No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Motion Control and Sensor Fault Diagnostic Systems for Autonomous Electric Vehicle
Abstract
Motion control of an autonomous or self-driving car depends intensely on data associated with its lateral and longitudinal motion sensors. These sensor data is used to formulate necessary and appropriate control signal for smooth and stable maneuver, through steering and acceleration subsystems. The work here focus on implementation of such motion control systems on a physical vehicle that is modified to achieve desired autonomous functionality on a predefined path. In addition, a sensor diagnostic system for monitoring the sensor health condition is tested to identify the faulty values in the system.
The era of electronics began very early in automobiles but was rejected or discontinued mainly because of the size and cost of electronics by the consumers and original equipment manufacturers as vehicle population day by day started ramping up. This became the biggest hurdle for developing countries as most of the countries in the world have to import the required fuel, and most importantly, these vehicles on the road started polluting the environment. The air pollution caused by vehicles has been a huge impact on the health of every creature on this planet. They forced the government entities to put forth stringent emission norms for the original equipment manufacturers and suppliers. This was the main reason for electronics to enter into automobiles because the conventional (mechanical) method to control the fuel economy and exhaust emission was inadequate/inefficient. Another biggest reason for the sudden rush of electronics into automotive was the emerging semiconductor era. As a very large-scale integration of the transistors into a single chip began. That is, the system on chip development drastically reduced the size and cost of the electronics being used. The electronics in an automobile started controlling the mechanical components or even replaced many conventional mechanical components. The era of electronics began with controlling fuel economy and emission, but now modern electronics are not just limited to these objectives. Now, modern CARs use up to 100 electronic control unit (ECU). ECUs are used for every look and corner of the vehicle such as controlling the engine, braking, steering, suspension, infotainment, telematics, safety, and many more functions, which goes up to 2500 functions with 10 million lines of code. The paper majorly focuses on vehicle emission monitoring and updating the status of each of the vehicles on the cloud server using an IOT application. The paper’s second objective is to focus on the model-based design using Simulink. The conventional method has been code-based design, but the majority of the automotive industries are focusing on model-based design because of its versatile advantages. If the vehicle under monitoring is crossing the specified limit of the emission standards, then the controller monitors the condition and updates the emission status of the vehicle on the cloud. It gives the broader picture of the corrupt vehicles to the government entities, and necessary actions can be taken.
In cloud computing technology, task scheduling is one of the research challenges. For these various algorithms, works such as particle swarm optimization (PSO), firefly algorithm, ant colony optimization (ACO) and genetic algorithm (GA). PSO is inspired by the bird’s movement, and ACO is based on the behaviour of ants. GA works based on the natural evolution process. This paper presents the hybrid of PSO-ACO-GA for task scheduling on virtual machines of cloud computing known as ant particle swarm genetic algorithm (APSGA). Here, GA and PSO will perform iteration to get the task basis on fitness value and further ACO will distribute the task on specific virtual machines. This paper has achieved improved results for parameters such as CPU utilization, makespan and execution time. Our proposed algorithm has achieved makespan that is reduced by 27.1%, 19.45% and 21.24% with compare to PSO, ACO and GA, respectively. It has achieved maximum of CPU utilization and execution time.
There has been an exponential growth in the vehicle population in recent times, adding to the metropolitan traffic. This increase in the number of vehicles has led to the problem of inadequate parking spaces resulting in traffic congestion. To address this challenge, a smart parking system is proposed in this paper, which makes use of TIME RESOURCE SHARING to effectively utilize the parking spaces based on peak demand time and enables prior identification and reservation of parking space with the help of unique identification. The system periodically updates the parking status. The interaction of the driver and the owner of the parking space takes place through the application connected through the cloud. The related work in this area has also been referred. The proposed system has the potential to transform the current parking method and alleviate the traffic congestion caused by insufficient parking space.
