A new study by MIT researchers reveals that widespread adoption of self-driving vehicles could lead to massive carbon emissions, equivalent to the emissions profile of all the data centres in the world.

Led by Soumya Sudhakar, a graduate student in aeronautics and astronautics at MIT, the study explored the potential energy consumption of the powerful computers onboard autonomous vehicles and related carbon emissions. The researchers found that hardware efficiency would need to advance rapidly to keep computing-related emissions in check in the event self-driving vehicles were adopted widely.

The carbon footprint of data centres that house the physical computing infrastructure used for running applications is massive, currently accounting for about 0.3 percent of global greenhouse gas emissions – equivalent to the annual emissions output of Argentina. To study the potential footprint of autonomous vehicles, the MIT researchers built a statistical model and determined that 1 billion autonomous vehicles, each driving for one hour every day with a computer consuming 840 watts, would use enough energy to generate about the same amount of emissions as data centres currently do.

Therefore, to keep autonomous vehicle emissions lower than current data centre emissions, each vehicle must use less than 1.2 kilowatts of power for computing, which would require more efficient hardware.

“If we just keep the business-as-usual trends in decarbonisation and the current rate of hardware efficiency improvements, it doesn’t seem like it is going to be enough to constrain the emissions from computing onboard autonomous vehicles. This has the potential to become an enormous problem. But if we get ahead of it, we could design more efficient autonomous vehicles that have a smaller carbon footprint from the start,” says Sudhakar.

Sudhakar wrote the paper with her co-advisors Vivienne Sze, associate professor in the Department of Electrical Engineering and Computer Science (EECS) and a member of the Research Laboratory of Electronics (RLE); and Sertac Karaman, associate professor of aeronautics and astronautics and director of the Laboratory for Information and Decision Systems (LIDS). The study was published in IEEE Micro.

Modelling emissions

The researchers built a framework to explore the operational emissions from computers onboard a global fleet of electric vehicles that are fully autonomous. The model is a function of the number of vehicles in the global fleet, the power of each computer on each vehicle, the hours driven by each vehicle, and the carbon intensity of the electricity powering each computer.

The researchers modelled the workload of a popular algorithm for autonomous vehicles, known as a multitask deep neural network, and explored how much energy this deep neural network would consume if it were processing many high-resolution inputs from many cameras with high frame rates, simultaneously.

When they used the probabilistic model to explore different scenarios, Sudhakar was surprised by how quickly the algorithms’ workload added up.

For example, if an autonomous vehicle has 10 deep neural networks processing images from 10 cameras, and that vehicle drives for one hour a day, it will make 21.6 million inferences each day. One billion vehicles would make 21.6 quadrillion inferences. To put that into perspective, all of Facebook’s data centres worldwide make a few trillion inferences each day (1 quadrillion is 1,000 trillion).

“These vehicles could actually be using a ton of computer power. They have a 360-degree view of the world, so while we have two eyes, they may have 20 eyes, looking all over the place and trying to understand all the things that are happening at the same time,” Karaman says.

Also, if autonomous vehicles are used for moving goods, there could be a massive amount of computing power distributed along global supply chains. Additionally, the researchers’ model only considers computing, without taking into account the energy consumed by vehicle sensors or the emissions generated during manufacturing.

Keeping emissions in check

One way to keep emissions in check is to boost the efficiency of the computing hardware in autonomous vehicles so that the energy consumption is lower than 1.2 kilowatts. This requires more specialised hardware designed to run specific driving algorithms. However, vehicles tend to have 10- or 20-year lifespans, so the specialised hardware would need to be ‘future-proof’ to be able to run new algorithms.

In the future, researchers could also make the algorithms more efficient, so they would need less computing power, which could be a challenge.

“We are hoping that people will think of emissions and carbon efficiency as important metrics to consider in their designs. The energy consumption of an autonomous vehicle is really critical, not just for extending the battery life, but also for sustainability,” says Sze.

Source: MIT News

Image credit: Christine Daniloff, MIT