Algorithm For Autonomous Vehicles Research Articles

Research on a Personalized Decision Control Algorithm for Autonomous Vehicles Based on the Reinforcement Learning from Human Feedback Strategy

To address the shortcomings of previous autonomous decision models, which often overlook the personalized features of users, this paper proposes a personalized decision control algorithm for autonomous vehicles based on RLHF (reinforcement learning from human feedback). The algorithm combines two reinforcement learning approaches, DDPG (Deep Deterministic Policy Gradient) and PPO (proximal policy optimization), and divides the control scheme into three phases including pre-training, human evaluation, and parameter optimization. During the pre-training phase, an agent is trained using the DDPG algorithm. In the human evaluation phase, different trajectories generated by the DDPG-trained agent are scored by individuals with different styles, and the respective reward models are trained based on the trajectories. In the parameter optimization phase, the network parameters are updated using the PPO algorithm and the reward values given by the reward model to achieve personalized autonomous vehicle control. To validate the control algorithm designed in this paper, a simulation scenario was built using CARLA_0.9.13 software. The results demonstrate that the proposed algorithm can provide personalized decision control solutions for different styles of people, satisfying human needs while ensuring safety.

Modeling the Deployment and Management of Large-Scale Autonomous Vehicle Circulation in Mixed Road Traffic Conditions Considering Virtual Track Theory

This paper offers a novel view for managing and controlling the movement of driverless, i.e., autonomous, vehicles by converting this movement to a simulated train movement moving on a rail track. It expands on the “virtual track” theory and creates a model for virtual track autonomous vehicle management and control based on the ideas and methods of railway train operation. The developed model and adopted algorithm allow for large-scale autonomous driving vehicle control on the highway while considering the temporal-spatial distribution of vehicles, temporal-spatial trajectory diagram optimization, and the management and control model and algorithm for autonomous vehicles, as design goals. The ultimate objective is to increase the safety of the road traffic environment when autonomous vehicles are operating in it together with human-driven vehicles and achieve more integrated and precise organization and scheduling of these vehicles in such mixed traffic conditions. The developed model adopted a “particle swarm” optimization algorithm that is tested in a hypothetical network pending a full-scale test on a real highway. The paper concludes that the proposed management and control model and algorithm based on the “virtual track” theory is promising and demonstrates feasibility and effectiveness for further development and future application.

Impact of Autonomous Vehicles on Traffic Flow in Rural and Urban Areas Using a Traffic Flow Simulator

Autonomous vehicles have the potential to significantly improve modes of transportation, and many businesses and research facilities are developing such systems. Although there are studies on the social implementation of autonomous vehicles, these studies are based on limited conditions such as predetermined driving environments. Therefore, in this study, we target urban areas and rural areas, and we simulate a behavioral algorithm for autonomous vehicles being developed and owned by Kanazawa University. In this study, a traffic flow simulation system (Aimsun) was constructed to reproduce the current situation of traffic flow in the city during normal times, using data from a person-trip survey conducted by the local government. In addition, we varied the mixing rate of automated vehicles and evaluated its effect on the delay time between ODs. We assume the gradual replacement of existing vehicles by autonomous vehicles on actual road networks and for realistic traffic volumes, and we investigate their impact on traffic flow. We vary the mixing rate of autonomous vehicles into actual traffic environments, and we measure the delay in the origin-destination (OD) interval to evaluate the impact of autonomous vehicles on traffic flow. The results obtained show that as the mixing rate of autonomous vehicles increases, the delay between OD intervals increases. Then, once the mixing rate exceeds a certain value, the delay between OD intervals gradually decreased. The delay time for all vehicles slightly increases as the mixing rate of autonomous vehicles increased from 10 to 45%. When the mixing rate increased from 45 to 50%, the delay time for all vehicles decreased notably, and when the mixing rate was 50 to 100%, it remained constant. Analytical results showed that when socially implementing autonomous vehicles, their mixing rate impacts the traffic flow; thus, there is a need to determine appropriate distribution scenarios and areas for implementation.

