AEye’s iDAR is designed to intelligently prioritize and interrogate co-located 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 products. Additionally, iDAR is capable of overlaying 2D images on 3D point clouds for the creation of True Color LiDAR. The introduction of iDAR follows AEye’s September demonstration 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 fundamental limitations of first generation spinning or raster scanning LiDAR technologies,” said Luis Dussan, AEye founder and CEO. “These first generation systems silo sensors and use rigid asymmetrical data collection that either oversample or undersample 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’s iDAR system uses proprietary low-cost, solid-state beam-steering 1550nm MOEMS-based LiDAR, computer vision, and embedded artificial intelligence to enable dynamic control of every co-located pixel and voxel in each frame within rapidly changing scenes.
MIT Technology Review adds: "there’s one point that there is no getting around: AEye’s device only has a 70° field of view, which means that a car would need five or six of the sensors dotted around it for a full 360 degrees. And that raises a killer question: how much will it cost? Dussan won’t commit to a number, but he makes it clear that this is supposed to be a high-end option—not competing with hundred-dollar solid state devices, but challenging high-resolution devices like those made by Velodyne. For a full set of sensors around the car, he says, “if you compare true apples-to-apples, we’re going to be the lowest-cost system around.”
PRNewswire: Ouster emerges from stealth mode and announces the launch of OS1 model LIDAR, and $27 million in Series A funding, led by Cox Enterprises. The 64-channel OS1 Lidar has begun shipping to customers, and is rapidly ramping up commercial-scale production at a price point approximately 85% below that of its competition (Costs $12,000, according to Ouster site).
The company was founded by CEO Angus Pacala, co-founder and former head of engineering of Quanergy, and CTO Mark Frichtl, a prior Quanergy Systems engineer who also spent time at Palantir Technologies, First Solar, and the Apple Special Projects Group. Pacala and Frichtl formed Ouster with the vision to create a high-performance, reliable, and small form factor LIDAR sensor that could be manufactured at a scale and price that would allow autonomous technology to continue its rapid expansion without the cost and manufacturing constraints currently present in the market.
"The company has maintained a low-profile for over two years – staying heads-down and focusing on getting the OS1 ready to ship," noted CEO and co-founder Angus Pacala. "I'm incredibly proud of our team for their hard work to produce the most advanced, practical, and scalable LIDAR sensor on the market, and we're very excited about the impact our product will have in autonomous vehicles and other applications in robotics," Pacala added.
Ouster's Series A funding will primarily be used for the manufacturing and the continued development of its next sensor designs. The company anticipates manufacturing capacity in the tens of thousands of sensors in 2018 based on its current product design, and Ouster's product roadmap supports continually improving resolution, range, and alternative form factors. Additionally, the new capital will support the company's expansion from approximately 40 employees today to 100 employees by summer 2018.
PRNewswire: Innovusion too comes out of the stealth mode with a Lidar featuring:
- Resolution: provides near picture quality with over 300 lines of resolution and several hundred pixels in both the vertical and horizontal dimensions.
- Range: detects both light and dark objects at distances up to 150 meters away which allows cars to react and make decisions at freeway speeds and during complex driving situations.
- Sensor fusion: fuses LiDAR raw data with camera video in the hardware layer which dramatically reduces latency, increases computing efficiency and creates a superior sensor experience.
- Accessibility: enables a compact design which allows for easy and flexible integration without impairing vehicle aerodynamics. Innovusion's products leverage components available from mature supply chain partners, enabling fast time-to-market, affordable pricing and mass production.
Chinese-language sites Ifeng and Kuwankeji publish more infor about Innovusion product:
"Innovusion also achieved a very important function, is the fusion of laser radar point cloud and camera video data at the hardware level, greatly reducing the sensor data fusion software processing time.
The company founders used to work for Velodyne and Baidu.
For the reflectivity of 10% of objects, their detectable distance of 100 meters or more.
There are still mechanical components in the product nowadays, which can be called hybrid solid-state radar. Innovusion's team considered design for manufacturing at design stage, and components used in the product are also mature components. In addition, the 1550 nm laser is used in the prototype."
No comments:
Post a Comment
All comments are moderated to avoid spam and personal attacks.