Oser Communications Group

SEMA18.Nov2

Issue link: http://osercommunicationsgroup.uberflip.com/i/1038161

Contents of this Issue

Navigation

Page 62 of 79

Aftermarket Daily News 6 3 Friday, November 2, 2018 AEye Introduces Groundbreaking iDAR Technology AEye Inc, a robotic perception pioneer, introduced iDAR™, a new form of intel- ligent data collection that enables rapid, dynamic perception and path planning. iDAR (Intelligent Detection and Ranging) combines the world's first agile MOEMS LiDAR, pre-fused with a low- light camera and embedded artificial intelligence – creating software-defin- able and extensible hardware that can dynamically adapt to real-time demands. iDAR will deliver higher accuracy, longer range, and more intelligent infor- mation to optimize path planning soft- ware, enabling radically improved autonomous vehicle safety and perform- ance at a reduced cost. AEye's iDAR is designed to intelli- gently prioritize and interrogate co-locat- ed pixels (2D) and voxels (3D) within a frame, enabling the system to target and identify objects within a scene 10-20x more effectively than LiDAR-only prod- ucts. Additionally, iDAR is capable of overlaying 2D images on 3D point clouds for the creation of True Color LiDAR. Its embedded AI capabilities enable iDAR to utilize thousands of existing and custom computer vision algorithms, which add intelligence that can be leveraged by path planning software. The introduction of iDAR follows AEye's September demon- stration of the first 360 degree, vehicle- mounted, solid-state LiDAR system with ranges up to 300 meters at high resolution. "AEye's unique architecture has allowed us to address many of the funda- mental limitations of first generation spinning or raster scanning LiDAR tech- nologies," said Luis Dussan, AEye Founder and Chief Executive Officer. "These first generation systems silo sen- sors and use rigid asymmetrical data col- lection that either oversample or under- sample information. This dynamic exposes an inherent tradeoff between density and latency in legacy sensors, which restricts or eliminates the ability to do intelligent sensing. For example, while traditional 64 line systems can hit an object once per frame (every 100ms or so), we can, with intelligent sensing, selectively revisit any chosen object twice within 30 microseconds – an improvement of 3000X. This embedded intelligence optimizes data collection, so we can transfer less data while delivering better quality, more relevant content." AEye is also announcing the iDAR Development Partner Program for OEM customers, Tier 1 partners, and universi- ties interested in integrating iDAR into their vehicles. The company is demoing iDAR and announcing its automotive product suite at CES. Agile LiDAR A shortcoming of traditional LiDAR is that most systems oversample less impor- tant information like the sky, road and trees, or undersample critical information such as a fast-approaching vehicle. They then have to spend significant processing power and time extracting critical objects like pedestrians, cyclists, cars and ani- mals. AEye's iDAR technology mimics how a human's visual cortex focuses on and evaluates potential driving hazards. It uses a distributed architecture and at-the- edge processing to dynamically track tar- gets and objects of interest, while always critically assessing general surroundings. "Humans have an instinctive ability to respond to visual cues. By fusing intel- ligence within the data collection process, iDAR takes us a step closer to this instinc- tive response," said AEye Director of Software Jon Lareau. "AEye's iDAR is also an open and extensible platform, allowing us to integrate best-of-breed sensors to improve performance, increase redundancy, and reduce cost. Most impor- tantly, iDAR should help our customers streamline their development process and bring better autonomous vehicles to mar- ket, faster." AEye's iDAR system uses propri- etary low-cost, solid-state beam-steering 1550nm MOEMS-based LiDAR, com- puter vision and embedded artificial intelligence to enable dynamic control of every co-located pixel and voxel in each frame within rapidly changing scenes. This enables path-planning software to address regions and objects of interest, or to apply differentiated focus on select objects or obstacles. By adding intelli- gence to the sensor layer, objects of inter- est can be identified and tracked with minimal computational latency. For example, the system can identify objects and then revisit them even within the same frame giving the perception and path planning layers the ability to make calculations such as multi-directional velocity and acceleration vectors simul- taneously. This allows for faster and bet- ter predictability of behavior and intent. True Color LiDAR An additional limitation of traditional LiDAR is that it doesn't provide sufficient- ly detailed information on color or text, so it can't decipher color nuances in road striping, curbs, signage and traffic lights. iDAR's True color LiDAR instantaneously overlays 2D real-world color on 3D data, adding computer vision intelligence to 3D point clouds. Traditional LiDAR-based systems have to post-process, with inher- ent delays and computational drain due to registration and alignment challenges. True Color LiDAR's unique fusion enables absolute color and distance seg- mentation, and co-location with no regis- tration processing, so almost no computa- tional penalty. This enables much greater accuracy and speed in interpreting