Assignment Sample Big Data in Autonomous Driving
Automation nowadays started generating demands for living services and goods. Automation is one term for any technical application where one human minimizes all the inputs. Automation generally takes rudimentary, simple tasks and makes them automated. An automated driving system on one vehicle can perform all the aspects of one driver’s task. However, all the aspects need to be done in some circumstances. The circumstances are like at any time; the driver needs to be ready for any situation to take control of the car. Big data basically helps a self-driving car to transform more efficiently. It generally provides all the necessary information that will help the vehicle choose one route from many that also help the driver avoid things such as parking issues or it also helps to avoid congestion. The big data on self-driving cars can also be used to act after planning, and the acts will be based on gathering several pieces of data.
The research objectives regarding the topic of big data systems within the automation driving process are provided below. These objectives have made the entire research project more authentic and more understanding for all people.
- To make the trajectory or path planning is one of the vital tasks for operating autonomous vehicles.
- For designing a case related to autonomous vehicles, which are linked with a cloud-based environment.
- To select an effective and safe trajectory by using big data mining processes and analysis for real-time accidents as well as real-time vehicles
- for making a decision by selecting these types of trajectories.
In this case, the entire research questions regarding the topic of big data systems within the automation driving process are mainly based on the proposed research objectives. For this reason, the research objectives are described below.
- What is the main operational path for making the operational activities of autonomous vehicles more proper?
- How are the operational activities designed for autonomous vehicles?
- How is the entire working analysis placed for processing the autonomous vehicles?
- What are the necessary decisions of trajectories?
Project outcomes are the kind of changes that happen as one result of one’s action. These actually take part to have an improvement for one service and product. At the time of project designing, it is very much important to know about the project. This project basically gives an outcome for such people as people having disabilities. Automation will help all the people who are physically disabled will help them to drive one car. It may be that one person is blind; the automated car will help one live their life how they want. These vehicles can also increase independence for senior people. Automation can also help to reduce the number of road crashes. As the report mentions, it is predicted that if all the cars become automated, the number of chances for accidents will be reduced.
According to the author Chen et al. (2018), advanced automation driving in the technical world has generated an opportunity for smart mobility. Automated vehicles nowadays become so popular topic with the rise of smart cities. However, urban administration, legislators, and some of the planners are already unprepared to make one deal with any possible disruption in automation vehicles. The main aim of the research study is to determine one’s position. The research paper may have some lack of knowledge on the disrupted capabilities. The research paper basically helps to develop one outline framework which will interlink between driving forces. The review helps to reveal all the trajectories regarding development in technology. The research paper includes one systematic review on present evidence to make everyone understand the impact, planning, capability and the issued policy in autonomous vehicles (Chen et al. 2018). The research paper mentions all the possible needs to overcome many challenges of any urbanization like climate change, greenhouse emission. Transport is one integral part of one city which is basically responsible for greenhouse emissions. The research paper includes one symmetric review on one current existing event.
Regarding the research note of the author Dremel, Herterich & Brenner (2017), the main basic concept of the automated road vehicle helps refer to the changes of many or some of the workers who actually run electric devices. In the early 20th century, automation on driving technology could easily be traced. The technology mainly concentrates on autonomous speed, lane control, break, and other basic control aspects. In the last decade, incubating conditions in the digital and also industrial revolution have given birth to many technological advancements in the normal field (Dremel, Herterich & Brenner, 2017). The research paper also includes the next generation technique generating on the top aim to give the best quality communication services. All the relevant services depend on one high output, and also, all the best quality services depend on the low delay and massive connectivity. The research paper also includes the exponential growth of all numerical data, leading to the big data era. The research paper also mentions that machine learning has become one of the most promising artificial intelligence tools and helps analyze a huge amount of data. Analyzing all the data becomes invoked on several researchers in both the area such as industry area and also in the academic area.
