Intelligent Autonomous Vehicles Research Articles

Review of Autonomous Intelligent Vehicles for Urban Driving and Parking

With the concept of Internet-of-Things, autonomous vehicles can provide higher driving efficiency, traffic safety, and freedom for the driver to perform other tasks. This paper first covers enabling technology involving a vehicle moving out of parking, traveling on the road, and parking at the destination. The development of autonomous vehicles relies on the data collected for deployment in actual road conditions. Research gaps and recommendations for autonomous intelligent vehicles are included. For example, a sudden obstacle while the autonomous vehicle executes the parking trajectory on the road is discussed. Several aspects of social problems, such as the liability of an accident affecting the autonomous vehicle, are described. A smart device to detect abnormal driving behaviors to prevent possible accidents is briefly discussed.

Routing and scheduling of intelligent autonomous vehicles in industrial logistics systems

Routing and scheduling of intelligent autonomous vehicles in industrial logistics systems

Autonomous Intelligent Vehicles (AIV): Research statements, open issues, challenges and road for future

The vehicle business has accomplished extraordinary outcomes in creating dependable, sheltered and reasonable vehicles throughout the only remaining century. Autonomous Vehicles (AV) are turning into a reality due to generous late improvements in Internet of Things (IoTs), Programmable Logic Controller (PLC) and correspondence innovations in computing filed. Notice that self-sufficient vehicles here are for vehicles just including transports, light vehicles, and so forth Model models have now voyaged a huge number of miles in test driving for self-ruling vehicles (under self-sufficient vehicles). This isn't a final attempt to self-governing vehicles; we have to plan Autonomous Intelligent Vehicles (AIV) that can make a compelling (for example, without hurting people) choice over the street organization. Later on, self-governing vehicles will be a reality, in any event, for commercialization, as by and by. In AIV, we face various specialized and non-specialized issues, for example, programming multifaceted nature, constant information examination and testing and confirmation. Handling these issues requires viable and prompt arrangements that meet the prerequisites, guidelines and strategies of clients, industry and government. The analysis of this work will help numerous research analysts who work in Autonomous Vehicles or Intelligent Transport Systems today and so on in near future to get better solution.

Technology of self-driving in challenging road and weather conditions

Every year, the development of autonomous vehicle control systems is becoming more and more pressing due to more global projects in the field of transport, the development of new hard-to-reach areas, and the increasing volume of freight transportation. Particularly acute is the issue of improving control systems in regions with challenging road and weather conditions as well as insufficient visibility, which have a significant impact on traffic safety. It is required to develop algorithmic software for an intelligent autonomous vehicle control system used when transporting goods along a given route. The paper considers the control algorithm as well as the equipment of the control system and the tracking machine vision system. The results of experimental studies on the movement of an autonomous vehicle based on the KamAZ 6520 production vehicle are presented.

Computer vision based obstacle detection and target tracking for autonomous vehicles

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.

Integration of an MES and AIV Using a LabVIEW Middleware Scheduler Suitable for Use in Industry 4.0 Applications

Industry 4.0 uses the analysis of real-time data, artificial intelligence, automation, and the interconnection of components of the production lines to improve manufacturing efficiency and quality. Manufacturing Execution Systems (MESs) and Autonomous Intelligent Vehicles (AIVs) are key elements of Industry 4.0 implementations. An MES connects, monitors, and controls data flows on the factory floor, while automation is achieved by using AIVs. The Robot Operating System (ROS) built AIVs are targeted here. To facilitate MES and AIV interactions, there is a need to integrate the MES and the AIVs to help in building an automated and interconnected manufacturing environment. This integration needs middleware, which understands both MES and AIVs. To address this issue, a LabVIEW-based scheduler is proposed here as the middleware. LabVIEW communicates with the MES through webservices and has support for ROS. The main task of the scheduler is to control the AIV based on MES requests. The scheduler developed was tested in a real factory environment using the SAP MES and a Robotnik ‘RB-1′ robot. The scheduler interface provides real-time information about the current status of the MES, AIV, and the current stage of scheduler processing. The proposed scheduler provides an efficient automated product delivery system that transports the product from process cell to process cell using the AIV, based on the production sequences defined by the MES. In addition, using the proposed scheduler, integration of an MES is possible with any low-cost ROS-built AIV.