YOLOv8-QSD: An Improved Small Object Detection Algorithm for Autonomous Vehicles Based on YOLOv8

YOLOv8-QSD: An Improved Small Object Detection Algorithm for Autonomous Vehicles Based on YOLOv8

The Dynamic Path Planning of Autonomous Vehicles on Icy and Snowy Roads Based on an Improved Artificial Potential Field

The crucial dynamic path planning of autonomous vehicles is achieved via obstacle avoidance path planning technology. The reduction of the tire adhesion coefficient on icy and snowy roads (ISRs) increases the difficulty of autonomous vehicles’ control. In this paper, the driving characteristics of vehicles on ISRs are established, and the artificial potential field function is introduced to avoid collision risk when planning a path. A dynamic path planning algorithm for autonomous vehicles based on the artificial potential field (APF) is established. The adjustment factor is added to the gravitational potential field, and a judgment coefficient is added to the repulsive potential field to improve the artificial potential field function, based on the low adhesion of vehicles on ISRs. Moreover, a path with a continuous curvature is generated to achieve the driving comfort and driving safety of the planned path via trajectory smoothing. By establishing the Carsim/Simulink co-simulation platform, the effectiveness of dynamic path planning for autonomous vehicles under different algorithms and different obstacle models is compared. The results show that the improved APF algorithm has an obvious effect on the smoothness of the path and the reduction of the curvature mutation and can generate a safe and efficient path on icy and snowy roads. The dynamic obstacle avoidance of the improved APF algorithm improves the pre-judgment accuracy of the collision risk assessment of autonomous vehicles and shows the superiority of the improved algorithm.

Fast Trajectory Tracking Control Algorithm for Autonomous Vehicles Based on the Alternating Direction Multiplier Method (ADMM) to the Receding Optimization of Model Predictive Control (MPC).

In order to improve the real-time performance of the trajectory tracking of autonomous vehicles, this paper applies the alternating direction multiplier method (ADMM) to the receding optimization of model predictive control (MPC), which improves the computational speed of the algorithm. Based on the vehicle dynamics model, the output equation of the autonomous vehicle trajectory tracking control system is constructed, and the auxiliary variable and the dual variable are introduced. The quadratic programming problem transformed from the MPC and the vehicle dynamics constraints are rewritten into the solution of the ADMM form, and a decreasing penalty factor is used during the solution process. The simulation verification is carried out through the joint simulation platform of Simulink and Carsim. The results show that, compared with the active set method (ASM) and the interior point method (IPM), the algorithm proposed in this paper can not only improve the accuracy of trajectory tracking, but also exhibits good real-time performance in different prediction time domains and control time domains. When the prediction time domain increases, the calculation time shows no significant difference. This verifies the effectiveness of the ADMM in improving the real-time performance of MPC.

Optimizing and Analyzing Performance of Motor Fault Diagnosis Algorithms for Autonomous Vehicles via Cross-Domain Data Fusion

Electric motors play a pivotal role in the functioning of autonomous vehicles, necessitating accurate fault diagnosis to ensure vehicle safety and reliability. In this paper, a novel motor fault diagnosis approach grounded in vibration signals to enhance fault detection performance is presented. The method involves capturing vibration signals from the motor across various operational states and frequencies using vibration sensors. Subsequently, the signals undergo transformation into frequency domain representations through fast Fourier transform. This includes normalizing and concatenating the amplitude frequency and phase frequency signals into comprehensive frequency domain information. Leveraging Gramian image-encoding attributes, cross-domain fusion of time-domain and frequency-domain data is achieved. Finally, the fused Gram angle field map is fed into the ConvMixer deep learning model, augmented by the ECA mechanism to facilitate precise motor fault identification. Experimental outcomes underscore the efficacy of cross-domain data fusion, showcasing improved pattern recognition and recognition rates for the models compared to traditional time-domain methods. Additionally, a comparative analysis of various deep learning models highlights the superior performance of the ECA-ConvMixer model. This study makes significant contributions by introducing a cross-domain data fusion method, merging time-domain and frequency-domain information to enhance motor vibration signal analysis. Additionally, the incorporation of the ECA-ConvMixer deep learning model, equipped with attention mechanisms, effectively captures critical features, thus serving as a robust tool for motor fault diagnosis. These innovations not only enhance diagnostic accuracy but also have broad applications in areas like autonomous vehicles and industry, leading to reduced maintenance expenses and enhanced equipment reliability.