According to the author Kaffash, Nguyen & Zhu (2021), big data follows machine learning classification. Some wireless users normally generate big data. All the users contain a lot of useful information like many activity patterns. The research paper also mentions all the data varied over time; in different frequencies, interference power also changed. Supervised learning is implemented in automatic cars. The research paper also includes one major branch of machine learning. Many quantities should be rapidly needed for implementing one functional mapping with the sample training data. The main advantage shown in supervised learning is to make conversation speed higher. The research paper also observes that collecting data is the easiest process, and the cost for collecting all the data is also low (Kaffash, Nguyen & Zhu, 2021). The research paper also mentions one algorithm named batch learning algorithm that helps to build the automated car. It is basically a batch learning algorithm that helps to train all the models typically. To test the model, sufficient data is generated. The online-based learning method basically has the advantage of allowing more models on machine learning to do frequent testing. It enables one model to learn from one streamed data that can arrive sequentially. The main advantage of using batch learning is that the speed of convergence is actually too high. It may be that batch learning is not suited for real-time learning while all the data is fluctuating rapidly.
According to the author Liu, Tang & Gaudiot (2017), at the time for extracting features from one dataset that basically contains the entire mobile user’s geolocation tag. The possible data can also be social cloud data or wireless data. The research paper also mentions that every year all car manufacturers become close to developing autonomous vehicles successfully. In the last few years, all the major technology companies started pairing up with all the car manufacturers to develop one technology that will allow most of the vehicles to move on the road. The researchers also mentioned that all the car manufacturers expect that all the fully automatic vehicles will be released in the next decade. All these vehicles have an expectation that within the next decade, all the automated vehicles will be released (Liu, Tang & Gaudiot, 2017). The automated car will also have a huge impact on society. All the automated vehicles are expected to have huge safety numbers and also environmental benefits. Big data is one of the most helpful data to gather enough information, and it also provides deep learning into the datasets. The research paper also mentions that it may be that all these technologies give one linear step to automation that is why all of them remained long distance to make one vehicle automated. Big data takes one major step in changing the whole industry. Big data uses deep learning techniques. Deep learning techniques contribute a huge amount of data to make one vehicle fully automated.
According to the author Sharma (2021), autonomous vehicles of big data help one use sensors properly. All autonomous cars do not exist if there is no big data. It also cannot stay without the sensors. Sensors are the most important thing to make an automated car efficient. The sensors help the cars in every way to avoid car crashes and go to reach the goal. In the process of sense everything, an autonomous vehicle usually takes help from three types of sensors: camera, lidar, and radar (Sharma, 2021). The camera basically helps to get a 360-degree surrounding view. Another automated car sensor is lieder that generate one 3D surrounding image and creates the map around the car to avoid all the obstacles. The most crucial parts of autonomous driving are one kind of software and one server that will create the main map.
All the information is taken from secondary resources such as online articles, journals, and other references like books and online PDFs. One qualitative analysis is followed to make a process to the whole work report. The methodology is one of the procedures that will make all the overall research methods in one efficient way. Qualitative analysis is used to gather all the information for this particular topic. The qualitative analysis uses subjective judgment to properly analyse one company’s value on non-quantifiable information like industry cycle management expertise, development and research strength, and the relation between the labourers. Qualitative\ analysis basically mainly deals with inexact information and intangibles that make everything difficult to measure and collect. It also helps to understand people and the cultures of one particular company, which are mainly central to the qualitative analysis. It helps to gather all the necessary equipment; secondary analysis is also done like all the necessary information is taken from Books, pdf, online articles, and also from relevant websites. Secondary analysis is one kind of analysis that directly refers to the present data sets to find all the answers to one question. The secondary analysis also involves one researcher who will be using all the necessary information gathered by someone else. Data analysis is one attempt to give answers to many research questions. The secondary analysis also has one alternative perspective for one original question. The design part is implemented using this technique. There are two types of secondary data, one is internal data, and another one is external data. Here most of the research is done using external data like online pdf books. In the process to create the research design, several strategies are taken, such as sampling methods. It is very hard to collect data from all individuals. Probability sampling is used to gather all the information for this particular topic. Probability sampling can be defined as one of the efficient ways to collect huge amounts of data. 4 sampling techniques are used in this research process. Systematic sampling technique is used to gather the major information, and cluster sampling and stratified sampling is also used to create the research design.