Natural language interfaces are gaining popularity as an alternative interface for non-technical users. Natural language interface to database (NLIDB) systems have been attracting considerable interest recently that are being developed to accept user’s query in natural language (NL), and then converting this NL query to an SQL query, the SQL query is executed to extract the resultant data from the database. This Text-to-SQL task is a long-standing, open problem, and towards solving the problem, the standard approach that is followed is to implement a sequence-to-sequence model. In this paper, I recast the Text-to-SQL task as a machine translation problem using sequence-to-sequence-style neural network models. To this end, I have introduced a parallel corpus that I have developed using the WikiSQL dataset. Though there are a lot of work done in this area using sequence-to-sequence-style models, most of the state-of-the-art models use semantic parsing or a variation of it. None of these models’ accuracy exceeds 90%. In contrast to it, my model is based on a very simple architecture as it uses an open-source neural machine translation toolkit OpenNMT, that implements a standard SEQ2SEQ model, and though my model’s performance is not better than the said models in predicting on test and development datasets, its training accuracy is higher than any existing NLIDB system to the best of my knowledge.
Self driving cars are picking up pace and thus serves as a challenging research domain. One of the most crucial functions in an autonomous vehicle is accurately detecting and recognising the traffic signs. Traffic sign detection is a crucial task in traffic sign recognition systems. Deep neural networks are proven powerful in traffic sign classification. As traffic sign violation leads to law and order disruption, posing a threat to human life, there is a need for robust algorithms with efficient actuation to perform the delegated task. Thus, this paper proposes a robust algorithm which addresses challenges like haze, fog, unclear images due to improper condition of roads to efficiently detect and recognize traffic signs using Image manipulation, Optical Character Recognition (OCR) algorithm and You Only Look Once (YOLOv3) detection algorithm. The proposed algorithm in this paper for hazy images that aids in ADAS applications has an accuracy of 87.29%. This contributes to the emerging research domains of autonomous vehicles and self-driving cars.
The ability to acquire quality learning is always being a very subjective affair of individuals. Every lecture/session spent during the study doesn’t assure complete knowledge transfer between instructors and student. Today’s world focuses more on student-centered learning where the learning aims at a high degree of student engagement with encouragement. This motivates for Institutional Research Project (IRP) initiative, where students are encouraged in self-learning under guidance, with an objective to accomplish a project or task at their own pace of learning under stipulated time, while fostering their interests. A team of students and researchers from the School of Electronics, Computers and Mechanical sciences at KLE Tech are developing an open platform for studying computational algorithms, sensors and electronics, drives and mechanical designs for autonomous or self-driving vehicles under automotive research.
The latest version of the ISO 26262 standard from 2016 represents the state of the art for a safety-guided development of safety-critical electric/electronic vehicle systems. These vehicle systems include advanced driver assistance systems and vehicle guidance systems. The development process proposed in the ISO 26262 standard is based upon multiple V-models, and defines activities and work products for each process step. In many of these process steps, scenario based approaches can be applied to achieve the defined work products for the development of automated driving functions. To accomplish the work products of different process steps, scenarios have to focus on various aspects like a human understandable notation or a description via state variables. This leads to contradictory requirements regarding the level of detail and way of notation for the representation of scenarios. In this paper, the authors discuss requirements for the representation of scenarios in different process steps defined by the ISO 26262 standard, propose a consistent terminology based on prior publications for the identified levels of abstraction, and demonstrate how scenarios can be systematically evolved along the phases of the development process outlined in the ISO 26262 standard.
Driving test is critical to the deployment of autonomous vehicles. It is necessary to review the related works since the methodologies summaries are rare, which will help to set up an integrated method for autonomous driving test in different development stages, and help to provide a reliable, quick, safe, low cost and reproducible method and accelerate the development of autonomous vehicle. In this paper, we review the related autonomous driving test works, including autonomous vehicle functional verification, vehicle integrated testing, system validation in different architectures. This review work will be helpful for autonomous vehicle development.
In this paper we explore the opportunities of improving the testing and verification phases of product development in the automotive industry, through a combination of broadband telematic services and tools and methods for distributed collaborative engineering. The development of a prototype system for remote vehicle testing is described, and experiences from experimental usage of the system at an automotive winter testing facility are reported. The prototype system supports real time communication of audio, video and measurement data from a vehicle at a test track, to a remote location such as an automotive company's development site. Initial results from using the system are promising, indicating a clear potential of improving the testing and verification phases of product development within the automotive sector, which will be essential in the future in order to meet demands on shortened development cycles and increased testing needs.
