynamics model, this paper proposes a vehicle lane-changing control strategy based on NNTSMC method (neural network enhanced non-singular fast terminal sliding mode control). The designed lane-changing controller can well realize the designed path tracking, and both lateral position and yaw angle can well track the expected value. This method enables the vehicle to control the front wheel steering angle intelligently, and the lateral acceleration during steering changes in the small scope, which ensures the steering stability of the vehicle. In this study, an improved adaptive RBF neural network with bounded mapping is designed to estimate the upper bound of the total disturbance of the system, which effectively reduces the chattering phenomenon of the control force. The Lyapunov function constructed in this study proves that the designed controller can ensure the stability of the controlled system. Finally, a comparative experiment is performed by the MATLAB/Simulink-CarSim co-simulation. Compared with SMC and TSMC (non-singular fast terminal sliding mode control), the proposed method has a performance improvement of at least 58.0% and 34.1%, respectively. The effectiveness and superiority of the proposed control method were confirmed by the experiments on the co-simulation platform.

Cooperation-Based Risk Assessment Prediction for Rear-End Collision Avoidance in Autonomous Lane Change Maneuvers

In this study, we present an innovative approach to risk assessment for rear-end collision avoidance using a cooperation concept for an autonomous lane change system. A Kalman filter is designed to estimate the longitudinal acceleration and predict the relative longitudinal position, velocity, and acceleration. Risk assessment is performed using the predicted motion of the object vehicle in the target lane. The cooperation concept is proposed to improve the flexibility of the lane change. If the risk assessment for the lane change indicates collision risk, the cooperativeness of the driver of the object vehicle is determined. If the driver of the object vehicle is regarded as a cooperative driver, within the original lane, the ego vehicle moves toward the target lane in preparation for the lane change. Subsequently, as soon as the risk assessment indicates that there is no collision risk, the lane change is performed. Thus, unlike conventional methods, the autonomous lane change using the proposed risk assessment can be initiated. Furthermore, the proposed risk assessment using cooperation concept is more flexible compared with previous methods for autonomous lane change in cluttered traffic.

Autonomous self-driving vehicles - Design of professional laboratory exercises in the field of automotive mechatronics

Self-driving cars are gradually making their way into road traffic and represent the main component of the new form of mobility. Major companies such as Tesla, Google, and Uber are researching the continuous improvement of self-driving vehicles and their reliability. Therefore, it is of great interest for trained professionals to deal with and understand the principles and requirements for autonomous driving. This paper aims to describe the new concept of a Bachelor / Master level university course for automotive technology students to address new mobility and self-driving cars. For the practice-oriented course, hardware in a low budget range (US $80) was used, which nevertheless has all the necessary sensors and requirements for a comprehensive practical introduction to the topic of self-driving automotive technology. The modular structure of the course contains lectures and exercises on the following topics: The first Exercise deals with the construction and modification of the Car-Kit, followed by the setup of the used Raspberry Pi. Since the car kit and Raspberry Pi are ready to use, the third exercise will steer the car remotely. The autonomous lane lectures and exercises follow this navigation with color spaces and masking, the Canny edge detection, Hough transform, steering, and stabilization.

Robust tube-based LPV-MPC for autonomous lane keeping

This paper proposes a control architecture for autonomous lane keeping by a vehicle. In this paper, the vehicle dynamics consist of two parts: lateral and longitudinal dynamics. Therefore, the control architecture comprises two subsequent controllers. A longitudinal model predictive control (MPC) makes the vehicle track the desired longitudinal speeds that are assumed to be generated by a speed planner. The longitudinal speeds are then passed to a lateral MPC for lane keeping. Due to the dependence of the lateral dynamics on the longitudinal speed, they are represented in a linear parameter-varying (LPV) form, where its scheduling parameter is the longitudinal speed of the vehicle. In order to deal with the imprecise information of the future longitudinal speed (the scheduling parameter), a bound of uncertainty is considered around the nominal trajectory of the future longitudinal velocities. Then, a tube-based LPV-MPC is adopted to control the lateral dynamics for attaining the lane keeping goal. In the end, the effectiveness of the proposed methods is illustrated by carrying out simulation tests.

Manoeuvring speed estimation of a lane-change system using geometric hermite interpolation

Autonomous vehicles demand a continuous path to provide the passengers with physical ease and relaxation. Smooth experience in autonomous vehicles is very essential and can be accomplished by having good trajectories. The trajectory generated by the interpolation algorithm for Geometric Hermite is provided in this paper. The proposed algorithm calculates a path based on a set of geometric Hermite data that consists of predefined points including prescribed tangent angles and curvature values. The generated path has the potential to determine the maximum speed allowed for safe autonomous driving on roads by providing curvature information. It describes an alternative way to estimate design speed permitted on the road for autonomous lane change systems.

Decoupled Longitudinal and Lateral Vehicle Control Based Autonomous Lane Change System Adaptable to Driving Surroundings

The purpose of this study is to develop an autonomous lane change control system that adapts to variable surrounding conditions, to ensure vehicle safety and traffic flow stability. In this paper, we propose decision-making and control procedures for realizing autonomous lane changing; to this end, we consider not only behaviors for changing lanes but also those involved in approaching the lane changing state, with a focus on the controller design. A decoupled control structure and longitudinal trajectory-free control approach are suggested. We design a novel inter-vehicle spacing policy and a 3DOF lateral error vehicle dynamics model. To verify the effectiveness of our system, simulation experiments are performed for 12 scenarios, and system assessments are conducted based on four evaluation perspectives. The results confirm that our system can safely control the vehicle amidst various surrounding vehicle conditions and can also ensure vehicle motion stability. Furthermore, we solve the existing dynamic instability problem of lateral control, which arises through longitudinal acceleration variability. Another significant advantage of this model is that the controlled vehicle does not interfere with the target-lane traffic flow and smoothly synchronizes with the flow during lane changing.

A Vehicle-Independent Autonomous Lane Keeping and Path Tracking System

This paper describes a lateral controller for path following developed to work on a wide range of vehicles without any changes in tuning between platforms. This vehicle independent path following controller employs a cascaded adaptive architecture, with the outer loop controlling the path dynamics and the inner loop controlling the vehicle dynamics. The controller is validated on four vehicle models in simulation at a variety of speeds. The controller is then implemented and validated in real-time on a Lincoln MKZ, a Class-8 Peterbilt 579 cab, a Peterbilt 579 with a loaded trailer, and a 1/10 th scale RC car. The controller is shown to perform well on the four simulated vehicles and the four experimental platforms at a range of longitudinal speeds, matching or exceeding human performance with consistent and smooth steering.