Everyone’s lifestyle can have a huge improvement while self-driving. The foundation of national science makes improvements in all the traffic boosted flows. It also helps to reduce congestion by influencing many traffic flows. Fuel consumption is another major issue that can also be solved by this automated car (Tian, Chin & Yanikomeroglu, 2018). Autonomous vehicles mainly raise one host of many ethical challenges, including maintaining the interaction with human drivers in one environment that can be mixed trafficked. Automated vehicles raise one ethical host challenge. It also includes the interaction of mixed environments with human drivers. Automated vehicles inevitably create an accident scenario. The findings also indicated that ethics differed among civilizations. Volunteers from Latin America and France and its past and current overseas territories, for example, significantly favoured sparing women, young people, and athletes (Xu, Zhu & Wu, 2019). Furthermore, in industrialized nations with robust rules and institutions, jaywalkers were saved less frequently than those who followed traffic laws.
There are some risks in automation cars
- False security senses.
- Fire issues
- Lacking self-driving regulation
The project proposal takes 5 days. And the selection for the project proposal also takes 5 days. The research objective also takes 5 days. One initial literature survey is done, and that takes almost 20 days. The background verifications also take 13 days. The literature survey is also done, and it takes 15 days. The proposed methodology is done within 8 days. It takes more than 9 days to collect all the data. Finding parts is also done in 10 days. The discussion part is also done in 5 days. The discussion part is also done in 7 days. It takes 5 days to complete the recommendation part. The project closes in 3 days. And the final submission is made in two days. The project proposal starts on 9th September and ends on 15th September. The selection of the process also takes some days it is started on 23rd September and ends on 20 October.
Automation nowadays started generating demands for living services and goods. Big data basically offers to have a smooth path that will fully create one path for automated cars in the PR department. The main ability of an automated car is it will navigate to the destination automatically with safety measures. An automated driving system on one vehicle can perform all the aspects of one driver’s task. However, all the aspects need to be done in some circumstances. The circumstances are like at any time; the driver needs to be ready for any situation to take control of the car. Big data basically helps a self-driving car to transform more efficiently. It generally provides all the necessary information that will help the vehicle to choose one route from many that also help the driver to avoid things such as parking issues or it also helps to avoid congestion. Big data is actually helping all self-driving cars to make them more efficient. Big data will allow all autonomous cars to make connections on an existing network, producing a massive amount of data to navigate the road. It can be easily estimated that self-driving can use 30 terabytes of data within 8 hours. This network development will be the most critical factor for the future for both unfolds data and self-drivers also.
Chen, L., Hu, X., Tian, W., Wang, H., Cao, D., & Wang, F. Y. (2018). Parallel planning: A new motion planning framework for autonomous driving. IEEE/CAA Journal of Automatica Sinica, 6(1), 236-246. Retrieved from: https://www.academia.edu/download/58201395/Parallel_Planning__A_New_Motion_Planning_Framework_for_Autonomous_Driving.pdf [Retrieved on 28.09.2021]
Cheng, N., Lyu, F., Chen, J., Xu, W., Zhou, H., Zhang, S., & Shen, X. (2018). Big data-driven vehicular networks. IEEE Network, 32(6), 160-167. Retrieved from: https://arxiv.org/pdf/1804.04203.pdf [Retrieved on 28.09.2021]
