Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Special Issues
Artificial Intelligence Based Autonomous Vehicles
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Artificial Intelligence Based Autonomous Vehicles

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Vehicular Sensing".

Deadline for manuscript submissions: closed (15 August 2023) | Viewed by 42755

Special Issue Editors

Prof. Dr. Mustafa Ilhan Akbas

E-Mail Website
Guest Editor
Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, Daytona Beach, FL 32114, USA
Interests: computer engineering; cyber–physical systems; software defined networks
Special Issues, Collections and Topics in MDPI journals
Dr. Jun Chen

E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering, Oakland University, Rochester, MI 48309, USA
Interests: model predictive control; reinforcement learning; connected and automated vehicles; electric vehicles; renewable energy systems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Autonomous vehicle technologies have the potential to fundamentally transform various industries. These industries include not only automotive, transportation, or aerial vehicles but also a diverse set of sectors such as energy, farming, and smart cities. Artificial intelligence (AI) is at the core of autonomous vehicles, particularly in decision making, and there has been a significant investment in AI platforms both from academia and industry.

The aim of this Special Issue will be to feature articles on AI-based autonomous vehicles and how they will impact technology and society in the future. Articles might span across connected and autonomous vehicle applications, unmanned aerial vehicle applications, sensor and control technologies for autonomous systems, vehicular technologies enabling AI-based applications, assurance and safety mechanisms, and infrastructure-level technologies to support autonomous systems.

Within the above dimensions, the scope of the Special Issue welcomes high-quality original research and review articles that cover a broad range of topics related to AI and autonomous vehicles. Potential topics include but are not limited to the following:

  • Deep learning for autonomous vehicles;
  • AI-based autonomous vehicle applications in urban air mobility;
  • Safety assurance of autonomous vehicles;
  • Protocol design for autonomous systems;
  • Edge computing for autonomous vehicles;
  • Validation and verification of autonomous systems;
  • Localization, navigation, and tracking;
  • Crowdsensing for autonomous vehicle applications;
  • Reinforcement learning for autonomous vehicle training and testing;
  • Vehicular networks with autonomous systems;
  • Security for autonomous vehicles;
  • Control system design in autonomous vehicles;
  • Autonomous vehicle and human interaction;
  • Advanced driver assistance systems (ADAS);
  • Advanced sensor systems for autonomous vehicles;
  • AI-based autonomous vehicle hardware solutions.

Dr. Mustafa Akbas
Dr. Jun Chen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Autonomous vehicles
  • Artificial intelligence
  • Connected vehicles
  • Advanced driver assistance systems
  • Unmanned aerial vehicles
  • Machine learning
  • Human–AV interaction
  • Edge computing
  • Cloud-based AV control

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (16 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

22 pages, 13326 KiB  
Article
Self-Supervised Steering and Path Labeling for Autonomous Driving
by Andrei Mihalea, Robert-Florian Samoilescu and Adina Magda Florea
Sensors 2023, 23(20), 8473; https://doi.org/10.3390/s23208473 - 15 Oct 2023
Cited by 1 | Viewed by 1354
Abstract
Autonomous driving is a complex task that requires high-level hierarchical reasoning. Various solutions based on hand-crafted rules, multi-modal systems, or end-to-end learning have been proposed over time but are not quite ready to deliver the accuracy and safety necessary for real-world urban autonomous [...] Read more.
Autonomous driving is a complex task that requires high-level hierarchical reasoning. Various solutions based on hand-crafted rules, multi-modal systems, or end-to-end learning have been proposed over time but are not quite ready to deliver the accuracy and safety necessary for real-world urban autonomous driving. Those methods require expensive hardware for data collection or environmental perception and are sensitive to distribution shifts, making large-scale adoption impractical. We present an approach that solely uses monocular camera inputs to generate valuable data without any supervision. Our main contributions involve a mechanism that can provide steering data annotations starting from unlabeled data alongside a different pipeline that generates path labels in a completely self-supervised manner. Thus, our method represents a natural step towards leveraging the large amounts of available online data ensuring the complexity and the diversity required to learn a robust autonomous driving policy. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