Can We Replace Real-World With Synthetic Data in Deep Learning-Based ADAS Algorithm Development?

Deep learning models require vast amounts of annotated training data. Gathering and annotating the data from the real world is an expensive and time-consuming process. Thus, synthetically generated data is being researched more and more. This paper tries to answer the question of whether and to what extent synthetically generated data can help in developing the advanced driver-assistance system (ADAS) algorithms for autonomous vehicles, for the object detection task based on deep learning. Two state-of-the-art deep learning object detectors were trained on various combinations of real-world and synthetic data. A total of 12 detectors were tested on real-world test images. Results show that synthetic data can contribute to better detector performance until a certain ratio between real-world and synthetic data is reached.

Uncertainties in Onboard Algorithms for Autonomous Vehicles: Challenges, Mitigation, and Perspectives

Autonomous driving is considered one of the revolutionary technologies shaping humanity’s future mobility and quality of life. However, safety remains a critical hurdle in the way of commercialization and widespread deployment of autonomous vehicles on public roads. Safety concerns require the autonomous driving system to handle uncertainties from multiple sources that are either preexisting, e.g., the stochastic behavior of traffic participants or scenario occlusion, or introduced as a result of processing, e.g., the application of neural networks. Thus, it is crucial to analyze the sources of uncertainties and quantify the risks associated with them, including the propagated risks that accumulate in the decision-making system. In this context, this paper provides an overview of uncertainty challenges and state-of-the-art techniques for mitigating these challenges. We argue that the uncertainties mainly originate from two aspects: 1) the external traffic environment, and 2) the internal autonomous driving system. Specifically, this paper first analyzes the safety challenges caused by the uncertainties and summarizes their sources. In addition, the corresponding techniques that mitigate and quantify the risk of uncertainties are presented. Finally, research perspectives are highlighted to facilitate future studies for guaranteeing the safety of autonomous vehicles.

Neural Network Approach Super-Twisting Sliding Mode Control for Path-Tracking of Autonomous Vehicles

This paper proposes a neural network approach adaptive super-twisting sliding mode control algorithm for autonomous vehicles. An adaptive and robust control algorithm in autonomous vehicles is needed to compensate for disturbance and parametric uncertainty from the variable environment and vehicle conditions. The sliding mode control (SMC) is a robust controller that compensates for robust and reasonable control performance against disturbance and parametric uncertainty. However, the inherent limitation of the sliding mode control, namely the chattering phenomenon, has a negative effect on the system. Additionally, when the disturbance exceeds the defined boundaries, the control stability is compromised. To overcome these limitations, this study incorporates the radial basis function neural network (RBFNN) and Lyapunov function to estimate disturbance and parametric uncertainty. The estimated disturbance is reflected in the super-twisting sliding mode control (STSMC) to reduce the chattering phenomenon and achieve enhanced robust performance. The performance evaluation of the proposed neural network approach control algorithm is conducted using the double lane change (DLC) scenario and rapid path-tracking (RPT) scenario, implemented in the CarMaker and Matlab/Simulink environments, respectively.

Controllable Clothoid Path Generation for Autonomous Vehicles

This paper proposes a novel and simple smooth path generation algorithm for autonomous vehicles. The proposed method can rapidly generate feasible and curvature continuous paths connecting any two given states with null curvature. The generated path comprises straight lines, circular arcs and clothoid segments that are close to human driving behavior. Moreover, while keeping an accurate connection with the boundary states, the proposed method also allows fine-tuning the curve with the maximum curvature of the path and the midpoint's position, which makes it more flexible in avoiding obstacles while keeping feasibility. Various experiments show that the proposed method has extremely low time consumption and high robustness for different conditions. Meanwhile, it is more flexible than the recent research and the spline-based methods.

A real-time collision-free maneuver generation algorithm for autonomous driving

In this paper we propose a real-time maneuver generation algorithm for Autonomous Vehicles (AVs). Given a planar road geometry with static and moving obstacles along it, we are interested in finding collision-free maneuvers that satisfied the AV’s dynamics and subject to physical and comfort limits. Based on longitudinal and transverse coordinates, we propose a novel collision avoidance constraint and formulate a suitable maneuver regulation optimal control problem. Maneuver regulation has intrinsic robustness with respect to standard trajectory tracking that stems from the requirement of following a desired path with a desired velocity profile assigned on it. The optimization problem is solved by using a nonlinear optimal control technique that generates (local) optimal trajectories. We demonstrate the efficacy of the proposed algorithm by providing numerical computations on two different scenarios. Finally, experimental results are presented to demonstrate the efficiency of the proposed algorithm both in terms of computational effort and dynamic features captured.

