Despite commendable efforts and progress in autonomous vehicles (AVs) by companies like Waymo and Alphabet, their commercialization has not been achieved yet, because no single technology has been able to provide comprehensive answers to different challenges posed by driverless cars. Reliable and secure communication of AVs with their surrounding environment including traffic signals, other vehicles, pedestrians, and lanes is the foremost requirement for their eventual commercialization. Quantum technologies may offer a ground-breaking solution for enhancing AV communication systems. By rapidly processing large amounts of data, they can resolve AV issues related to navigation, perception, and secure connectivity.1
Image Credit: AlinStock/Shutterstock.com
Quantum Computing and AV Navigation
Quantum computing uses qubits for information processing instead of the traditional binary bits, which can be generated physically by controlling electron spin.1 While bits in classical computing can store only one value (0 or 1) at a time, a qubit can store multiple values simultaneously.2 Qubit properties of superposition, interference, and entanglement enable computing power that is exponentially faster than conventional computing algorithms, and at lower costs.
A shift to electronically controlled AVs from mechanical systems requires quick decision-making using a robust computing mechanism. It involves collecting input data for decision-making from multiple sources, ensuring the data is secure and free from external influences, quickly arriving at the decision, and communicating the data between different recipients. 2 With its ability to process vast amounts of data, quantum computing can accelerate learning in AV navigation. It can help in multimodal fleet-route optimization and large-scale traffic flow, which is currently subject to data loading issues.1
The navigation system in AVs needs to first find the route options available to reach a destination. It also requires monitoring dynamic changes in the environment like obstacles on the way due to construction activity or an event taking place, a sudden surge in traffic, etc. Thus, complex navigation algorithms exchanging huge amounts of data are essential for efficient AV navigation. Quantum computers can handle multiple data values from vehicle sensors simultaneously in real time, thereby improving navigation and decision-making processes.2
Quantum Encryption for Secure Vehicle-to-Vehicle Communication
It is critical for driverless vehicles to have a secure communication system, for the safety of passengers, other vehicles, and pedestrians. A breach in the vehicle’s safety system can be life-threatening, and cause material losses for the manufacturer. Most of the current secure data transfer depends on Rivest-Shamir-Adelman (RSA) encryption, which can be broken by quantum factorization. Quantum encryption provides better alternatives for secure vehicle-to-vehicle communication like quantum key distribution (QKD).1 QKD involves the generation of secure encryption keys from the quantum properties of photons (like polarization states) and then distributing them for use.3
Vehicle-to-vehicle communication is an important aspect of AVs involving wireless data transfer between different vehicles. This helps to identify the potential hazards near the vehicle and understand conditions in the journey ahead. It is important to protect AV communication systems from cyber threats like denial-of-service attacks, spamming, message alteration, message spoofing, malware, and eavesdropping. Because of the dynamic and time-sensitive nature of communication in AVs, high-performance security like QKD becomes essential, as it ensures a statistical security guarantee even in the presence of eavesdroppers.3
Quantum Sensors for Enhanced Vehicle Perception
One of the key elements of AV development is estimating intentional behavior and interacting with other vehicles and human traffic participants. Human behavior on the roads can be uncertain and irrational. Thus, AVs need to be equipped with effective cognitive and decision-making capabilities. The currently prevalent deep learning methods to enhance perception and decision-making in AVs require massive big-data sample training. Alternatively, quantum theory helps in the correct understanding of the unpredictable behavior of human traffic participants and enables making the right interactive behavior decisions.4
The commonly used localization systems in AVs are global positioning systems (GPS), Light Detection and Ranging (LiDAR), radar, cameras, and ultrasonic sensors. While GPS struggles with precision in dense areas, LiDAR does not work properly in adverse weather conditions. Radar lacks fine details, cameras require proper lightning, and ultrasonic sensors are limited to low-speed applications. In such a scenario, quantum sensors provide highly accurate measurements of time, frequency, and magnetic fields, which can significantly improve perception and localization in AVs. Quantum accelerometers and gyroscopes can further enhance the accuracy and reliability of the surrounding data without the need for external signals like GPS.5
Challenges and Solutions in Quantum Integration
Quantum computing has its inherent challenges as it needs atomic level stability (ultracold and noise-free environment), and any interference can disrupt the computing process if it impacts the quantum particles.1 Scientists are trying to develop means to control and manipulate qubits for computing without the need for cryogenic temperatures.2 Additionally, quantum computers are very sensitive and still have high error rates. Since quantum algorithms don’t work on today’s classical computers, integrating them smoothly into the AV value chain is a challenge.1
Another difficulty in quantum integration with AVs is its novelty and relatively small emergent market. Quantum computing depends on other supporting technologies like machine learning (ML), artificial intelligence (AI), big data, and cloud computing.1 The currently available noisy intermediate-scale quantum computers can only run limited algorithms due to the limited number of qubits and lack of error correction. Efficient quantum integration in AVs requires collaboration between tech giants, academic institutions, government laboratories, and start-ups involving quantum software developers.1
Conclusion and Future Perspectives
Quantum technologies in autonomous driving are expected to parallelly solve optimization issues and process data for ML and AI algorithms. Quantum computing can turn out to be a hybrid solution, working in tandem with classical computers to enhance AV features like high local traffic optimization and improved vehicle routing.1 Until quantum technologies hit the commercial stage, the interface between quantum and classical computers will need more work.2
For large-scale AV integration, quantum computing as a service may become more common thanks to its cost-effectiveness and scalability.2 The widespread adoption of AVs is possible only through improved safety and reliability features, which in turn depend on the accuracy and robustness of the computing technologies supporting them. Integrating quantum computing with AI, ML, advanced sensors, 6G communication, and other existing technologies can lead to a future of accurate and intelligent autonomous driving, making roads safer and transportation more efficient.5
References and Further Reading
- JEREMY, C. J. J. (2022). Autonomous vehicle innovation and implications on adoption, liability and policy, using quantum technologies and artificial wisdom. Singapore Management University. https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=1446&context=etd_coll
- Ayisha. (2021). How Quantum Computing is shaping the Future of Urban Mobility. SAEINDIA. https://saeindia.org/how-quantum-computing-is-shaping-the-future-of-urban-mobility/
- Fowler, D. S., Maple, C., & Epiphaniou, G. (2023). A Practical Implementation of Quantum-Derived Keys for Secure Vehicle-to-Infrastructure Communications. Vehicles, 5(4), 1586–1604. https://doi.org/10.3390/vehicles5040086
- Song, Q., Fu, W., Wang, W., Sun, Y., Wang, D., & Zhou, J. (2022). Quantum decision-making in automatic driving. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-14737-2
- Tao, X., Meng, P., Zhu, B., & Zhao, J. (2024). Navigating the future: A comprehensive survey of localization systems in autonomous vehicles. Metaverse, 5(1), 2627. https://doi.org/10.54517/m.v5i
Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.