21 pages, 13110 KiB  
Article
GPU Rasterization-Based 3D LiDAR Simulation for Deep Learning
by Leon Denis, Remco Royen, Quentin Bolsée, Nicolas Vercheval, Aleksandra Pižurica and Adrian Munteanu
Sensors 2023, 23(19), 8130; https://doi.org/10.3390/s23198130 - 28 Sep 2023
Cited by 1 | Viewed by 2323
Abstract
High-quality data are of utmost importance for any deep-learning application. However, acquiring such data and their annotation is challenging. This paper presents a GPU-accelerated simulator that enables the generation of high-quality, perfectly labelled data for any Time-of-Flight sensor, including LiDAR. Our approach optimally [...] Read more.
High-quality data are of utmost importance for any deep-learning application. However, acquiring such data and their annotation is challenging. This paper presents a GPU-accelerated simulator that enables the generation of high-quality, perfectly labelled data for any Time-of-Flight sensor, including LiDAR. Our approach optimally exploits the 3D graphics pipeline of the GPU, significantly decreasing data generation time while preserving compatibility with all real-time rendering engines. The presented algorithms are generic and allow users to perfectly mimic the unique sampling pattern of any such sensor. To validate our simulator, two neural networks are trained for denoising and semantic segmentation. To bridge the gap between reality and simulation, a novel loss function is introduced that requires only a small set of partially annotated real data. It enables the learning of classes for which no labels are provided in the real data, hence dramatically reducing annotation efforts. With this work, we hope to provide means for alleviating the data acquisition problem that is pertinent to deep-learning applications. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

20 pages, 3977 KiB  
Article
Model-Based Predictive Control and Reinforcement Learning for Planning Vehicle-Parking Trajectories for Vertical Parking Spaces
by Junren Shi, Kexin Li, Changhao Piao, Jun Gao and Lizhi Chen
Sensors 2023, 23(16), 7124; https://doi.org/10.3390/s23167124 - 11 Aug 2023
Cited by 8 | Viewed by 2467
Abstract
This paper proposes a vehicle-parking trajectory planning method that addresses the issues of a long trajectory planning time and difficult training convergence during automatic parking. The process involves two stages: finding a parking space and parking planning. The first stage uses model predictive [...] Read more.
This paper proposes a vehicle-parking trajectory planning method that addresses the issues of a long trajectory planning time and difficult training convergence during automatic parking. The process involves two stages: finding a parking space and parking planning. The first stage uses model predictive control (MPC) for trajectory tracking from the initial position of the vehicle to the starting point of the parking operation. The second stage employs the proximal policy optimization (PPO) algorithm to transform the parking behavior into a reinforcement learning process. A four-dimensional reward function is set to evaluate the strategy based on a formal reward, guiding the adjustment of neural network parameters and reducing the exploration of invalid actions. Finally, a simulation environment is built for the parking scene, and a network framework is designed. The proposed method is compared with the deep deterministic policy gradient and double-delay deep deterministic policy gradient algorithms in the same scene. Results confirm that the MPC controller accurately performs trajectory-tracking control with minimal steering wheel angle changes and smooth, continuous movement. The PPO-based reinforcement learning method achieves shorter learning times, totaling only 30% and 37.5% of the deep deterministic policy gradient (DDPG) and twin-delayed deep deterministic policy gradient (TD3), and the number of iterations to reach convergence for the PPO algorithm with the introduction of the four-dimensional evaluation metrics is 75% and 68% shorter compared to the DDPG and TD3 algorithms, respectively. This study demonstrates the effectiveness of the proposed method in addressing a slow convergence and long training times in parking trajectory planning, improving parking timeliness. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

