Sensors

Research

19 pages, 4061 KiB

Open AccessArticle

The Braking-Pressure and Driving-Direction Determination System (BDDS) Using Road Roughness and Passenger Conditions of Surrounding Vehicles

by YiNa Jeong, SuRak Son, ByungKwan Lee and SuHee Lee

Sensors 2022, 22(12), 4414; https://doi.org/10.3390/s22124414 - 10 Jun 2022

Cited by 3 | Viewed by 1548

Abstract

A fully autonomous vehicle must ensure not only fully autonomous driving but also the safety and comfort of its passengers. However, the self-driving technology that is currently completed focuses only on perfect driving and does not guarantee the safety and comfort of passengers. [...] Read more.

A fully autonomous vehicle must ensure not only fully autonomous driving but also the safety and comfort of its passengers. However, the self-driving technology that is currently completed focuses only on perfect driving and does not guarantee the safety and comfort of passengers. This paper proposes a braking-pressure and driving-direction determination system (BDDS), which computes the brake pressure and steering angle optimized for passenger safety by utilizing more diverse information than existing autonomous vehicles. The BDDS proposed in this paper consists of two modules. The road roughness classification module (RRCM) classifies the roughness of the road by using the pressure data applied to the suspension and the K-NN algorithm and computes the optimal brake pressure. The passenger recognition and sharing module (PRSM) identifies the current occupant status of the vehicle by using a body pressure sensor and CNN, shares the information with surrounding vehicles, and computes the optimal steering angle using passenger information and road information. As a result of the simulations described in this paper, the parameters of AI models were optimized. In addition, the RRCS was about 7% more accurate than the K-means clustering algorithm, and PRS was about 9% more accurate than the existing seat recognition system. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

20 pages, 7099 KiB

Open AccessArticle

Customizable FPGA-Based Hardware Accelerator for Standard Convolution Processes Empowered with Quantization Applied to LiDAR Data

by João Silva, Pedro Pereira, Rui Machado, Rafael Névoa, Pedro Melo-Pinto and Duarte Fernandes

Sensors 2022, 22(6), 2184; https://doi.org/10.3390/s22062184 - 11 Mar 2022

Cited by 6 | Viewed by 3328

Abstract

In recent years there has been an increase in the number of research and developments in deep learning solutions for object detection applied to driverless vehicles. This application benefited from the growing trend felt in innovative perception solutions, such as LiDAR sensors. Currently, [...] Read more.

In recent years there has been an increase in the number of research and developments in deep learning solutions for object detection applied to driverless vehicles. This application benefited from the growing trend felt in innovative perception solutions, such as LiDAR sensors. Currently, this is the preferred device to accomplish those tasks in autonomous vehicles. There is a broad variety of research works on models based on point clouds, standing out for being efficient and robust in their intended tasks, but they are also characterized by requiring point cloud processing times greater than the minimum required, given the risky nature of the application. This research work aims to provide a design and implementation of a hardware IP optimized for computing convolutions, rectified linear unit (ReLU), padding, and max pooling. This engine was designed to enable the configuration of features such as varying the size of the feature map, filter size, stride, number of inputs, number of filters, and the number of hardware resources required for a specific convolution. Performance results show that by resorting to parallelism and quantization approach, the proposed solution could reduce the amount of logical FPGA resources by 40 to 50%, enhancing the processing time by 50% while maintaining the deep learning operation accuracy. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

13 pages, 18473 KiB

Open AccessArticle

Evaluation of 3D Vulnerable Objects’ Detection Using a Multi-Sensors System for Autonomous Vehicles

by Esraa Khatab, Ahmed Onsy and Ahmed Abouelfarag

Sensors 2022, 22(4), 1663; https://doi.org/10.3390/s22041663 - 21 Feb 2022

Cited by 9 | Viewed by 3503

Abstract

One of the primary tasks undertaken by autonomous vehicles (AVs) is object detection, which comes ahead of object tracking, trajectory estimation, and collision avoidance. Vulnerable road objects (e.g., pedestrians, cyclists, etc.) pose a greater challenge to the reliability of object detection operations due [...] Read more.