To know the nature of the surrounding is very crucial, and the profile of the terrain geometry must be known to decide the motion path in autonomous cars. The obstacles must be detected along with their coordinates with the vehicle as origin (reference) and relative velocity to determine a collision free path. Most autonomous vehicle manufacturers depend extensively on LIDAR such as Uber and Google, whereas Tesla uses RADAR as a primary sensor. RADAR is relatively less expensive and works equally well in all weather conditions such as fog, rain, snow, and dust. It can also determine relative traffic speed using Doppler frequency shift which is not possible in case of LIDAR. Hence, RADAR is a viable solution for autonomous cars considering above parameters, and it provides good results when used with secondary sensors such as ultrasonic and camera. This paper proposes a methodology for testing RADAR sensor AWR1642 in various configurations with respect to distance and angle of coverage. The testing of the above RADAR is carried out on real vehicle. The results obtained verify that RADAR provides accurate results within 50 m range for medium-sized objects with appropriate tuning of parameters such as best range and best range resolution.
Project-based learning (PBL) is an instructional method in which students learn a range of skills and subject matter in the process of creating their own projects. Sometimes, these projects are solutions to a real-world problem. But what is most important in project is that students gain the design experience. They work in groups and bring their own experiences, abilities, learning styles, and perspectives to the project. Students work in teams under the direction of a faculty advisor to tackle an engineering design project. Engineering communication, such as reports and oral presentations are covered. We emphasize practical, hands-on experience, and integrate analytical and design skills acquired in companion senior-level core courses. In this paper, we propose to introduce the project-based learning approach throughout the course at various levels and its impact at learning ability and employability. This experiential learning helped the students to improve comprehensive application ability and innovative consciousness.
Modern automotive systems are rapidly becoming highly defined and characterized by embedded electronics and software. With new technologies in the vehicle the industry is facing new opportunities and also new challenges. Electronics have improved the performance of vehicles and at the same time, new more complex applications are introduced. Any new component introduced in the vehicle must be cost-efficient. This means that there must be some added value or reduced cost associated with the component, there is no value in itself for choosing electronics as the technology for a given function. Further, new technologies must be evaluated for dependability. Electronics and particularly software are immature engineering disciplines that require further efforts to create dependable and trusted solutions. We are all far too aware of the malfunctioning personal computers in our homes to blindly trust embedded computers in safety-critical applications. This report describes different aspects of cost efficiency and dependability for modern automotive electronics. Some general areas of dependability concerns, together with methods to solve these concerns and their cost-efficiency are discussed. Considering that safety cannot be compromised, several of the methods supporting safety must be utilized in order to achieve an acceptable level of safety even if higher costs are incurred. Some methods are found to be generally beneficial, like the introduction of system layering and modular components. A more formalized layering with tools, middleware or models may be beneficial in many cases but the methods should be introduced with care, the important factor to consider is the possibility for reuse of the designs in the system. Another trade-off is the choice of reliable components and the level of redundancy, a balancing act between production costs and availability/maintenance costs. Knowing the basic methods and factors that improve dependability and the incurred costs some general conclusions can be drawn. It is however necessary to consider the market value of functions before specific conclusions can be drawn. The cost efficient and dependable electronic system architectures for future automotive systems will be decided by the market preferences for functionality.
Speed Control of DC Motor Using PID Controller
- H Pooja
- G Priyanka
- H Prithvi
- U Sapna
- S Ramya
- B Priyanka
Pooja, H., Priyanka, G., Prithvi, H., Sapna, U., Ramya, S., Priyanka, B., et al. (2016). Speed
Control of DC Motor Using PID Controller. International Journal of Industrial Electronics
and Electrical Engineering, 4(5), 5-7. ISSN: 2347-6982.
Speed Control of DC Motor Using PID Controller ISSN: 2347-6982
- H Pooja
- G Priyanka
- H Prithvi
- U Sapna
- S Ramya
- B Priyanka
- I Swathi
- RM Shet
Reliability engineering. Hemisphere Publishing Corp
- P D T O'connor
O'Connor, P. D. T. (1988). Reliability engineering. Hemisphere Publishing Corp. ISBN 0-89116-684-X.