Deep CNN, Body Pose, and Body-Object Interaction Features for Drivers’ Activity Monitoring

Automatic recognition and prediction of in-vehicle human activities has a significant impact on the next generation of driver assistance and intelligent autonomous vehicles. In this article, we present a novel single image driver action recognition algorithm inspired by human perception that often focuses selectively on parts of the images to acquire information at specific places which are distinct to a given task. Unlike existing approaches, we argue that human activity is a combination of pose and semantic contextual cues. In detail, we model this by considering the configuration of body joints, their interaction with objects being represented as a pairwise relation to capture the structural information. Our body-pose and body-object interaction representation is built to be semantically rich and meaningful, which is highly discriminative even though it is coupled with a basic linear SVM classifier. We also propose a Multi-stream Deep Fusion Network (MDFN) for combining high-level semantics with CNN features. Our experimental results demonstrate that the proposed approach significantly improves the drivers’ action recognition accuracy on two exacting datasets.

A convolutional neural network accelerator for real-time underwater image recognition of autonomous underwater vehicle

In the field of underwater image recognition, a chip with smaller footprint and lower energy consumption is required to be implanted into autonomous intelligent underwater vehicle to make real-time response to the surrounding objects. Therefore, a promising accelerator with high performance and low energy consumption is designed, which optimizes the features possessed by convolutional neural network. The sharing of weights between neurons reduces the memory requirement. With all convolutional neural network data stored within on-chip static random-access memory, the need for memory access is drastically decreased. Besides, several small processing elements are used to form neural functional unit, which considerably reduces the bandwidth requirement through inter-processing element data transmission. By sending control signals to autonomous underwater vehicle, this accelerator enables it to avoid dangerous areas such as rocks and algae in time. The result suggests the proposed accelerator successfully achieves a higher processing speed than that of CPU and GPU with a footprint of 6.09 mm2 only and the energy consumption of 327.3 mW at 1 GHz.

Robotic Movement Based on Color Detection

In recent times, to reduce human labor robots are being manufactured and used in various fields. Robots are the intelligent vehicles that are designed to work according to the instructions given to them by their creators. Some of these robots are also made automatic. The aim of the paper is to design and implement a robot to perform the act of monitoring as well as detecting specific colored objects in its path. This robot is generally an autonomous intelligent vehicle that recognizes the color of the object in its path and reacts according to the users instructions. While on its motion, the camera mounted on the robot helps for live video streaming so that operators can see the route of the robot. Integration of the robot can only be measured when it can overcome the obstacles in its route efficiently and reach its destination autonomously.f these robots are also made automatic. The aim of the paper is to design and implement a robot to perform the act of monitoring as well as detecting specific colored objects in its path. This robot is generally an autonomous intelligent vehicle that recognizes the color of the object in its path and reacts according to the users instructions. While on its motion, the camera mounted on the robot helps for live video streaming so that operators can see the route of the robot. Integration of the robot can only be measured when it can overcome the obstacles in its route efficiently and reach its destination autonomously.

Deep Convolutional Framework for Perception Systems in Intelligent Autonomous Vehicles

Deep Learning algorithms can facilitate and strengthen sophisticated ADAS/Autonomous vehicle technologies to a large extent. Vision based perception functions powered by modern sensor networks in combination with Convolutional Neural Network (CNN) models can provide cutting-edge results in computer vision problems. The paper encompasses different types of deep learning architectures, some popular vehicular datasets and the most viable deep learning libraries for implementing the autonomous driving algorithms. In this paper, convolutional model algorithm is designed using Keras to train the dataset and is evaluated which provided considerable accuracy rate to implement them in future object detection algorithms. CNNs can provide state of the art solutions for the problems related to perception related tasks such as classifying objects, traffic environment understanding and taking appropriate actions.

Design and Development of a Material Handling System for an Autonomous Intelligent Vehicle for Flexible Manufacturing

Flexible Manufacturing Systems (FMS) is a domain where progressive research has been undertaken. The future for survival, in an increasingly congested industrial environment can be achieved by making an innovative, technical, organisational and major financial effort to secure ultimate viability from low cost labour countries. A potential solution was the research and integration of a material handling system with an Autonomous Intelligent Vehicles (AIV) for the seamless transportation of product in a manufacturing environment. AIVs were indicated as a positive solution to the reduction of mundane and laborious manual handling operations present in manufacturing processes. Further research into advancements of electromechanical interface technologies for a material handling system combined with an AIV. The research focused on an industrial capable product with a collection of sensors for material handling. The research proposed to progress the material handling system with Industry 4.0 capabilities through machine to machine (M2M) communication. The on-board sensors of the material handling system together with the intelligence of the AIV delivered an automated and autonomous system capable of intralogistics movement of material in the modern world of Industry 4.0.This paper presents a detailed account of the phases of research in design, build, test and integration.