One of the primary tasks undertaken by autonomous vehicles (AVs) is object detection, which comes ahead of object tracking, trajectory estimation, and collision avoidance. Vulnerable road objects (e.g., pedestrians, cyclists, etc.) pose a greater challenge to the reliability of object detection operations due to their continuously changing behavior. The majority of commercially available AVs, and research into them, depends on employing expensive sensors. However, this hinders the development of further research on the operations of AVs. In this paper, therefore, we focus on the use of a lower-cost single-beam LiDAR in addition to a monocular camera to achieve multiple 3D vulnerable object detection in real driving scenarios, all the while maintaining real-time performance. This research also addresses the problems faced during object detection, such as the complex interaction between objects where occlusion and truncation occur, and the dynamic changes in the perspective and scale of bounding boxes. The video-processing module works upon a deep-learning detector (YOLOv3), while the LiDAR measurements are pre-processed and grouped into clusters. The output of the proposed system is objects classification and localization by having bounding boxes accompanied by a third depth dimension acquired by the LiDAR. Real-time tests show that the system can efficiently detect the 3D location of vulnerable objects in real-time scenarios. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

20 pages, 8860 KiB

Open AccessEditor’s ChoiceArticle

Visualizing Street Pavement Anomalies through Fog Computing V2I Networks and Machine Learning

by Rogelio Bustamante-Bello, Alec García-Barba, Luis A. Arce-Saenz, Luis A. Curiel-Ramirez, Javier Izquierdo-Reyes and Ricardo A. Ramirez-Mendoza

Sensors 2022, 22(2), 456; https://doi.org/10.3390/s22020456 - 8 Jan 2022

Cited by 19 | Viewed by 2521

Abstract

Analyzing data related to the conditions of city streets and avenues could help to make better decisions about public spending on mobility. Generally, streets and avenues are fixed as soon as they have a citizen report or when a major incident occurs. However, [...] Read more.

Analyzing data related to the conditions of city streets and avenues could help to make better decisions about public spending on mobility. Generally, streets and avenues are fixed as soon as they have a citizen report or when a major incident occurs. However, it is uncommon for cities to have real-time reactive systems that detect the different problems they have to fix on the pavement. This work proposes a solution to detect anomalies in streets through state analysis using sensors within the vehicles that travel daily and connecting them to a fog-computing architecture on a V2I network. The system detects and classifies the main road problems or abnormal conditions in streets and avenues using Machine Learning Algorithms (MLA), comparing roughness against a flat reference. An instrumented vehicle obtained the reference through accelerometry sensors and then sent the data through a mid-range communication system. With these data, the system compared an Artificial Neural Network (supervised MLA) and a K-Nearest Neighbor (Supervised MLA) to select the best option to handle the acquired data. This system makes it desirable to visualize the streets’ quality and map the areas with the most significant anomalies. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

24 pages, 411 KiB

Open AccessFeature PaperArticle

SEE-TREND: SEcurE Traffic-Related EveNt Detection in Smart Communities

by Stephan Olariu and Dimitrie C. Popescu

Sensors 2021, 21(22), 7652; https://doi.org/10.3390/s21227652 - 18 Nov 2021

Cited by 4 | Viewed by 1597

Abstract

It has been widely recognized that one of the critical services provided by Smart Cities and Smart Communities is Smart Mobility. This paper lays the theoretical foundations of SEE-TREND, a system for Secure Early Traffic-Related EveNt Detection in Smart Cities and Smart Communities. [...] Read more.

It has been widely recognized that one of the critical services provided by Smart Cities and Smart Communities is Smart Mobility. This paper lays the theoretical foundations of SEE-TREND, a system for Secure Early Traffic-Related EveNt Detection in Smart Cities and Smart Communities. SEE-TREND promotes Smart Mobility by implementing an anonymous, probabilistic collection of traffic-related data from passing vehicles. The collected data are then aggregated and used by its inference engine to build beliefs about the state of the traffic, to detect traffic trends, and to disseminate relevant traffic-related information along the roadway to help the driving public make informed decisions about their travel plans, thereby preventing congestion altogether or mitigating its nefarious effects. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

22 pages, 1093 KiB

Open AccessArticle

Integration of Context Awareness in Smart Service Provision System Based on Wireless Sensor Networks for Sustainable Cargo Transportation

by Dalė Dzemydienė and Aurelija Burinskienė

Sensors 2021, 21(15), 5140; https://doi.org/10.3390/s21155140 - 29 Jul 2021

Cited by 9 | Viewed by 2151

Abstract

Smart service provision systems can assist in the management of cargo transportation. The development of these systems faces a number of issues that relate to the analysis of numerous factors, which are influenced by the properties of such complex and dynamic systems. The [...] Read more.

Smart service provision systems can assist in the management of cargo transportation. The development of these systems faces a number of issues that relate to the analysis of numerous factors, which are influenced by the properties of such complex and dynamic systems. The aim of this research was the development of an adaptable smart service provision system that is able to recognize a wide spectrum of contextual information, which is obtained from different services and heterogeneous devices of wireless sensor networks (WSNs). To ensure that the smart service provision system can assist with the analysis of specific cases of unforeseen and unwanted situations during the cargo transportation process, the system must have additional adaptability. To address the adequate provision of contextual data, we examined the problems of multi-dimensional definitions of contextual data and the choice of appropriate artificial intelligence (AI) methods for recognition of contextual information. The objectives relate to prioritizing potential service provision by ensuring the optimal quality of data supply channels and avoiding the flooding of wireless communication channels. The proposed methodology is based on methods of smart system architecture development that integrate the identification of context-aware data, conceptual structures of data warehouses, and algorithms for the recognition of transportation situations based on AI methods. Experimental research is outlined to illustrate the algorithmic analysis of the prototype system using an appropriate simulation environment. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