TriPField: A 3D Potential Field Model and Its Applications to Local Path Planning of Autonomous Vehicles

Potential fields have been integrated with local path-planning algorithms for autonomous vehicles (AVs) to tackle challenging scenarios with dense and dynamic obstacles. Most existing potential fields are isotropic without considering the traffic agent’s geometric shape and could cause failures due to local minima. We propose a three-dimensional potential field (TriPField) model to overcome this drawback by integrating an ellipsoid potential field with a Gaussian velocity field (GVF). Specifically, we model the surrounding vehicles as ellipsoids in corresponding ellipsoidal coordinates, where the formulated Laplace equation is solved with boundary conditions. Meanwhile, we develop a nonparametric GVF to capture the multi-vehicle interactions and then plan the AV’s velocity profiles, reducing the path search space and improving computing efficiency. Finally, a local path-planning framework with our TriPField is developed by integrating model predictive control to consider the constraints of vehicle kinematics. Our proposed approach is verified in three typical scenarios, i.e., active lane change, on-ramp merging, and car following. Experimental results show that our TriPField-based planner obtains a shorter, smoother local path with a slight jerk during control, especially in the scenarios with dense traffic flow, compared with traditional potential field-based planners. Our proposed TriPField-based planner can perform emergent obstacle avoidance for AVs with a high success rate even when the surrounding vehicles behave abnormally.

An ethical trajectory planning algorithm for autonomous vehicles

With the rise of artificial intelligence and automation, moral decisions that were formerly the preserve of humans are being put into the hands of algorithms. In autonomous driving, a variety of such decisions with ethical implications are made by algorithms for behaviour and trajectory planning. Therefore, here we present an ethical trajectory planning algorithm with a framework that aims at a fair distribution of risk among road users. Our implementation incorporates a combination of five ethical principles: minimization of the overall risk, priority for the worst-off, equal treatment of people, responsibility and maximum acceptable risk. To the best of our knowledge, this is the first ethical algorithm for trajectory planning of autonomous vehicles in line with the 20 recommendations from the European Union Commission expert group and with general applicability to various traffic situations. We showcase the ethical behaviour of our algorithm in selected scenarios and provide an empirical analysis of the ethical principles in 2,000 scenarios. The code used in this research is available as open-source software.

Learning-Based Path Planning and Predictive Control for Autonomous Vehicles With Low-Cost Positioning

Navigation algorithms for autonomous vehicles have become the subject of increasing interest, but most of them heavily rely on expensive high-precision positioning equipment, which hinders autonomous vehicles development. In this paper, we propose a path planning and control framework for autonomous vehicles with low-cost positioning. For the path planning layer, a potential field is constructed by the potential functions of road boundaries, obstacles, and reference waypoints. According to the potential field, a reinforcement learning agent is developed to generate a collision-free path for path tracking. For the control layer, a model predictive control based on vehicle dynamics is designed and a linear terminal constraint is considered. Simulation results show that the proposed algorithm can effectively avoid static and dynamic obstacles. Moreover, compared with traditional methods, the proposed algorithm performs better when the positioning devices are imprecise. Furthermore, the real-time performance can meet the requirements of navigation.

HDM-RRT: A Fast HD-Map-Guided Motion Planning Algorithm for Autonomous Driving in the Campus Environment

On campus, the complexity of the environment and the lack of regulatory constraints make it difficult to model the environment, resulting in less efficient motion planning algorithms. To solve this problem, HD-Map-guided sampling-based motion planning is a feasible research direction. We proposed a motion planning algorithm for autonomous vehicles on campus, called HD-Map-guided rapidly-exploring random tree (HDM-RRT). In our algorithm, A collision risk map (CR-Map) that quantifies the collision risk coefficient on the road is combined with the Gaussian distribution for sampling to improve the efficiency of algorithm. Then, the node optimization strategy of the algorithm is deeply optimized through the prior information of the CR-Map to improve the convergence rate and solve the problem of poor stability in campus environments. Three experiments were designed to verify the efficiency and stability of our approach. The results show that the sampling efficiency of our algorithm is four times higher than that of the Gaussian distribution method. The average convergence rate of the proposed algorithm outperforms the RRT* algorithm and DT-RRT* algorithm. In terms of algorithm efficiency, the average computation time of the proposed algorithm is only 15.98 ms, which is much better than that of the three compared algorithms.

