{"id":2557,"date":"2019-11-14T14:27:16","date_gmt":"2019-11-14T19:27:16","guid":{"rendered":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/?p=2557"},"modified":"2026-03-26T12:04:19","modified_gmt":"2026-03-26T16:04:19","slug":"the-data-deluge-what-do-we-do-with-the-data-generated-by-avs","status":"publish","type":"post","link":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/the-data-deluge-what-do-we-do-with-the-data-generated-by-avs\/","title":{"rendered":"The Data Deluge: What do we do with the data generated by AVs?"},"content":{"rendered":"\n
This is part two of a seven-part series on the growing importance of automotive software. Click here<\/a> to read part one, or visit siemens.com\/aes<\/a> to learn more.<\/em><\/h5>\n\n\n\n

The automotive industry is becoming data-driven at an exponential rate as autonomous vehicles come closer to . For vehicles to sense, think, and act<\/a> you need state-of-the-art software and advanced computing systems to transform sensor data into decisions in real time. But, how much data are we talking about? Estimates of the amount of data an autonomous vehicle will generate vary greatly. The rate of data generation all depends on the automation levels implemented in the vehicle.<\/p>\n\n\n\n

The Society of Automotive Engineers (SAE) defines six levels of sophistication for autonomous vehicles, from zero to five (figure 1). A car with level two autonomy may feature active cruise control, a lane departure warning system, lane keep assist, and parking assistance. In total, this car requires about seventeen sensors to enable its driver assistance systems. A level five autonomous vehicle will have complete control over the driving task, requiring no human input. As a result, a level five car is projected to have more than thirty additional sensors of a much wider variety to cover the immense number of tasks an autonomous vehicle will need to perform. On top of the ultrasonic, surround camera, and long- and short-range radar sensors of a level two car, level five will require long range and stereo cameras, LiDAR, and dead reckoning sensors.<\/p>\n\n\n\n

\"\"
The SAE describes varying levels of vehicle automation, from assistance (left) through full autonomy (right).<\/figcaption><\/figure><\/div>\n\n\n\n

Lower-level automation requires fewer sensors, fewer network connections, and thus generates less data. Level 1 vehicles (think current driver assistance systems) require about 8 sensors, while a fully autonomous vehicle is expected to carry at least 32. Each of these sensor types generates data at different rates. In a recent presentation, Stephan Heinrich<\/a> (2017) from Lucid Motors shared some estimates on the raw sensor data generated by each type of sensor, summarized in the table below:<\/p>\n\n\n\n

Radar<\/strong><\/td>0.1-15 Mbit\/s\/sensor<\/strong><\/td><\/tr>
LIDAR<\/strong><\/td>20-100 Mbit\/s\/sensor<\/strong><\/td><\/tr>
Camera<\/strong><\/td>500-3500 Mbit\/s\/sensor<\/strong><\/td><\/tr>
Ultrasonic<\/strong><\/td><0.01 Mbit\/s\/sensor<\/strong><\/td><\/tr>
Vehicle motion, GNSS, IMU<\/strong><\/td><0.1 Mbit\/s\/sensor <\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

Based on these\nnumbers, Heinrich estimates that a vehicle at the lower end of the autonomous\nspectrum will produce about 3 Gbit\/s of data, which amounts to about 1.4\nterabytes every hour. At higher levels of autonomy, the total sensor bandwidth\nwill be closer to 40 Gbit\/s and approximately 19 terabytes per hour. According\nto the AAA American\nDriving Survey<\/a> (2019), the average\nAmerican spends 51 minutes driving every day. Over a whole year, that is 18,615\nminutes, the equivalent of almost 13 full days. Thus, at the data rates above a\nvehicle could generate 434 TB for lower level autonomy or up to 5,894 TB of\ndata for higher-level autonomy, in\njust one year! <\/p>\n\n\n\n

Based on these estimates, a single autonomous car will produce more\ndata in a year than the roughly 320 million monthly users of Twitter create (Kastrenakes,\n2019<\/a>; Matthews,\n2018<\/a>). Multiply this by millions of autonomous vehicles and you can\nget an idea of the crippling data crunch that will result from mainstream adoption\nof autonomous vehicles.<\/p>\n\n\n\n

The Data Management Dilemma<\/strong><\/h3>\n\n\n\n

With all this data, it becomes critical to find out how much of the\ndata is useful and how much can be deleted. Autonomous vehicle manufacturers\nwill need to make critical decisions regarding what data to keep, where it\nshould be processed, and how much and for how long it should be stored. In\naddition, automotive manufacturers will need to determine how to leverage the\ndata to deliver superior mobility experiences that are safer, personalized,\nconvenient, and affordable.<\/p>\n\n\n\n