24 pages, 5637 KiB  
Article
A Generalized Hamilton Robust Control Scheme of Trajectory Tracking for Intelligent Vehicles
by Yu Zhang, Wenhui Pei, Qi Zhang and Baosen Ma
Sensors 2023, 23(15), 6975; https://doi.org/10.3390/s23156975 - 5 Aug 2023
Viewed by 1297
Abstract
To ensure the accuracy and stability of intelligent-vehicle-trajectory tracking, a robust trajectory-tracking control strategy based on generalized Hamilton theory is proposed. Firstly, a dynamic Hamilton dissipative controller (DHDC) and trajectory-tracking Hamilton dissipative controller (TTHDC) were designed based on the established vehicle-dynamics control system [...] Read more.
To ensure the accuracy and stability of intelligent-vehicle-trajectory tracking, a robust trajectory-tracking control strategy based on generalized Hamilton theory is proposed. Firstly, a dynamic Hamilton dissipative controller (DHDC) and trajectory-tracking Hamilton dissipative controller (TTHDC) were designed based on the established vehicle-dynamics control system and trajectory-tracking control system using the orthogonal decomposition method and control-switching method. Next, the feedback-dissipative Hamilton realizations of the two systems were obtained separately to ensure the convergence of the system. Secondly, based on the dissipative Hamilton system designed by TTHDC, a generalized Hamilton robust controller (GHRC) was designed. Finally, the co-simulation of Carsim and MATLAB/Simulink was used to verify the effectiveness of the three control algorithms. The simulation results show that DHDC and TTHDC can achieve self-stabilizing control of vehicles and enable certain control effects for the trajectory tracking of vehicles. The GHRC solves the problems of low tracking accuracy and poor stability of DHDC and TTHDC. Compared with the sliding mode controller (SMC) and linear quadratic regulator (LQR) controller, the GHRC can reduce the lateral error by 84.44% and the root mean square error (RMSE) by 83.92%, which effectively improves the accuracy and robustness of vehicle-trajectory tracking. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

22 pages, 899 KiB  
Article
Performance Improvement during Attitude Motion of a Vehicle Using Aerodynamic-Surface-Based Anti-Jerk Predictive Controller
by Ejaz Ahmad and Iljoong Youn
Sensors 2023, 23(12), 5714; https://doi.org/10.3390/s23125714 - 19 Jun 2023
Cited by 2 | Viewed by 1741
Abstract
This study presents the effectiveness of an anti-jerk predictive controller (AJPC) based on active aerodynamic surfaces to handle upcoming road maneuvers and enhance vehicle ride quality by mitigating external jerks operating on the body of the vehicle. In order to eliminate body jerk [...] Read more.
This study presents the effectiveness of an anti-jerk predictive controller (AJPC) based on active aerodynamic surfaces to handle upcoming road maneuvers and enhance vehicle ride quality by mitigating external jerks operating on the body of the vehicle. In order to eliminate body jerk and improve ride comfort and road holding during turning, accelerating, or braking, the proposed control approach assists the vehicle in tracking the desired attitude position and achieving a realistic operation of the active aerodynamic surface. Vehicle speed and upcoming road data are used to calculate the desired attitude (roll or pitch) angles. The simulation results are performed for AJPC and predictive control strategies without jerk using MATLAB. The simulation results and comparison based on root-mean-square (rms) values show that compared to the predictive control strategy without jerk, the proposed control strategy significantly reduces the effects of vehicle body jerks transmitted to the passengers, improving ride comfort without degrading vehicle handling at the cost of slow desired angle tracking. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

