Autonomous Cars Transform Smart Cities with Cutting-edge Tech

Advancements in AI, sensors, and connectivity propel autonomous vehicles in smart cities. Real-time data, 5G communication, and precise navigation redefine urban mobility, promising safer, efficient, and sustainable transportation.

NOTE: The views expressed here are solely those of the author and/or interview subject and do not represent positions of IEEE. Some references may require subscription to access content.

Examples of smart cities with autonomous car deployments (source: IoT|Times and DDS Wireless):

  • Phoenix, AZ, USA
  • Arlington, TX, USA
  • San Francisco, CA, USA
  • Stockholm, Sweden
  • The Woven City, Japan
  • Singapore
  • Hwaseong, South Korea

Autonomous vehicles can positively contribute to smart cities. As more of the world’s population moves into these smart urban environments [ 1 ], most people will rely on transportation that they no longer own. In the past, the concept of autonomous cars was confined to the realm of science fiction. Today, self-driving vehicles have become a tangible reality, revolutionizing the way we think about transportation. Beyond convenience, autonomous cars can play a pivotal role in the development of smart cities, creating an interconnected urban landscape. The evolution of autonomous cars along with technological advancements is driving progress in real-world examples of their deployment.

Autonomous cars have undergone a remarkable evolution over the years. What started as experimental projects in research labs, 1970’s Japan, 1980’s Germany, 1990’s US, has transformed into a developing industry reliant on a variety of engineering components. The journey from basic assisted driving features to fully autonomous capabilities has benefited from advancements in artificial intelligence, sensor technology, and connectivity.

One key enabler of autonomous driving is artificial intelligence (AI). Machine learning algorithms, powered by large datasets, allow vehicles to perceive and interpret their surroundings. Cameras, lidar, radar, and ultrasonic sensors act as the eyes and ears of autonomous cars [ 2 ], providing real-time data that enables them to navigate complex environments safely. In their paper, “Design of multifunctional autonomous car using ultrasonic and infrared sensors,” [ 3 ] published in the International Symposium on Wireless Systems and Networks (ISWSN), the authors present novel and simple circuit designs for performing different functions in an autonomous car. These designs have been practically implemented and tested by the authors as a part of their final-year engineering project.

Safety of autonomous vehicles is a critical aspect that requires aligned technology. “IEEE Standards for Assumptions in Safety-Related Models for Automated Driving Systems” [ 4 ] defines a minimum set of reasonable assumptions and foreseeable scenarios that shall be considered in the development of safety-related models that are part of an automated driving system. IEEE Vehicular Technology provides a vast resource on autonomous cars and other vehicle systems.

Technology is critical in developing the vehicles but also in creating a safe driving environment for the vehicle as well as those interacting with the vehicles, such as pedestrians, cyclists, and even animals.

Some of the autonomous vehicle technology advancements include:

Machine Learning and Neural Networks: 

Autonomous cars leverage sophisticated machine-learning algorithms and neural networks to process and analyze vast amounts of data. This enables them to recognize and respond to dynamic situations on the road, such as pedestrians, cyclists, and other vehicles.

LiDAR, Light Detection and Ranging, is a remote sensing technology that uses laser light to measure distances with high precision. LiDAR emits laser pulses at a target and measures the time it takes for the light to reflect back to the sensors.

Sensor Fusion:

To enhance the accuracy of perception, particularly in managing pedestrian avoidance, autonomous vehicles employ sensor fusion techniques [ 5 ]. LiDAR has found applications in autonomous vehicles and mapping of terrain and buildings.

Vehicle-to-everything (V2X) Communication:

V2X communication is a crucial aspect of autonomous driving in smart cities as vehicles must communicate with each other as well as with infrastructure elements such as traffic lights and road signs. Advancements in V2X communications make for safer driving environments [ 6 ].

Edge Computing:

In autonomous cars, edge computing ensures that critical decisions, such as braking or changing lanes, are made in real time. As noted in their paper, “Edge computing for autonomous vehicles – a scoping review,” [ 7 ] the authors point out that many of the existing solutions rely on sensors and computing equipment located on the vehicle itself. In this context, it is worth giving attention to the idea of relocating certain sensing and computing tasks to a network of roadside (“edge”) devices capable of communicating in real time with a plurality of vehicles, while reducing the onboard equipment.

5G Technology: 

The rollout of 5G networks plays a role in the development of autonomous vehicles within smart cities. 5G can enable seamless communication between vehicles and the surrounding infrastructure, contributing to safer and more efficient transportation systems [ 8 ].

As autonomous cars continue to evolve, they are becoming integral components of smart cities, contributing to a more sustainable, efficient, and interconnected urban environment. The technological advancements are driving the development of autonomous vehicles, including cars, buses, and trains, paving the way where commuting is safer and environmentally friendly.

Share this article:

[1] Ritchie, H. and Roser, M. (2018). Urbanization. Our World in Data. [online]

[2] J. Stähler, C. Markgraf, M. Pechinger and D. W. Gao, “High-Performance Perception: A camera-based approach for smart autonomous electric vehicles in smart cities,” in IEEE Electrification Magazine, vol. 11, no. 2, pp. 44-51, June 2023, doi: 10.1109/MELE.2023.3264920.

[3] A. Iqbal, S. S. Ahmed, M. D. Tauqeer, A. Sultan and S. Y. Abbas, “Design of multifunctional autonomous car using ultrasonic and infrared sensors,” 2017 International Symposium on Wireless Systems and Networks (ISWSN), Lahore, Pakistan, 2017, pp. 1-5, doi: 10.1109/ISWSN.2017.8250023.

[4] “IEEE Standard for Assumptions in Safety-Related Models for Automated Driving Systems,” in IEEE Std 2846-2022 , pp.1-59, 22 April 2022, doi: 10.1109/IEEESTD.2022.9761121.

[5] S. -G. Shin, D. -R. Ahn and H. -K. Lee, “Occlusion handling and track management method of high-level sensor fusion for robust pedestrian tracking,” 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), Daegu, Korea (South), 2017, pp. 233-238, doi: 10.1109/MFI.2017.8170434.

[6] Y. He, B. Wu, Z. Dong, J. Wan and W. Shi, “Towards C-V2X Enabled Collaborative Autonomous Driving,” in IEEE Transactions on Vehicular Technology, vol. 72, no. 12, pp. 15450-15462, Dec. 2023, doi: 10.1109/TVT.2023.3299844.

[7] C. Sandu and I. Susnea, “Edge computing for autonomous vehicles – A scoping review,” 2021 20th RoEduNet Conference: Networking in Education and Research (RoEduNet), Iasi, Romania, 2021, pp. 1-5, doi: 10.1109/RoEduNet54112.2021.9638275.

[8] F. Raissi, S. Yangui and F. Camps, “Autonomous Cars, 5G Mobile Networks and Smart Cities: Beyond the Hype,” 2019 IEEE 28th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE), Napoli, Italy, 2019, pp. 180-185, doi: 10.1109/WETICE.2019.00046.