Autonomous cars promise to make driving safer, smarter and more efficient. Production of these vehicles requires high-performance computing capacity, along with seamless cyber security, and the ability to manage vast data sets. This is why organisations are taking advantage of the cloud, including cloud infrastructure’s reliability, scalability, and security. But what’s the best approach to ensure that connected transport is as safe as possible?
Training and testing
Autonomous cars strive to operate more safely than humans. Delivering on this ambition requires extensive modelling and testing, the ability to collect, store, and manage data and advanced machine learning (ML) techniques.
Toyota Research Institute (TRI) believes that accurately training autonomous cars requires trillions of miles of testing. It uses its fleet of test cars equipped with LiDAR sensors to record, collect, and analyse terabytes of data every day. Using Amazon Web Services (AWS), TRI manages this data and accesses the processing power required to train ML models quickly. By following similar models, more automotive businesses will accelerate the development of safer cars.
These machines need backing by reliable infrastructure with low latency and high availability
Enabling autonomous cars to make rapid, data-driven decisions will make our roads safer. These machines need backing by reliable infrastructure with low latency and high availability. They also need to analyse information, such as weather conditions, in real-time. Applying artificial intelligence (AI) allows the car to react swiftly and safely to road conditions.
Edge computing allows this core in-car technology to perform its in-car data crunching. When a lag can make the difference between a safe or dangerous response, autonomous vehicles can’t wait for data to process in the cloud. Organisations need to look for cloud providers with integrated edge solutions. These allow the analysis of mission-critical data at the source and reduce the cost of transmitting additional data to the cloud.
Security in the cloud
Cybersecurity is crucial when developing safety-focused autonomous cars. Each vehicle becomes a new endpoint that must be secured. Protection must be a top priority to ensure the security of driving controls and the data that runs through each vehicle.
Autonomous car producers are turning to the cloud to ensure cybersecurity updates and upgrades regularly happen. The best cloud providers also apply ML to manage tasks proactively including security assessments, threat detection, and policy management. By having security baked in, manufacturers can be confident that they have the solutions in place to detect new and emerging vulnerabilities, which will reduce harm to drivers.
When a lag can make the difference between a safe or dangerous response, autonomous vehicles can’t wait for data to process in the cloud
Connected cars, cloud and security
To drive adoption of autonomous cars, manufacturers must ensure they are secure and supported by robust infrastructure. Using the right cloud vendors is critical, enabling organisations to focus their resources on building differentiated automotive experiences, rather than managing IT infrastructure. Some providers offer a full suite of services to support Advanced Driver Assistance Systems (ADAS) and autonomous vehicle development and deployment. Ideally, a combination of scalable storage and compute capacity and support for deep learning frameworks will help accelerate testing and service development. At the same time, an agile platform helps businesses accelerate the pace of innovation, improve security posture and lower IT cost structure.
The opinions expressed here are those of the author and do not necessarily reflect the positions of Automotive World Ltd.
Steve Bryen is Senior Developer Advocate, UK and Ireland, at Amazon Web Services
The Automotive World Comment column is open to automotive industry decision makers and influencers. If you would like to contribute a Comment article, please contact email@example.com