24 pages, 8097 KiB  
Article
Intelligent Vehicle Path Tracking Control Method Based on Curvature Optimisation
by Qing Ye, Chaojun Gao, Yao Zhang, Zeyu Sun, Ruochen Wang and Long Chen
Sensors 2023, 23(10), 4719; https://doi.org/10.3390/s23104719 - 12 May 2023
Cited by 3 | Viewed by 1692
Abstract
In this study, an intelligent vehicle (IV) path tracking control method based on curvature optimisation is proposed to reduce the comprehensive performance conflict of the system. This system conflict is caused by the mutual restriction between the path tracking accuracy and the body [...] Read more.
In this study, an intelligent vehicle (IV) path tracking control method based on curvature optimisation is proposed to reduce the comprehensive performance conflict of the system. This system conflict is caused by the mutual restriction between the path tracking accuracy and the body stability during the movement of the intelligent automobile. First, the working principle of the new IV path tracking control algorithm is briefly introduced. Then, a three-degrees-of-freedom vehicle dynamics model and a preview error model considering vehicle roll are established. In addition, a path tracking control method based on curvature optimisation is designed to solve the deterioration of vehicle stability even when the path tracking accuracy of the IV is improved. Finally, the effectiveness of the IV path tracking control system is validated through simulations and the Hardware in the Loop (HIL) test with various conditions forms. Results clearly show that the optimisation amplitude of the IV lateral deviation is up to 84.10%, and the stability is improved by approximately 2% under the vx = 10 m/s and ρ = 0.15 m−1 condition; the optimisation amplitude of the lateral deviation is up to 66.80%, and the stability is improved by approximately 4% under the vx = 10 m/s and ρ = 0.2 m−1 condition; the body stability is improved by 20–30% under the vx = 15 m/s and ρ = 0.15 m−1 condition, and the boundary conditions of body stability are triggered. The curvature optimisation controller can effectively improve the tracking accuracy of the fuzzy sliding mode controller. The body stability constraint can also ensure the smooth running of the vehicle in the optimisation process. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

17 pages, 7502 KiB  
Article
Investigating the Path Tracking Algorithm Based on BP Neural Network
by Lu Liu, Mengyuan Xue, Nan Guo, Zilong Wang, Yuwei Wang and Qixing Tang
Sensors 2023, 23(9), 4533; https://doi.org/10.3390/s23094533 - 6 May 2023
Cited by 1 | Viewed by 1957
Abstract
In this paper, we propose an adaptive path tracking algorithm based on the BP (back propagation) neural network to increase the performance of vehicle path tracking in different paths. Specifically, based on the kinematic model of the vehicle, the front wheel steering angle [...] Read more.
In this paper, we propose an adaptive path tracking algorithm based on the BP (back propagation) neural network to increase the performance of vehicle path tracking in different paths. Specifically, based on the kinematic model of the vehicle, the front wheel steering angle of the vehicle was derived with the PP (Pure Pursuit) algorithm, and related parameters affecting path tracking accuracy were analyzed. In the next step, BP neural networks were introduced and vehicle speed, radius of path curvature, and lateral error were used as inputs to train models. The output of the model was used as the control coefficient of the PP algorithm to improve the accuracy of the calculation of the front wheel steering angle, which is referred to as the BP–PP algorithm in this paper. As a final step, simulation experiments and real vehicle experiments are performed to verify the algorithm’s performance. Simulation experiments show that compared with the traditional path tracking algorithm, the average tracking error of BP–PP algorithm is reduced by 0.025 m when traveling at a speed of 3 m/s on a straight path, and the average tracking error is reduced by 0.27 m, 0.42 m, and 0.67 m, respectively, at a speed of 1.5 m/s with a curvature radius of 6.8 m, 5.5 m, and 4.5 m, respectively. In the real vehicle experiment, an electric patrol vehicle with an autonomous tracking function was used as the experimental platform. The average tracking error was reduced by 0.1 m and 0.086 m on a rectangular road and a large curvature road, respectively. Experimental results show that the proposed algorithm performs well in both simulation and actual scenarios, improves the accuracy of path tracking, and enhances the robustness of the system. Moreover, facing paths with changes in road curvature, the BP–PP algorithm achieved significant improvement and demonstrated great robustness. In conclusion, the proposed BP–PP algorithm reduced the interference of nonlinear factors on the system and did not require complex calculations. Furthermore, the proposed algorithm has been applied to the autonomous driving patrol vehicle in the park and achieved good results. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

