AEye extends patent portfolio, creating industry’s most comprehensive library of solid-state LiDAR intellectual property

By | February 22, 2019

US: Artificial perception pioneer AEye has announced a significant expansion of its global patent portfolio, demonstrating its ongoing commitment to innovative solutions that promote safe and reliable vehicle autonomy. In addition to three patents previously announced, AEye has been awarded eight additional patents covering core components of AEye’s iDAR™ (Intelligent Detection and Ranging) perception system, including its solid-state MEMs-based agile LiDAR, fused HD camera, and software definable AI technology.

Six of the new patents relate to iDAR’s unique ability to enable software-defined frames and dynamic scan patterns. iDAR eliminates the constraints of the typical static point cloud by introducing dynamic scan modes designed to improve information acuity and minimize latency. With iDAR, scan modes can be combined and their data aggregated, enabling an AEye iDAR-powered device to be configured according to situational demands, such as when a vehicle moving at speed encounters congestion. This results in improved perception and time-to-reaction, while significantly reducing resource overhead.

Two of AEye’s recent patents focus on how the iDAR platform monitors and manages the laser energy of its agile LiDAR. iDAR deploys adaptive energy control on a pulse-by-pulse basis, allowing the system to automatically adjust the energy, tuning and shaping of each laser pulse. This advanced architecture allows for both the dynamic adjustment of scan patterns and the ability to adapt the laser energy for each pulse — enabling complete interference mitigation, eye safety and retro mitigation.

“AEye set out to create the optimal architecture for artificial perception, reinventing the core technologies that enable it,” said Aravind Ratnam, vice president of Products at AEye. “These patents represent AEye innovations that allow us to intelligently process data at its source, while using the minimal laser power to actively interrogate each frame. By optimizing and adjusting pulse power and direction in real-time, we are able simultaneously to focus on regions of interest, filter irrelevant data, and eliminate interference and spoofing, while delivering the highest levels of eye safety and retro mitigation.“

Conventional LiDAR systems are designed to provide basic search capabilities – passively capturing limited data and treating it all equally without distinguishing critical threats or objects in the scene. In contrast, AEye’s iDAR performs multi-modal intelligent search which can then acquire, pre-classify and track multiple objects quickly. Putting this intelligence in the sensor at the edge of the network produces better quality perception data that is more quickly, efficiently and accurately processed into actionable information. In addition, iDAR is a software-definable artificial perception system designed to be interoperable with existing LiDAR sensors and can be customized and extended as needed.

“The difference is our fundamental system architecture, which allows us to produce mobility solutions with industry leading range, resolution and update rate performance, while at the same time delivering ADAS solutions that are optimized for size, weight, power, and price,” said Joel Benscoter, head of Customer Success for AEye. “We can do this while ensuring both products will be under ASIL-B functional safety certification, to ensure they meet the automotive industry’s stringent safety standards. Nobody else can do this.”

AEye recently announced the AE110 for the mobility applications and theAE200 for ADAS solutions. The features enabled by the technologies covered in these patents will be available in both product lines.

The post AEye extends patent portfolio, creating industry’s most comprehensive library of solid-state LiDAR intellectual property appeared first on Geospatial World.

Read the original article

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.