signage, emergency warning lights, brake versus reverse lights and other scenarios that have historically been tricky for legacy LiDAR- based systems to navigate. In addition, this approach dramatically expands the ability to do "enhanced training" for autonomous vehicles. Software-Definable and Extensible Hardware A key feature of AEye's iDAR platform is its software-definable hardware. iDAR adds three feedback loops that do not exist today: one at the sensor layer, one at the perception layer and another with path planning software. By enabling customiz- able data collection in real-time, the sys- tem is able to adapt to the environment and dynamically change performance based on the customer's/host's applica- tions and needs. In addition, it can emulate legacy systems, define regions of interest, focus on threat detection and/or be pro- grammed for variable environments, such as highway or city driving. This config- urability leads to optimized data collec- tion, reduced bandwidth, improved vision perception and intelligence and faster motion planning for autonomous vehicles. By designing its system from the ground up to accommodate multivariable customization through its software API, AEye optimizes functional control and puts OEMs and Tier 1s in the driver's seat. In addition, iDAR's system archi- tecture allows for remote updates of the firmware and software, which enables rapid prototyping without requiring hard- ware modifications. iDAR is just the latest milestone AEye has achieved in advancing next generation vision systems. In September, the company announced completion of a live metropolitan demonstration show- casing vehicle-mounted solid state com- mercial LiDAR with 360-degree cover- age. The demo broke new ground in enabling autonomous vehicles to collect real-time high density point clouds while simultaneously detecting objects up to 300 meters. Other recent company announcements include recent additions to executive team and investors. About AEye AEye develops advanced vision hard- ware, software and algorithms that act as the eyes and visual cortex of autonomous vehicles. Since its demonstration of its solid state LiDAR scanner in 2013, AEye has pioneered breakthroughs in intelli- gent sensing. The company is based in the San Francisco Bay Area, and backed by world-renowned investors including Kleiner Perkins Caufield & Byers, Airbus Ventures and Intel Capital. For more information, visit www.aeye.ai. Crash Point Systems Makes Auto Estimating Easier Crash Point makes taking photographs for estimating and appraisal on a vehicle much quicker and less problematic than ever before. "It is my strong belief this tool pro- vides education through communica- tion," says Justin Forkuo, the creator of Crash Point Systems. He developed this tool while seeking better methods for vehicle appraisal, than what is currently available, by forming a standard process for taking photographs. This resulted in the creation of a simple device designed with maximum efficiency in mind. Its one-handed ambidextrous design allows for greater mobility. The lightweight durable plas- tic polymer reduces fatigue, and resists wear during heavy usage. The five 'wands' are color-coded and use known industry terms to relay accurate infor- mation to all personnel involved in the repair process. Being a touchless method, there's no need to write or attach anything on the vehicle's surface – reducing prep work. The tool also aids those who have diffi- culty taking good pictures. "It's almost a natural tool we use in our shop when taking estimate pho- tos," says Gerald McNee, Owner of Ultimate Collision Repair in New Jersey who is one of the early adopters of Crash Point Systems. "The assorted colors make it easier to indicate exact- ly what needs to be done in the photos instead of second guessing it later when writing the estimate." DECKED Debuts System for Midsize Pickups DECKED is pleased to announce that its highly requested storage and organization system for midsize trucks is now available. After two years of engineering and manu- facturing preparation, DECKED is now offered for trucks like Tacoma, Colorado, Canyon and Frontier in North America as well as a wide variety of fitments for for- eign vehicles like Hi-Lux, Amarok, Navara and Ranger in the international market. DECKED for midsize trucks fea- tures the same 2,000lb system payload, 200lb load capacity per drawer and over- all system weight of around 210lbs as full-size vehicle versions. The new mid- size DECKED system is constructed from the same injection molded HDPE with a galvanized steel sub-frame in- molded for strength and rigidity. Like all DECKED systems, it is engineered in Detroit and made in the USA. The midsize product comes with numerous improvements over the exist- ing full-size product with weatherproof ammo can storage bins and other enhanced weatherproofing features. DECKED for midsize also features a "detent stop" on drawers which keeps drawers open on inclines. "We couldn't be happier or more excited with this new product, which has truly given us a chance to iterate and push the envelope on our engineering, design and manufacturing capabilities. The phones have been ringing literally since our company's inception for this fitment and it is quite satisfying to address that demand with what we believe will be a great product," said DECKED General Manager, Jake Peters. Learn more at decked.com.

Articles in this issue

Links on this page

view archives of Oser Communications Group - SEMA18.Nov2