Civil Maps introduces ‘Fingerprint Base Map’ for AV localization and navigation

 Civil Maps has announced the availability of Fingerprint Base Map™, the industry’s most robust, scalable solution for precise autonomous vehicle localization and navigation.

Fingerprint Base Map™ allows self-driving cars to precisely determine their location in six degrees of freedom (6DoF), while evaluating the safest route to travel. This technology serves as the localization layer in the company’s HD Semantic Map.

Highlights of Fingerprint Base Map™

  • Compatibility with any sensor configuration
  • Compact map data format (100-300 kB/km) minimizes operational complexity and costs
  • Freedom to drive anywhere by downloading new base maps, on-the-go
  • Low-cost and low-energy ARM-based architecture
  • Localization in 6DoF within 10 centimeter precision providing trust-building Augmented Reality Maps™ for passengers
  • Robust performance under challenging weather conditions, road changes, and high speeds
  • Customizable, in-car software development kit for faster design cycles

Fingerprint Base Map™ leverages Civil Maps’ proprietary fingerprinting process to tackle some of the most significant obstacles related to operating autonomous driving programs at scale. Using the company’s novel algorithms, raw point cloud data collected from self-driving cars is transformed into lightweight voxel-based fingerprints, which vehicles use to find their location within a map. Unlike conventional solutions that are dependent on costly processing hardware, large storage arrays, and third-party data centers, Civil Maps’ Fingerprint Base Map™ is created and utilized entirely on-the-edge, in-vehicle.

With a data footprint that is up to 10,000 times smaller than traditional base maps, Fingerprint Base Map™ enables autonomous vehicle developers to radically reduce the costs associated with data processing, computing power, data storage, bandwidth, and energy consumption. For example, a conventional base map of San Francisco requires as much as 4 TB of in-car storage, while a voxel-based Fingerprint Base Map™ of the same area comprises only 400 MB. Purpose-built for portability, fingerprinted data can easily be transmitted over existing 3G and 4G cellular network infrastructure, enabling Edge Mapping™, Civil Maps’ process for map creation, map usage, and crowdsourcing.

Source: Civil Maps