You are currently viewing SemiWiki as a guest which gives you limited access to the site. To view blog comments and experience other SemiWiki features you must be a registered member. Registration is fast, simple, and absolutely free so please, join our community today!

Precisely positioned for autonomous success: Arm and Swift Navigation

AmandaK

Administrator
The promise of autonomous vehicles is driving a wave of innovation in the automotive industry, with the potential to redefine our concepts of mobility. However, in order to realize this future, new capabilities are required. As autonomous vehicles become more of a reality, it will be critical to the safety of the passenger for a self-driving car to be able to accurately determine its position in the world. Today’s news that Arm and Swift Navigation are partnering to bring a cost-effective, scalable and high-integrity positioning solution to developers of autonomous and connected vehicles is meant to promote just that – a safe, trusted and reliable passenger experience.

Autonomous prototype vehicles today are very dependent on their sensor suite to effectively determine what is going on around them. For cars to be able to make autonomous maneuvers safely, they need to know where they are with a high degree of accuracy.

Again, sensors coupled with very detailed high-definition maps can go a long way to figuring this out, especially when the route is well-known, the weather is clement, and roads and street signs are well marked. These specific conditions that the cars can operate under are known as the Operational Design Domains (ODD). As these ODDs broaden, maybe to travel farther, with less road definition or in difficult weather conditions (such as rain or snow), then another input is required to help the car position itself to make the correct road maneuvers.

This is where high-precision navigation signals will become a necessity, down to centimeter accuracy, and they will augment the other sensor inputs to give the vehicle an absolute position in the world. When coupled with HD maps, this will allow the car to “see” where it is regardless of the environment around it.

Navigation systems are commonplace on the cars of today, but these types of systems are only accurate to around 3-5 meters, which is not sufficient for lane-level positioning accuracy. Accuracy is not the only requirement here – high-integrity measurements are critical to meeting the strict safety requirements of autonomous vehicles, demanding full confidence in that positioning.

Delivering high-integrity, high-accuracy positioning for autonomous deployment at scale
Arm recognizes the importance of accurate positioning for its automotive ecosystem of partners to succeed in the autonomous future, and our partnership with Swift delivers just that.

We chose to partner with Swift because their Starling positioning engine is an Arm-based GNSS solution. This works in conjunction with a correction network of base stations to enhance the measurement accuracy of commercially available GNSS hardware solutions. This helps Swift enhance precision down to the centimeter. Starling is both a hardware proven and hardware agnostic, end-to-end solution, tunable for customer specific requirements and designed to be compatible with industry leading silicon makers who build their solutions on Arm. As well as its lane-level accuracy, it is also a high integrity solution with end-to-end redundancy and integrity monitoring services.


Arm and Swift Navigation


Enabling future automotive innovation
As we get closer to deployable autonomy, new technology innovations are a must. We must be able to prove that autonomous vehicles are safer at navigating our world than their human driver counterparts, and much of this will come down to proving the reliability of these technology innovations. At Arm we are broadening our automotive technology portfolio with our automotive enhanced products and our safety-ready portfolio, to help enable the safe deployment of the computing required to power autonomous and ADAS systems. We are complementing this technology innovation with a partner ecosystem that is also committed to this cause.

The partnership between Arm and Swift will enable the widespread, high-volume adoption of connected car applications, Level 2+ Advanced Driver Assistance Systems, and fully autonomous vehicles through its cost-effective scalability. This will pave the way for a safer and broader deployment of autonomy on our roads and brings with it the promise of a world where humans and machines can co-exist seamlessly.
 
Top