A Comprehensive Survey on Autonomous Driving Cars: A Perspective View
- PDF / 831,259 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 99 Downloads / 227 Views
A Comprehensive Survey on Autonomous Driving Cars: A Perspective View S. Devi1 · P. Malarvezhi1 · R. Dayana1 · K. Vadivukkarasi1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Over the past decades Machine Learning and Deep Learning algorithm played a vital part in the development of Autonomous Vehicle. It is indeed for the perception system to examine the environment around the vehicle and identify the objects such as pedestrian, vehicle and traffic signals, etc. Using this information, control system module can take necessary action to control the vehicle in terms of braking, speed, lane change or steering, etc. This paper focuses on the survey of machine learning algorithms and techniques applied in the design of autonomous driving system over a decade. Performance of each algorithm was analyzed in terms of prediction time and accuracy have been documented and compared. Keywords Machine learning · Deep learning · Autonomous driving · Object detection · Navigation
1 Introduction In the recent years, Automobile Industries compete with each other to launch the first fully autonomous vehicle. In future we will see lot of self-driving cars around the world. Many companies like GM, Ford, Toyota, Tesla, etc. are taking test drives in recent years. Many Automobile industries have invested for developing Autonomous Vehicle. GM paid out $581 million to obtain cruise automation in the year 2016. It was testing its vehicles in various cities across California, Arizona and Michigan. In 2017 Ford spent $1 billion into AI-start up Argo AI [1]. In 2019 Ford’s Argo AI had put $15 million for forming an autonomous vehicle research Centre. In [2] in 2015 Toyota invested $1 billion to develop autonomous vehicle. Volvo joint venture with Uber [3] spent $300 million to develop next generation self-driving cars. Hyundai also financed $30 million in self-driving car developer Aurora and invested $1.7 billion targeting for the highway driving in 2020 and urban driving in 2030. BWM with Daimler spent $250 million to work in the development of self-driving cars (BWM iNEXT) [4]. Many other automakers [5, 6] like Tesla, Fiat-Chrysler, Renault Nissan partnered with Waymo, Honda, Waymo LLC and other non-Automotive companies like Amazon, Apple, Baidu, * P. Malarvezhi [email protected] 1
Department of ECE, SRMIST, Chennai, India
13
Vol.:(0123456789)
S. Devi et al.
Cisco, Microsoft are working on developing full autonomous vehicle. Figure 1 shows that automobile industries have done lot of investment to develop fully Autonomous Vehicle (AV). The AV should provide more comfort and safety to the people than human drivers. In a recent report, Business Insider predicted that as many as 10 million self-driving cars would be on the road in early 2020. But this doesn’t seem likely. Autonomous vehicle require both the right legal and technological framework. Autonomous vehicles are equipped with a variety of sensors (Lidar, camera-360° & GPS, etc.) to perceive their surroundings. An accurate environmen
Data Loading...