15 pages, 2720 KiB  
Article
Reinforcement Learning-Based Approach for Minimizing Energy Loss of Driving Platoon Decisions
by Zhiru Gu, Zhongwei Liu, Qi Wang, Qiyun Mao, Zhikang Shuai and Ziji Ma
Sensors 2023, 23(8), 4176; https://doi.org/10.3390/s23084176 - 21 Apr 2023
Cited by 4 | Viewed by 2262
Abstract
Reinforcement learning (RL) methods for energy saving and greening have recently appeared in the field of autonomous driving. In inter-vehicle communication (IVC), a feasible and increasingly popular research direction of RL is to obtain the optimal action decision of agents in a special [...] Read more.
Reinforcement learning (RL) methods for energy saving and greening have recently appeared in the field of autonomous driving. In inter-vehicle communication (IVC), a feasible and increasingly popular research direction of RL is to obtain the optimal action decision of agents in a special environment. This paper presents the application of reinforcement learning in the vehicle communication simulation framework (Veins). In this research, we explore the application of reinforcement learning algorithms in a green cooperative adaptive cruise control (CACC) platoon. Our aim is to train member vehicles to react appropriately in the event of a severe collision involving the leading vehicle. We seek to reduce collision damage and optimize energy consumption by encouraging behavior that conforms to the platoon’s environmentally friendly aim. Our study provides insight into the potential benefits of using reinforcement learning algorithms to improve the safety and efficiency of CACC platoons while promoting sustainable transportation. The policy gradient algorithm used in this paper has good convergence in the calculation of the minimum energy consumption problem and the optimal solution of vehicle behavior. In terms of energy consumption metrics, the policy gradient algorithm is used first in the IVC field for training the proposed platoon problem. It is a feasible training decision-planning algorithm for solving the minimization of energy consumption caused by decision making in platoon avoidance behavior. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

19 pages, 1279 KiB  
Article
Hierarchical Trajectory Planning for Narrow-Space Automated Parking with Deep Reinforcement Learning: A Federated Learning Scheme
by Zheng Yuan, Zhe Wang, Xinhang Li, Lei Li and Lin Zhang
Sensors 2023, 23(8), 4087; https://doi.org/10.3390/s23084087 - 18 Apr 2023
Cited by 10 | Viewed by 3617
Abstract
Collision-free trajectory planning in narrow spaces has become one of the most challenging tasks in automated parking scenarios. Previous optimization-based approaches can generate accurate parking trajectories, but these methods cannot compute feasible solutions with extremely complex constraints in a limited time. Recent research [...] Read more.
Collision-free trajectory planning in narrow spaces has become one of the most challenging tasks in automated parking scenarios. Previous optimization-based approaches can generate accurate parking trajectories, but these methods cannot compute feasible solutions with extremely complex constraints in a limited time. Recent research uses neural-network-based approaches that can generate time-optimized parking trajectories in linear time. However, the generalization of these neural network models in different parking scenarios has not been considered thoroughly and the risk of privacy compromise exists in the case of centralized training. To address the above issues, this paper proposes a hierarchical trajectory planning method with deep reinforcement learning in the federated learning scheme (HALOES) to rapidly and accurately generate collision-free automated parking trajectories in multiple narrow spaces. HALOES is a federated learning based hierarchical trajectory planning method to fully exert high-level deep reinforcement learning and the low-level optimization-based approach. HALOES further fuse the deep reinforcement learning model parameters to improve the generalization capabilities with a decentralized training scheme. The federated learning scheme in HALOES aims to protect the privacy of the vehicle’s data during model parameter aggregation. Simulation results show that the proposed method can achieve efficient automatic parking in multiple narrow spaces, improve planning time from 12.15% to 66.02% compared to other state-of-the-art methods (e.g., hybrid A*, OBCA) and maintain the same level of trajectory accuracy while having great model generalization. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