Real-time Image Contrast Enhancement VLSI Design for Intelligent Autonomous Vehicles

Abstract A novel hardware-oriented image contrast enhancement algorithm is proposed in this study for intelligent autonomous vehicles. It utilizes a weighted filter and calculates the brightness values of an image based on the adjusted image. The brightness values are processed to either reduce or increase the brightness values of the points. To further improve the quality of an image, the algorithm implements a block-based pixel processing as opposed to a per image frame processing. The brightness values for each block or area in the image are used to improve the contrast of the image. This is accomplished by reducing or increasing the different brightness values of the pixel or lifting point in each block. Simulation results showed that compared with previously proposed algorithms, this work improved on the average discrete entropy by 1% and increased the average color enhancement factor by 8.5%. The proposed novel algorithm was realized using TSMC 0.18 μm CMOS cell process. The VLSI design has a total gate count of 6028 and operates with a frequency of 201 MHz and a power rating of 17.47 mW.

Uncertain fault estimation using bicausal bond graph: Application to intelligent autonomous vehicle

This article addresses the fault detection and isolation problem of uncertain systems using the bond graph model–based approach. The latter provides through its causal and structural properties an automatic analytical redundancy relations generation. The numerical evaluation of analytical redundancy relations yields residuals, which are used to verify the coherence between the real system and reference behaviors describing the nominal operation. In fact, the residual is compared to its thresholds to detect the fault. In addition, the comparison between all fault signatures allows making a decision on fault isolation. Moreover, to isolate the faults that activate the same set of residuals, an additional residual must be calculated for each fault. This additional residual is the comparison between two estimations of the considered fault obtained using the sensitivity relations. However, due to the presence of uncertainties, errors can occur in the fault estimation allowing false decisions on fault isolation. The novelties and innovative interests in the present work are (1) to improve the fault estimation procedure based on the uncertainties modeling and bicausality notion, in order to overcome the problem related to errors in the estimated fault and (2) to suitably generate the isolation thresholds in a systematic way using the uncertain fault estimation procedure proposed in this article so that fault can be isolated successfully. The proposed methodology is studied under various scenarios via simulations over an electromechanical traction system corresponding to a quarter of intelligent autonomous vehicle, named RobuCar.

A Access Traffic Sign Detection Tracking and Recognition System for Video Frames using KNN Algorithms

Video-based traffic sign detectiontracking and recognition plays an important role in driving support system as well as in intelligent autonomous vehicles. This framework includes three parts like traffic sign detecting, target tracking and sign recognition. This paper contributes different methods for detecting and recognizing of traffic sign, so that drivers can be easily identify the type of signal in road sides. In this approach different methods like color segmentation and scale based intraframe fusion technics is proposed which includes the spatial-temperol constraints in videos, by fusing the different casings that have a place with an equivalent physical sign along to induce higher exactness.

Integration of autonomous intelligent vehicles into manufacturing environments: Challenges

As companies begin to move towards Industry 4.0 and implement Smart Manufacturing techniques, flexible manufacturing comes to the fore. This allows a facility to adapt to changing needs and demands, with less impact on production, when compared to rigid production lines.Traditionally, the introduction of new equipment into a production line is somewhat straightforward, as the equipment is generally static. In recent times however, Autonomous Intelligent Vehicles (AIVs) have become a pivotal component of smart production lines. Given there may be in excess of twenty AIVs working simultaneously, the integration challenge becomes even more complex.This paper identifies several challenges associated with the integration of an AIV into a manufacturing environment controlled by a Manufacturing Execution System (MES). Further to this a discussion of the solutions being implemented currently on a live project is provided.