Dremel, C., Wulf, J., Herterich, M. M., Waizmann, J. C., & Brenner, W. (2017). How AUDI AG Established Big Data Analytics in Its Digital Transformation. MIS Quarterly Executive, 16(2). Retrieved from: https://www.researchgate.net/profile/Christian-Dremel/publication/317232875_How_AUDI_AG_Established_Big_Data_Analytics_in_its_Digital_Transformation/links/59b6a72d458515c212b2e169/How-AUDI-AG-Established-Big-Data-Analytics-in-its-Digital-Transformation.pdf [Retrieved on 28.09.2021]
Kaffash, S., Nguyen, A. T., & Zhu, J. (2021). Big data algorithms and applications in intelligent transportation system: A review and bibliometric analysis. International Journal of Production Economics, 231, 107868. Retrieved from: http://www.deafrontier.net/papers/IJPE_bigdataITS.pdf [Retrieved on 28.09.2021]
Liu, S., Tang, J., Wang, C., Wang, Q., & Gaudiot, J. L. (2017). Implementing a cloud platform for autonomous driving. arXiv preprint arXiv:1704.02696. Retrieved from: https://arxiv.org/pdf/1704.02696 [Retrieved on 28.09.2021]
Liu, S., Tang, J., Zhang, Z., & Gaudiot, J. L. (2017). Caad: Computer architecture for autonomous driving. arXiv preprint arXiv:1702.01894. Retrieved from: https://arxiv.org/pdf/1702.01894 [Retrieved on 28.09.2021]
Liu, Y., Bi, S., Shi, Z., & Hanzo, L. (2019). When machine learning meets big data: A wireless communication perspective. IEEE Vehicular Technology Magazine, 15(1), 63-72. Retrieved from: https://arxiv.org/pdf/1901.08329 [Retrieved on 28.09.2021]
Ma, Y., Wang, Z., Yang, H., & Yang, L. (2020). Artificial intelligence applications in the development of autonomous vehicles: a survey. IEEE/CAA Journal of Automatica Sinica, 7(2), 315-329. Retrieved from: http://www.ieee-jas.net/fileZDHXBEN/journal/article/zdhxbywb/2020/2/PDF/JAS-2019-0401.pdf [Retrieved on 28.09.2021]
Sharma, R. (2021). Big Data for Autonomous Vehicles. In Deep Learning and Big Data for Intelligent Transportation (pp. 21-47). Springer, Cham. Retrieved from: https://www.researchgate.net/profile/Rinki-Sharma/publication/350795005_Big_Data_for_Autonomous_Vehicles/links/609d141a4585158bf0a71105/Big-Data-for-Autonomous-Vehicles.pdf [Retrieved on 28.09.2021]
Tian, J., Chin, A., & Yanikomeroglu, H. (2018). Connected and autonomous driving. IT Professional, 20(6), 31-34. Retrieved from: https://ieeexplore.ieee.org/iel7/6294/8617716/08617766.pdf [Retrieved on 28.09.2021]
Xu, J., Zhu, S., Guo, H., & Wu, S. (2019). Automated labeling for robotic autonomous navigation through multi-sensory semi-supervised learning on big data. IEEE Transactions on Big Data. Retrieved from: https://par.nsf.gov/servlets/purl/10109320 [Retrieved on 28.09.2021]
Xu, W., Zhou, H., Cheng, N., Lyu, F., Shi, W., Chen, J., & Shen, X. (2017). Internet of vehicles in the big data era. IEEE/CAA Journal of Automatica Sinica, 5(1), 19-35. Retrieved from: https://ieeexplore.ieee.org/iel7/6570654/8232582/08232587.pdf [Retrieved on 28.09.2021]
Yamanaka, N., Okamoto, S., Yamamoto, G., Muranaka, T., & Fumagalli, A. 5G Network Application: Autonomous Driving Vehicle using Dynamic Migrated Edge Computer Function. Retrieved from: http://biblio.yamanaka.ics.keio.ac.jp/file/Yamanaka_ISACIT_2019.pdf [Retrieved on 28.09.2021]
Yaqoob, I., Khan, L. U., Kazmi, S. A., Imran, M., Guizani, N., & Hong, C. S. (2019). Autonomous driving cars in smart cities: Recent advances, requirements, and challenges. IEEE Network, 34(1), 174-181. Retrieved from: http://networking.khu.ac.kr/gallery/entry/document_srl/layouts/net/publications/data/Journal/2020/3.pdf [Retrieved on 28.09.2021]
Zec, E. L., Mohammadiha, N., & Schliep, A. (2018, November). Statistical sensor modelling for autonomous driving using autoregressive input-output HMMs. In the 2018 21st International Conference on Intelligent Transportation Systems (ITSC) (pp. 1331-1336). IEEE. Retrieved from: https://schlieplab.org/Static/Publications/2018-ITSC-AutoregressiveHMM.pdf [Retrieved on 28.09.2021]