A Smarter Approach to Self-Driving Technology
On a Mission to Deliver the Benefits of Self-Driving—Safely, Quickly, and Broadly
- Safely – Embedded in our work and the foundation of our culture
- Quickly – We draw on our experience to move with speed and precision
- Broadly – Designed to serve several industries
We founded Aurora because we saw the opportunity to safely accelerate the adoption of self-driving technology. We’re building an ecosystem with powerful, independent, and robust technology—the Aurora Driver—at its core, and we’re partnering with automakers, transportation networks, and fleet management companies to deliver its benefits broadly.
It’s not just bold bets that change the world; it’s the combination of thoughtful people with deep experience and a strong plan. Our leaders have decades of experience pushing limits in engineering and robotics, building and shipping some of the world’s most successful products, and collaborating with legislators and communities across the country.
- Operate with integrity – We do the right thing, even if it delays our work or makes less money.
- Focus – We’re solving one of the most challenging problems of our generation, and we’ll get there by fostering a culture of depth, focus, and rigorous engineering.
- No jerks – We solve hard technical problems through discussion and collaboration. We don’t waste time battling over personalities and egos.
- Be reasonable – We expect each other to use good judgment and always have the best interest of the company and our partners in mind.
- Set outrageous goals – We set ambitious goals that demand commitment and push us to do our best work.
- Win together – We are building a technology and a company that will serve people and communities around the world. Our team’s diverse perspective and experience make us stronger and better reflect the world we live in.
The Aurora Driver – Self-Driving Technology Built to Move People and Goods
The Aurora Driver consists of sensors that perceive the world, software that plans a safe path through it, and the computer that powers and integrates them both with the vehicle. We’ve designed it to enable any vehicle type, from passenger sedans to class-8 trucks, to move safely and efficiently through the world.
The Aurora Driver’s hardware, software, and data services allow it to operate any passenger or commercial vehicle.
- Aurora Computer – The Aurora Computer acts as a central hub that connects our hardware and autonomy software and enables the Aurora Driver to seamlessly integrate with every vehicle type.
- Sensor Suite – Our custom-designed sensor suite gives the Aurora Driver a 360˚ view and the ability to track objects over 300 meters away, enabling our vehicles to stop for pedestrians, travel safely on highways, avoid obstacles, and more.
- Autonomy Software – Our groundbreaking software combines the best of machine learning with state-of-the-art engineering. The goal is to help the Aurora Driver to move through the world safely, comfortably, and predictably.
The Aurora Ecosystem
We’ll fully feel the benefits of self-driving technology through a multifaceted network of manufacturing, mobility, logistics, and fleet management partners. With this network of partners, we will provide the storage, maintenance, dispatch, routing, and on-road support needed to move people and goods safely and efficiently through the world. We call this network the Aurora Ecosystem.
- Vehicle platforms – Automotive partners will manufacture the vehicle platforms powered by the Aurora Driver. So far, we’ve integrated the Aurora Driver into sedans, SUVs, minivans, commercial vehicles, and Class 8 trucks.
- Logistics services – The Aurora Driver is also designed for the vehicles that move goods at high volumes between ports, depots, homes, and businesses. We’ll work with the companies that specialize in these logistic networks to make both middle-mile (between distribution centers) and last-mile (directly to homes and businesses) deliveries.
- Mobility services – Self-driving technology is poised to make a big impact in the efficiencies and safety of ridesharing and public transportation entities that specialize in moving people. In the future, the Aurora Driver will help operate these massive platforms and transit networks.
- Fleet management services – Our fleet management partners are important for delivering a commercial operation at scale by maintaining and servicing the vehicle fleets powered by the Aurora Driver.
We do things differently at Aurora. We’re developing self-driving technology for the future we believe is possible. We’re building the Aurora Driver through foundational systems that enable us to test, learn, and iterate quickly, making progress for long-term impact.
Virtual Testing Suite
- Codebase unit and regression tests – We don’t leave testing to the end of the development process. As code is written, we write both unit tests (e.g., seeing if a method to calculate velocity gives the right answer) and integration tests (e.g., seeing whether that same method works well with other parts of the system). New work must pass all relevant tests before we can merge it with the larger codebase, allowing us to identify and fix issues early.
- Perception tests – We use real-world log data to create a series of specialized perception tests. For example, say a bicyclist passes very close to one of our vehicles. Specialists would review that footage and then label things like object category (bicyclist), velocity (3 mph), etc. We would then use that “ground truth” to test how well new versions of perception software can determine what really happened on the road.
- Simulations – Simulations are virtual models of the world where we can change the parameters to test how the Aurora Driver would react in many permutations of the same situation. For example, we might vary the number of pedestrians at a virtual crosswalk. We routinely flag interesting events we see on the road and use them as inspiration for new simulations. We’ve even built custom tools to automatically extract information from log data, like how fast a pedestrian is walking, and plug it into our simulation models.
We’ve adopted a “smarter, not farther” approach to on-road testing of our self-driving technology. Instead of blindly pushing to drive more and more miles, we’ve continued to focus on collecting quality real-world data and on getting the most value out of every data point. For example, we amplify the impact of real-world experience by flagging interesting or novel events and incorporating them into our Virtual Testing Suite. One real-life situation can inspire tens or even hundreds of test permutations, all of which can be continually used to fine-tune existing capabilities.