17 pages, 4327 KiB  
Article
CF-YOLOX: An Autonomous Driving Detection Model for Multi-Scale Object Detection
by Shuiye Wu, Yunbing Yan and Weiqiang Wang
Sensors 2023, 23(8), 3794; https://doi.org/10.3390/s23083794 - 7 Apr 2023
Cited by 11 | Viewed by 2953
Abstract
In self-driving cars, object detection algorithms are becoming increasingly important, and the accurate and fast recognition of objects is critical to realize autonomous driving. The existing detection algorithms are not ideal for the detection of small objects. This paper proposes a YOLOX-based network [...] Read more.
In self-driving cars, object detection algorithms are becoming increasingly important, and the accurate and fast recognition of objects is critical to realize autonomous driving. The existing detection algorithms are not ideal for the detection of small objects. This paper proposes a YOLOX-based network model for multi-scale object detection tasks in complex scenes. This method adds a CBAM-G module to the backbone of the original network, which performs grouping operations on CBAM. It changes the height and width of the convolution kernel of the spatial attention module to 7 × 1 to improve the ability of the model to extract prominent features. We proposed an object-contextual feature fusion module, which can provide more semantic information and improve the perception of multi-scale objects. Finally, we considered the problem of fewer samples and less loss of small objects and introduced a scaling factor that could increase the loss of small objects to improve the detection ability of small objects. We validated the effectiveness of the proposed method on the KITTI dataset, and the mAP value was 2.46% higher than the original model. Experimental comparisons showed that our model achieved superior detection performance compared to other models. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

17 pages, 1607 KiB  
Article
Highly Robust Adaptive Sliding Mode Trajectory Tracking Control of Autonomous Vehicles
by Fengxi Xie, Guozhen Liang and Ying-Ren Chien
Sensors 2023, 23(7), 3454; https://doi.org/10.3390/s23073454 - 25 Mar 2023
Cited by 13 | Viewed by 2238
Abstract
Autonomous driving technology has not yet been widely adopted, in part due to the challenge of achieving high-accuracy trajectory tracking in complex and hazardous driving scenarios. To this end, we proposed an adaptive sliding mode controller optimized by an improved particle swarm optimization [...] Read more.
Autonomous driving technology has not yet been widely adopted, in part due to the challenge of achieving high-accuracy trajectory tracking in complex and hazardous driving scenarios. To this end, we proposed an adaptive sliding mode controller optimized by an improved particle swarm optimization (PSO) algorithm. Based on the improved PSO, we also proposed an enhanced grey wolf optimization (GWO) algorithm to optimize the controller. Taking the expected trajectory and vehicle speed as inputs, the proposed control scheme calculates the tracking error based on an expanded vector field guidance law and obtains the control values, including the vehicle’s orientation angle and velocity on the basis of sliding mode control (SMC). To improve PSO, we proposed a three-stage update function for the inertial weight and a dynamic update law for the learning rates to avoid the local optimum dilemma. For the improvement in GWO, we were inspired by PSO and added speed and memory mechanisms to the GWO algorithm. Using the improved optimization algorithm, the control performance was successfully optimized. Moreover, Lyapunov’s approach is adopted to prove the stability of the proposed control schemes. Finally, the simulation shows that the proposed control scheme is able to provide more precise response, faster convergence, and better robustness in comparison with the other widely used controllers. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

23 pages, 2457 KiB  
Article
Comparative Study of Cooperative Platoon Merging Control Based on Reinforcement Learning
by Ali Irshayyid and Jun Chen
Sensors 2023, 23(2), 990; https://doi.org/10.3390/s23020990 - 15 Jan 2023
Cited by 8 | Viewed by 2874
Abstract
The time that a vehicle merges in a lane reduction can significantly affect passengers’ safety, comfort, and energy consumption, which can, in turn, affect the global adoption of autonomous electric vehicles. In this regard, this paper analyzes how connected and automated vehicles should [...] Read more.
The time that a vehicle merges in a lane reduction can significantly affect passengers’ safety, comfort, and energy consumption, which can, in turn, affect the global adoption of autonomous electric vehicles. In this regard, this paper analyzes how connected and automated vehicles should cooperatively drive to reduce energy consumption and improve traffic flow. Specifically, a model-free deep reinforcement learning approach is used to find the optimal driving behavior in the scenario in which two platoons are merging into one. Several metrics are analyzed, including the time of the merge, energy consumption, and jerk, etc. Numerical simulation results show that the proposed framework can reduce the energy consumed by up to 76.7%, and the average jerk can be decreased by up to 50%, all by only changing the cooperative merge behavior. The present findings are essential since reducing the jerk can decrease the longitudinal acceleration oscillations, enhance comfort and drivability, and improve the general acceptance of autonomous vehicle platooning as a new technology. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

