The pursuit of virtual creatures in Pokémon Go may have inadvertently paved the way for a new generation of delivery robots. Niantic Spatial, the company behind the augmented reality game, is leveraging the vast geospatial data collected through player activity to enhance the navigation capabilities of autonomous robots designed for urban environments. This innovative application demonstrates how crowdsourced data, initially gathered for entertainment, can be repurposed to address real-world logistical challenges.
At the heart of this advancement is Niantic’s Visual Positioning System (VPS), a technology that goes beyond the limitations of traditional GPS. Whereas GPS relies on satellite signals, which can be unreliable in dense urban canyons, VPS uses computer vision to identify a device’s location by comparing images captured by its camera with a detailed map of the surrounding area. This map isn’t built by dedicated surveying teams, but rather through the contributions of Pokémon Go players who voluntarily scan their surroundings while playing the game.
The system functions by analyzing images and associated metadata – including position, direction, and movement – to create a highly accurate geospatial model. According to Niantic, they have trained over 50 million neural networks with more than 150 trillion parameters, enabling operation in over a million locations. This large-scale machine learning approach allows the system to “understand” a scene and connect it to millions of others globally, even inferring details from unseen angles.
This technology is particularly crucial for robots, which often struggle with GPS inaccuracies in urban settings. Signals can be reflected or blocked by buildings, tunnels, and overpasses, leading to localization errors of tens of meters. Niantic Spatial has partnered with Coco Robotics, a startup developing robots for short-distance deliveries, to integrate VPS into their autonomous systems. The ARCore Geospatial API, powered by Google’s VPS, allows these robots to pinpoint their location with greater precision, even in challenging environments.
The application of VPS extends beyond Pokémon Go. Google’s Visual Positioning System is also integrated into Google Maps, improving location accuracy for users. The underlying principle remains the same: leveraging visual data to create a more robust and reliable positioning system. Niantic’s approach, however, uniquely benefits from the scale and engagement of its player base, effectively crowdsourcing the creation of a detailed 3D map of the world.
The partnership with Coco Robotics represents a significant step towards realizing the potential of this technology. By providing robots with a more accurate understanding of their surroundings, Niantic Spatial is enabling the development of more efficient and reliable delivery services. This could lead to faster delivery times, reduced costs, and improved customer satisfaction in urban areas.
Looking ahead, the implications of this technology are far-reaching. Beyond delivery robots, VPS could be used to enhance the navigation capabilities of self-driving cars, improve the accuracy of mapping applications, and enable new forms of augmented reality experiences. As Niantic continues to refine its Large Geospatial Model, we can expect to see even more innovative applications emerge, blurring the lines between the physical and digital worlds.
What other applications do you envision for this technology? Share your thoughts in the comments below.