Multilevel Modeling of System of Systems

A system of systems (SoS) is a large-scale integrated system. In an SoS, many complex independent systems work collectively for a common mission. Modeling of SoS is challenging due to their large-scale and complexity of the constituent systems. In this paper, generic modeling of a class of SoS, namely mechatronic systems, is proposed based on bond graph modeling approach. Bond graph modeling enables to develop a unified model of SoS, which combines the behavioral and the organizational modeling approaches of SoS. The proposed approach for SoS modeling is applied to intelligent transportation system, where road traffic dynamic in a platoon of intelligent autonomous vehicles (IAVs) is considered for modeling. Finally, the developed bond graph model is simulated for a platoon of four IAVs forming SoS.

Intelligent autonomous vehicles in digital supply chains

PurposeThe purpose of this paper is twofold: first, to discuss key challenges associated with the use of either simulation or real-world application of intelligent autonomous vehicles (IAVs) in supply network operations; and second, to provide a theoretical and empirical evidence-based methodological framework that supports the integrated application of conceptualisation, simulation, emulation and physical application of IAVs for the effective design of digital supply networks.Design/methodology/approachFirst, this study performs a critical review of the extant literature to identify major benefits and shortcomings related to the use of either simulation modelling or real-word application of physical IAVs. Second, commercial and bespoke software applications, along with a three-dimensional validation and verification emulation tool, are developed to evaluate an IAV’s operations in a conceptual warehouse. Third, a commercial depth-sensor is used as a test bed in a physical setting.FindingsThe results demonstrate that conceptual and simulation modelling should be initially used to explore alternative supply chain operations in terms of ideal performance while emulation tools and real-world IAV test beds are eminent in validating preferred digital supply chain design options.Research limitations/implicationsThe provided analysis framework was developed using literature evidence along with experimental work and research experience, without consulting any industry experts. In addition, this study was developed based on the application of a single physical device application as a test bed and, thus, the authors should further progress with the testing of a physical IAV in an industrial warehouse.Practical implicationsThe study provides bespoke simulation modelling and emulation tools that can be useful for supply chain practitioners in effectively designing network operations.Originality/valueThis work contributes in the operations management field by providing both a multi-stage methodological framework and a practical “toolbox” for the proactive assessment and incorporation of IAVs in supply network operations.

An Overview of Nature-Inspired, Conventional, and Hybrid Methods of Autonomous Vehicle Path Planning

Safe and smooth mobile robot navigation through cluttered environment from the initial position to goal with optimal path is required to achieve intelligent autonomous ground vehicles. There are countless research contributions from researchers aiming at finding solution to autonomous mobile robot path planning problems. This paper presents an overview of nature-inspired, conventional, and hybrid path planning strategies employed by researchers over the years for mobile robot path planning problem. The main strengths and challenges of path planning methods employed by researchers were identified and discussed. Future directions for path planning research is given. The results of this paper can significantly enhance how effective path planning methods could be employed and implemented to achieve real-time intelligent autonomous ground vehicles.

The VILMA intelligent vehicle: an architectural design for cooperative control between driver and automated system

Intelligent autonomous vehicles have received a great degree of attention in recent years. Although the technology required for these vehicles is relatively advanced, the challenge is firstly to ensure that drivers can understand the capabilities and limitations of such systems and secondly to design a system that can handle the interaction between the driver and the automated intelligent system. In this study, we describe an approach using different strategies for an autonomous system and a driver to drive a vehicle cooperatively. The proposed strategies are referred to as cooperative planning and control and determine when and how the path projected by the autonomous system can be changed safely by the driver to a path that he wishes to follow. The first phase of the project is described, covering the design and implementation of an autonomous test vehicle. Experiments are carried out with a driver to test the cooperative planning and control concepts proposed here.

Proposed Framework for Partial Vehicle Image Detection Using SVM and Fuzzy

Image of particular object as vehicle as image detection is mainly the important role in driver assistant system as well as in intelligent autonomous vehicles. Thus in real - time it run time performance in term of accuracy performance. Thus the proposed system is discussed with consideration of overlapping of one image with another and partial view of images etc.thus the partial vehicle detection module is basically on driver assistant system and intelligent auto-nous vehicles by considering what type of image as vehicle appears in which area should extracted and classification based color Histogram of Orientated Gradients. Thus it perform the conversion of the input image as vehicle into gray image then Supreme stable outer region thus extract input as stable object in the previous output with the use of more one or more frames. In upcoming research the support vector machine retrieve the image as data from maximum stable external region result and then matches with database of image. Thus the concurrently the fuzzy pattern cluster techniques retrieve the object of interest from SSOR result and then apply the colors after that it will matches it with existing database images of vehicles.