30 pages, 6548 KiB  
Article
Research on the Physics–Intelligence Hybrid Theory Based Dynamic Scenario Library Generation for Automated Vehicles
by Yufei Zhang, Bohua Sun, Yaxin Li, Shuai Zhao, Xianglei Zhu, Wenxiao Ma, Fangwu Ma and Liang Wu
Sensors 2022, 22(21), 8391; https://doi.org/10.3390/s22218391 - 1 Nov 2022
Cited by 1 | Viewed by 1847
Abstract
The testing and evaluation system has been the key technology and security with its necessity in the development and deployment of maturing automated vehicles. In this research, the physics–intelligence hybrid theory-based dynamic scenario library generation method is proposed to improve system performance, in [...] Read more.
The testing and evaluation system has been the key technology and security with its necessity in the development and deployment of maturing automated vehicles. In this research, the physics–intelligence hybrid theory-based dynamic scenario library generation method is proposed to improve system performance, in particular, the testing efficiency and accuracy for automated vehicles. A general framework of the dynamic scenario library generation is established. Then, the parameterized scenario based on the dimension optimization method is specified to obtain the effective scenario element set. Long-tail functions for performance testing of specific ODD are constructed as optimization boundaries and critical scenario searching methods are proposed based on the node optimization and sample expansion methods for the low-dimensional scenario library generation and the reinforcement learning for the high-dimensional one, respectively. The scenario library generation method is evaluated with the naturalistic driving data (NDD) of the intelligent electric vehicle in the field test. Results show better efficient and accuracy performances compared with the ideal testing library and the NDD, respectively, in both low- and high-dimensional scenarios. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

13 pages, 12252 KiB  
Article
Improving Semantic Segmentation of Urban Scenes for Self-Driving Cars with Synthetic Images
by Maksims Ivanovs, Kaspars Ozols, Artis Dobrajs and Roberts Kadikis
Sensors 2022, 22(6), 2252; https://doi.org/10.3390/s22062252 - 14 Mar 2022
Cited by 21 | Viewed by 5664
Abstract
Semantic segmentation of an incoming visual stream from cameras is an essential part of the perception system of self-driving cars. State-of-the-art results in semantic segmentation have been achieved with deep neural networks (DNNs), yet training them requires large datasets, which are difficult and [...] Read more.
Semantic segmentation of an incoming visual stream from cameras is an essential part of the perception system of self-driving cars. State-of-the-art results in semantic segmentation have been achieved with deep neural networks (DNNs), yet training them requires large datasets, which are difficult and costly to acquire and time-consuming to label. A viable alternative to training DNNs solely on real-world datasets is to augment them with synthetic images, which can be easily modified and generated in large numbers. In the present study, we aim at improving the accuracy of semantic segmentation of urban scenes by augmenting the Cityscapes real-world dataset with synthetic images generated with the open-source driving simulator CARLA (Car Learning to Act). Augmentation with synthetic images with a low degree of photorealism from the MICC-SRI (Media Integration and Communication Center–Semantic Road Inpainting) dataset does not result in the improvement of the accuracy of semantic segmentation, yet both MobileNetV2 and Xception DNNs used in the present study demonstrate a better accuracy after training on the custom-made CCM (Cityscapes-CARLA Mixed) dataset, which contains both real-world Cityscapes images and high-resolution synthetic images generated with CARLA, than after training only on the real-world Cityscapes images. However, the accuracy of semantic segmentation does not improve proportionally to the amount of the synthetic data used for augmentation, which indicates that augmentation with a larger amount of synthetic data is not always better. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

