Niantic Labs, the developer behind Pokémon Go, announced today via corporate blog that it would be opening its Augmented Reality (AR) platform to third-party developers. Called the Real World Platform, this technology is the driving force behind the company’s famous AR games.
Niantic CEO John Hanke wrote the following.
“We think of the Niantic Real World Platform as an operating system that bridges the digital and the physical worlds. Building on our collective experience to date, we are pushing the boundaries of geospatial technology, and creating a complementary, interactive real-world layer that consistently brings an engaging experience to users.”
The company, Hanke added, will be selecting a handful of third-party developers to begin working on the platform later this year. As Engadget noted, Niantic Labs is also the developer behind Ingress, and the upcoming Harry Potter: Wizards Unite.
According to Hanke, Niantic aims to bring this sophisticated technology to mobile devices, which will be a challenge, considering how limited in computing power most mobile devices are. Advanced AR, Niantic CEO wrote, requires a sophisticated understanding of reality. In particular, objects present in a given space. This is why the Real World Platform is building towards contextual computer vision, in order to ensure Niantic’s AR objects interact with real-world objects in unique ways.
The Niantic Real World Platform uses sophisticated algorithms to identify real-world objects, which are then added to an “AR vocabulary,” as Hanke put it. Meaning, once Niantic’s computer vision algorithm identifies objects and concludes what they are, putting them in context within a broader space, those objects are added to the vocabulary, making it larger, and the Real World Platform’s AR richer.
The biggest challenge of AR currently is the fact that AR objects are unable to meaningfully interact with other objects in a three-dimensional space, Niantic CEO noted, so the company’s London department has focused on this issue in particular. Niantic’s London researchers are using deep learning and computer vision to better understand three-dimensional space, enabling realistic interactions between AR and real-world objects.
The second biggest challenge in this arena, according to Niantic Labs CEO John Hanke, is multiplayer. In order to make the platform work across multiple users, the timing has to be perfect. In other words, more players mean more variables, and more variables mean several varying perspective. This is why Niantic Labs has developed proprietary, low-latency AR networking techniques.
Developers interested in working with Niantic’s newest tools can sign up via Niantic Labs‘ official website.