Processing the terabytes of data from autonomous vehicles requires a huge amount of memory, powerful applications and processing power after transferring the data into the cloud. In some cases, however, the inherent latency of sending data to the cloud for processing, analysis, and receipt of instructions is unacceptable (figure 2). Autonomous vehicles cannot afford any latency for critical driving and safety functions. In an autonomous vehicle, a few milliseconds of delay can result in an accident and catastrophic loss of lives. Self-driving cars need to react in real time to changing road conditions; they can\u2019t simply come to a stop while waiting for instructions or recommendations from a distant cloud server analyzing data.<\/p>\n\n\n\n

\"\"
Figure 2: Autonomous cars often cannot accept any latency between sensing and action.<\/figcaption><\/figure><\/div>\n\n\n\n

Moving the processing power closer to the source of the data (the\nsensors on an autonomous car in this case) can dramatically reduce or eliminate\nlatency in communicating and processing data. This is known as edge computing, where\nthe process of analyzing data is executed near its source to reduce\ncommunication back to the central data center. In an AV, edge computing will be\nperformed by the vehicle\u2019s onboard computers and will be responsible for\ninterpreting real-time sensor data to safely guide the vehicle through a\ndriving environment. Edge computing will also determine what data needs to stay\nat the edge for immediate processing, and what data needs to be communicated to\nother parts of the network for deeper analysis.<\/p>\n\n\n\n

Fog Computing:\nDemystifying Complex Driving Scenarios <\/strong><\/h3>\n\n\n\n

While edge computing improves how autonomous cars sense, think and act in\nreal-time, it is not enough for all driving conditions. As AVs share the roads\nwith multiple human drivers, pedestrians, and cyclists under varying road and\nweather conditions, they will routinely need to identify safe solutions to significantly\ncomplex challenges. The onboard computers may provide quick responses, but they\nwill need help from more sophisticated systems to choose an optimal course of\naction in these difficult situations. <\/p>\n\n\n\n

A fog computing network may provide the answer by enabling processing\nwith machine learning and AI algorithms on a local area network (LAN). A fog\nnetwork provides a balance between the power of cloud computing with AI and\nmachine learning, and the immediacy of computation at the edge. A fog network\ncan also gather data from multiple vehicles, smart infrastructure, and other\nconnected devices, providing each vehicle with a clearer picture of the overall\ndriving environment. <\/p>\n\n\n\n

Fog computing creates low-latency network connections between autonomous\nvehicles and processing hardware that is more powerful than what an AV could\ncarry onboard. This enables the network to support more data and more\nsophisticated algorithms so AVs can make better decisions. This fog architecture\nalso requires less bandwidth compared to transmitting data to a data center or\ncloud for processing. It can also be used in scenarios where a data center or\ncloud cannot be accessed, meaning data must be processed close to where it is\ncreated. <\/p>\n\n\n\n

Fog network owners, such as automotive manufacturers, can also place\nsecurity features in a fog network. From segmented network traffic to virtual\nfirewalls, fog networks provide greater abilities to protect critical data and to\nkeep AVs secure. Fundamentally, the development of fog computing frameworks\ngives automotive OEMs more choices for processing data wherever it is most\nappropriate to do so.<\/p>\n\n\n\n

Some of the data produced by an AV as it operates will need to be\nstored for use at another time. In some cases, companies will only store data\nfor a certain amount of time, while others will demand that data be stored in\nperpetuity. For example, the automaker will wish to keep some operational data\nto use in legal proceedings in case the technology fails in the field. All of\nthis data has to be stored cost effectively, scaled, and available for\nanalysis. Whether stored in a data center or on a commercial cloud service, the\ndata must be secure and immediately accessible. Many major automotive companies\nare well aware of the importance of AV data management. For instance, Hyundai\ngenerates about 10 GB of data every second from its AV prototypes, but it only\nstores a portion of this data (Amend,\n2018<\/a>). Some is stored on the vehicle and off-loaded later to a\nserver, and some is uploaded to the cloud (Amend, 2018). <\/p>\n\n\n\n

Vehicle to X Communications<\/strong><\/h3>\n\n\n\n

While AVs are the main subject of discussion regarding the evolution of how we get from point A to point B, other technologies may prove even more vital.  Vehicular communications technologies, known broadly as vehicle-to-everything (V2X) communication, will form the foundation of future mobility systems. V2X technologies, such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I), enable real-time communication between vehicles, and between vehicles and their surroundings to provide a safe, convenient, connected, and affordable mobility experience (figure 3). Critically, these real-time communications allow vehicles to interact with each other and with the environment directly, in a way that humans cannot replicate. Such interaction can improve road safety, avoid traffic congestion, and reduce fuel consumption to enhance the overall mobility experience.<\/p>\n\n\n\n