16 pages, 8066 KiB  
Article
The Identification of Non-Driving Activities with Associated Implication on the Take-Over Process
by Lichao Yang, Mahdi Babayi Semiromi, Yang Xing, Chen Lv, James Brighton and Yifan Zhao
Sensors 2022, 22(1), 42; https://doi.org/10.3390/s22010042 - 22 Dec 2021
Cited by 5 | Viewed by 3103
Abstract
In conditionally automated driving, the engagement of non-driving activities (NDAs) can be regarded as the main factor that affects the driver’s take-over performance, the investigation of which is of great importance to the design of an intelligent human–machine interface for a safe and [...] Read more.
In conditionally automated driving, the engagement of non-driving activities (NDAs) can be regarded as the main factor that affects the driver’s take-over performance, the investigation of which is of great importance to the design of an intelligent human–machine interface for a safe and smooth control transition. This paper introduces a 3D convolutional neural network-based system to recognize six types of driver behaviour (four types of NDAs and two types of driving activities) through two video feeds based on head and hand movement. Based on the interaction of driver and object, the selected NDAs are divided into active mode and passive mode. The proposed recognition system achieves 85.87% accuracy for the classification of six activities. The impact of NDAs on the perspective of the driver’s situation awareness and take-over quality in terms of both activity type and interaction mode is further investigated. The results show that at a similar level of achieved maximum lateral error, the engagement of NDAs demands more time for drivers to accomplish the control transition, especially for the active mode NDAs engagement, which is more mentally demanding and reduces drivers’ sensitiveness to the driving situation change. Moreover, the haptic feedback torque from the steering wheel could help to reduce the time of the transition process, which can be regarded as a productive assistance system for the take-over process. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

38 pages, 3389 KiB  
Article
Intelligent Transport System Using Time Delay-Based Multipath Routing Protocol for Vehicular Ad Hoc Networks
by Yashar Ghaemi, Hosam El-Ocla, Nitin Ramesh Yadav, Manisha Reddy Madana, Dheeraj Kurugod Raju, Vignesh Dhanabal and Vishal Sheshadri
Sensors 2021, 21(22), 7706; https://doi.org/10.3390/s21227706 - 19 Nov 2021
Cited by 11 | Viewed by 2615
Abstract
During the last decade, the research on Intelligent Transportation System (ITS) has improved exponentially in real-life scenarios to provide optimized transport network performance. It is a matter of importance that alert messages are delivered promptly to prevent vehicular traffic problems. The fact is [...] Read more.
During the last decade, the research on Intelligent Transportation System (ITS) has improved exponentially in real-life scenarios to provide optimized transport network performance. It is a matter of importance that alert messages are delivered promptly to prevent vehicular traffic problems. The fact is an ITS system per se could be a part of a vehicular ad hoc network (VANET) which is an extension of a wireless network. In all sorts of wireless ad hoc networks, the network topology is subjected to change due to the mobility of network nodes; therefore, an existing explored route between two nodes could be demolished in a minor fraction of time. When it comes to the VANETs, the topology likely changes due to the high velocity of nodes. On the other hand, time is a crucial factor playing an important role in message handling between the network’s nodes. In this paper, we propose Time delay-based Multipath Routing (TMR) protocol that effectively identifies an optimized path for packet delivery to the destination vehicle with a minimal time delay. Our algorithm gives a higher priority to alert messages compared to normal messages. It also selects the routes with the short round-trip time (RTT) within the RTT threshold. As a result, our algorithm would realize two goals. Firstly, it would speed up the data transmission rate and deliver data packets, particularly warning messages, to the destination vehicle promptly and therefore avoid vehicular problems such as car accidents. Secondly, the TMR algorithm reduces the data traffic load, particularly of the normal messages, to alleviate the pressure on the network and therefore avoids network congestion and data collisions. This, in turn, lessens the packets’ retransmissions. To demonstrate the effectiveness of the proposed protocol, the TMR has been compared with the other protocols such as AOMDV, FF-AOMDV, EGSR, QMR, and ISR. Simulation results demonstrate that our proposed protocol proves its excellent performance compared to other protocols. Full article
(This article belongs to the Special Issue Artificial Intelligence Based Autonomous Vehicles)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-16
Back to TopTop