An Efficient Lidar-Based Algorithm for Autonomous Vehicle's Visual Detection

An Efficient Lidar-Based Algorithm for Autonomous Vehicle's Visual Detection

Development of a Sliding-Mode-Control-Based Path-Tracking Algorithm with Model-Free Adaptive Feedback Action for Autonomous Vehicles.

This paper presents a sliding mode control (SMC)-based path-tracking algorithm for autonomous vehicles by considering model-free adaptive feedback actions. In autonomous vehicles, safe path tracking requires adaptive and robust control algorithms because driving environment and vehicle conditions vary in real time. In this study, the SMC was adopted as a robust control method to adjust the switching gain, taking into account the sliding surface and unknown uncertainty to make the control error zero. The sliding surface can be designed mathematically, but it is difficult to express the unknown uncertainty mathematically. Information of priori bounded uncertainties is needed to obtain closed-loop stability of the control system, and the unknown uncertainty can vary with changes in internal and external factors. In the literature, ongoing efforts have been made to overcome the limitation of losing control stability due to unknown uncertainty. This study proposes an integrated method of adaptive feedback control (AFC) and SMC that can adjust a bounded uncertainty. Some illustrative and representative examples, such as autonomous driving scenarios, are also provided to show the main properties of the designed integrated controller. The examples show superior control performance, and it is expected that the integrated controller could be widely used for the path-tracking algorithms of autonomous vehicles.

Obstacle-Avoidance Path-Planning Algorithm for Autonomous Vehicles Based on B-Spline Algorithm

To solve the problem of the real-time path-planning of autonomous vehicles for obstacle avoidance on structured roads, a path-planning approach based on the B-spline algorithm is proposed in this paper. Firstly, the mechanism of driver path planning is analyzed, and a dynamic risk-identification model based on the support vector machine is proposed. It combines the driver’s risk perception characteristics and a risk model. Then, the B-spline algorithm model is improved based on the risk-identification model. Furthermore, road features, road constraints and dynamic constraints are considered to further optimize the planning algorithm. To verify the path-planning approach proposed in this paper, a co-simulation experiment based on CarSim/Simulink is conducted. Results show that the improved algorithm is effective in static and dynamic obstacles avoidance. The algorithm can generate collision-free obstacle avoidance paths, and the paths meet the real-time requirements and dynamic constraints of obstacle avoidance scenarios. In addition, the proposed algorithm optimizes the path according to the driver’s operating characteristics, which can further improve the safety and comfort of autonomous vehicles.

Formally Robust and Safe Trajectory Planning and Tracking for Autonomous Vehicles

In this paper, a safe trajectory planning and tracking algorithm for autonomous vehicles is proposed. Specially, the safety problem considers the geometric constraints including the obstacle avoiding and the road side constraints, and the non-convex input constraints defined from the sideslip angle of the wheels and input boundedness. Control barrier function (CBF) is adopted to deal with the state and input constraints and generate nominal trajectory. For this purpose, the nominal dynamics of the autonomous vehicle is defined as the virtual dynamics, from which the CBF safety certificates are derived. By constructing appropriate feedback control, the tracking error of the actual trajectory can be bounded into a tube, which guarantees the geometric safety of the actual vehicle. Two safety certificates, the bearing and the distance safety certificates are derived for multiple-obstacle avoidance. In order to deal with the non-convex input constraints, a safe braking maneuver is carefully considered. The feasible initial velocity set for safe braking is proposed as a part of state constraints. The feasibility and the safety of the overall system is proved. The algorithm to synthesis the CBF certificates for multiple-obstacle avoidance, and the input constraints is proposed. Simulation results from an autonomous vehicle including disturbances demonstrate the feasibility of the algorithm. The software implementation of the proposed algorithm was developed in C++ intended for real-world testing.