\"\"
Figure 3: V2X communications enable vehicles to communicate with smart infrastructure, other vehicles, and external systems in real time.<\/figcaption><\/figure><\/div>\n\n\n\n

Here is a use case: an autonomous vehicle recognizes a fallen tree in\nthe road and applies the brakes to avoid a collision. The vehicle can simultaneously\nwarn vehicles behind it to decelerate, ensuring all vehicles safely come to a\nstop. The leading vehicle can even inform the local network of vehicles about\nthe tree, allowing them to avoid that specific road until it can be cleared. To\nmake this vision a reality, automotive manufacturers and suppliers are working\ntogether to develop vehicular communications based on cellular networks. The\ntechnology can use both today\u2019s mobile network and future 5G networks, enabling\ntransmission times in the millisecond range. <\/p>\n\n\n\n

A V2X infrastructure is necessary to realize level 4 and 5 autonomous\nmobility. This infrastructure can integrate with fog computing centers to\nfacilitate real-time data analysis, storage, and broadcast between many autonomous\nvehicles. As vehicles generate more and more data, properly managing and\ncommunicating that data will be crucial to successful operation.<\/p>\n\n\n\n

Automotive embedded software will be responsible for managing and extracting intelligence from this data. The sophistication of this software will need to rapidly increase to cope with the explosion of data that the connected, autonomous car will generate. Part 3<\/a> will take a deeper dive into the growing importance of automotive embedded software.<\/p>\n\n\n\n

References<\/strong><\/h2>\n\n\n\n

Amend, J. M. (2018, January 18). Storage almost full:\nDriverless cars create data crunch. Wards\nAuto<\/em>. Retrieved from https:\/\/www.wardsauto.com\/technology\/storage-almost-full-driverless-cars-create-data-crunch<\/a>\n<\/p>\n\n\n\n

Heinrich, S. (2017). Flash\nmemory in the emerging age of autonomy<\/em> [PDF document]. Retrieved from https:\/\/www.flashmemorysummit.com\/English\/Collaterals\/Proceedings\/2017\/Proceedings_Chrono_2017.html<\/a>\n<\/p>\n\n\n\n

Kastrenakes, J. (2019, February 7). Twitter keeps losing\nmonthly users, so it\u2019s going to stop sharing how many. The Verge<\/em>. Retrieved from https:\/\/www.theverge.com\/2019\/2\/7\/18213567\/twitter-to-stop-sharing-mau-as-users-decline-q4-2018-earnings<\/a>\n<\/p>\n\n\n\n

Kim, W., A\u00f1orve, V. & Tefft, B.C. (2019). American\nDriving Survey, 2014 \u2013 2017. AAA\nFoundation for Traffic Safety.<\/em> Retrieved from https:\/\/aaafoundation.org\/american-driving-survey-2014-2017\/<\/a><\/p>\n\n\n\n

Matthews, K. (2018, July 24). Here\u2019s how much big data\ncompanies make on the internet. Big Data\nShowcase<\/em>. Retrieved from https:\/\/bigdatashowcase.com\/how-much-big-data-companies-make-on-internet\/<\/a>\n<\/p>\n","protected":false},"excerpt":{"rendered":"

This is part two of a seven-part series on the growing importance of automotive software. Click here to read part…<\/p>\n","protected":false},"author":18471,"featured_media":2560,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"spanish_translation":"","french_translation":"","german_translation":"","italian_translation":"","polish_translation":"","japanese_translation":"","chinese_translation":"","footnotes":""},"categories":[1],"tags":[21,106,104,105],"industry":[120],"product":[],"coauthors":[],"class_list":["post-2557","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-autonomous-vehicles","tag-edge-computing","tag-embedded-software","tag-iot","industry-automotive-transportation"],"featured_image_url":"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/19\/2019\/11\/Fig-3-SMALL-V2V-scaled.jpg","_links":{"self":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts\/2557","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/users\/18471"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/comments?post=2557"}],"version-history":[{"count":5,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts\/2557\/revisions"}],"predecessor-version":[{"id":3279,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts\/2557\/revisions\/3279"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/media\/2560"}],"wp:attachment":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/media?parent=2557"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/categories?post=2557"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/tags?post=2557"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/industry?post=2557"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/product?post=2557"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/coauthors?post=2557"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}