21 pages, 842 KiB

Open AccessArticle

Autonomous Collision Avoidance Using MPC with LQR-Based Weight Transformation

by Shayan Taherian, Kaushik Halder, Shilp Dixit and Saber Fallah

Sensors 2021, 21(13), 4296; https://doi.org/10.3390/s21134296 - 23 Jun 2021

Cited by 7 | Viewed by 3323

Abstract

Model predictive control (MPC) is a multi-objective control technique that can handle system constraints. However, the performance of an MPC controller highly relies on a proper prioritization weight for each objective, which highlights the need for a precise weight tuning technique. In this [...] Read more.

Model predictive control (MPC) is a multi-objective control technique that can handle system constraints. However, the performance of an MPC controller highly relies on a proper prioritization weight for each objective, which highlights the need for a precise weight tuning technique. In this paper, we propose an analytical tuning technique by matching the MPC controller performance with the performance of a linear quadratic regulator (LQR) controller. The proposed methodology derives the transformation of a LQR weighting matrix with a fixed weighting factor using a discrete algebraic Riccati equation (DARE) and designs an MPC controller using the idea of a discrete time linear quadratic tracking problem (LQT) in the presence of constraints. The proposed methodology ensures optimal performance between unconstrained MPC and LQR controllers and provides a sub-optimal solution while the constraints are active during transient operations. The resulting MPC behaves as the discrete time LQR by selecting an appropriate weighting matrix in the MPC control problem and ensures the asymptotic stability of the system. In this paper, the effectiveness of the proposed technique is investigated in the application of a novel vehicle collision avoidance system that is designed in the form of linear inequality constraints within MPC. The simulation results confirm the potency of the proposed MPC control technique in performing a safe, feasible and collision-free path while respecting the inputs, states and collision avoidance constraints. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

23 pages, 4617 KiB

Open AccessEditor’s ChoiceArticle

Multi-Sensor Fault Detection, Identification, Isolation and Health Forecasting for Autonomous Vehicles

by Saeid Safavi, Mohammad Amin Safavi, Hossein Hamid and Saber Fallah

Sensors 2021, 21(7), 2547; https://doi.org/10.3390/s21072547 - 5 Apr 2021

Cited by 42 | Viewed by 8530

Abstract

The primary focus of autonomous driving research is to improve driving accuracy and reliability. While great progress has been made, state-of-the-art algorithms still fail at times and some of these failures are due to the faults in sensors. Such failures may have fatal [...] Read more.

The primary focus of autonomous driving research is to improve driving accuracy and reliability. While great progress has been made, state-of-the-art algorithms still fail at times and some of these failures are due to the faults in sensors. Such failures may have fatal consequences. It therefore is important that automated cars foresee problems ahead as early as possible. By using real-world data and artificial injection of different types of sensor faults to the healthy signals, data models can be trained using machine learning techniques. This paper proposes a novel fault detection, isolation, identification and prediction (based on detection) architecture for multi-fault in multi-sensor systems, such as autonomous vehicles.Our detection, identification and isolation platform uses two distinct and efficient deep neural network architectures and obtained very impressive performance. Utilizing the sensor fault detection system’s output, we then introduce our health index measure and use it to train the health index forecasting network. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

16 pages, 976 KiB

Open AccessArticle

Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages

by Sampo Kuutti, Richard Bowden and Saber Fallah

Sensors 2021, 21(6), 2032; https://doi.org/10.3390/s21062032 - 13 Mar 2021

Cited by 9 | Viewed by 2855

Abstract

The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement [...] Read more.

The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement learning based approach to autonomous vehicle longitudinal control, where the rule-based safety cages provide enhanced safety for the vehicle as well as weak supervision to the reinforcement learning agent. By guiding the agent to meaningful states and actions, this weak supervision improves the convergence during training and enhances the safety of the final trained policy. This rule-based supervisory controller has the further advantage of being fully interpretable, thereby enabling traditional validation and verification approaches to ensure the safety of the vehicle. We compare models with and without safety cages, as well as models with optimal and constrained model parameters, and show that the weak supervision consistently improves the safety of exploration, speed of convergence, and model performance. Additionally, we show that when the model parameters are constrained or sub-optimal, the safety cages can enable a model to learn a safe driving policy even when the model could not be trained to drive through reinforcement learning alone. Full article

(This article belongs to the Special Issue Artificial Intelligence and Internet of Things in Autonomous Vehicles)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence and Internet of Things in Autonomous Vehicles

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI