AEye, Seoul Robotics Offer Long-Range Perception System for Smart Traffic Systems

AEye's 4Sight M lidar will train on Seoul Robotics' SENSR 3D perception software for intelligent traffic systems.

AEye

The 4Sight M lidar is software-configurable and built on a modular architecture.

AEye Inc. and Seoul Robotics yesterday announced the integration of AEye's 4Sight M lidar sensor and intelligent detection and ranging platform with Seoul Robotics' SENSR 3D perception software. The companies said they will provide a complete system for long-range object detection, classification, and perception for intelligent traffic systems (ITS) by providing 3D perception for vehicles, cyclists, and pedestrians at distances beyond 300 m (984.2 ft.).

“ITS integrators typically don’t source individual sensors and software, instead relying on complete solution providers for smart mobility, traffic management, and automated tolling applications, and that’s exactly what we’re delivering,” said Akram Benmbarek, vice president of business development and strategic initiatives at AEye. “With the integration of the 4Sight M and SENSR, infrastructure developers and city operators using this solution will be able to evaluate data at high-risk intersections—including lane usage by vehicle type, vehicle counts per lane, accident rates, and near-misses—in adverse weather conditions and at distances beyond 300 meters.”

“In addition, traffic management facilities will be able to distinguish weaving motorcyclists during peak congestion and detect road debris or fallen cargo to alert utility vehicles as needed,” he said.

Industry analysts said they expect strong growth in the ITS market, driven by the desire to advance transportation safety, mobility, and environmental sustainability. Research firm Markets and Markets predicted that it will grow from $17.9 billion in 2020 to $36.5 billion by 2025. An H&Z study projected that the total available market for lidar in smart infrastructure will increase from $1.5 billion in 2025 to $14 billion in 2030.

AEye provides software-definable lidar

AEye said its lidar is software-definable, enabling systems integrators to address the unique sensing need of any ITS application simultaneously, from intersection management to autonomous vehicle (AV) infrastructure, automatic incident detection (AID) on highways, and automated tolling.

Founded in 2013, AEye provides adaptive sensors for vehicle autonomy, advanced driver-assistance systems (ADAS), and robotic vision applications. The Dublin, Calif.-based company's iDAR (Intelligent Detection and Ranging) system uses biomimicry and principles from automated targeting applications used by the military to scan the environment. AEye completed a SPAC merger and began trading on Nasdaq last month.

iDAR can enable faster, more accurate, and more reliable perception, claimed AEye. iDAR includes deterministic artificial intelligence to deliver industry-leading performance in range, resolution, and speed, said the company.

4Sight M trained for robust perception

Built on AEye’s iDAR platform, 4Sight M is an intelligent, adaptive, high-performance, and solid-state lidar that tailors its output to application-specific requirements, said the companies. Seoul Robotics has trained SENSR’s AI engine on the 4Sight M, whose data quality is maintained in daylight and at nighttime.

Coupled with 4Sight M’s long-range capability, the integrated system will be able to detect and classify objects in adverse weather conditions and at ranges not currently available on the market, said the companies.

It’s also the first and only sensor whose performance has been independently verified by a third-party testing organization. Active safety and automated vehicle technologies researcher VSI Labs has confirmed and published the 4Sight M’s range, resolution, and speed capabilities, said AEye and Seoul Robotics.

As a result, ITS integrators can benefit from reliable classification of motorists around the clock, even if some of the objects or obstacles are partially obstructed, fast-moving, or clustered together. Deep learning models enable SENSR to track more than 500 objects simultaneously with 10 cm (3.9 in.) accuracy, and weather-filtering algorithms allow tracking functionality in heavy rain and snow.

Seoul Robotics optimizes for ITS uses

“We’re extremely impressed with the adaptability of AEye’s 4Sight M sensor,” said William Muller, vice president of business development at Seoul Robotics. “It allows us to optimize output for different ITS use cases.”

“Similar to how our SENSR software uses AI to self-learn, AEye’s innovative architecture enables Seoul Robotics to process advanced feedback loops and optimized scan patterns,” he added. “This allows us to not only track motorists across all operational domains including roundabouts, four-way intersections, and toll booths, but also to now monitor high-speed traffic on divided highways, which has been historically challenging in the world of ITS.”

Founded in 2017, Seoul Robotics has developed its own proprietary software, which is compatible with nearly all lidar and 3D data sensors. The Seoul, South Korea-based company said its computer vision can increase accuracy and efficiency and ensure safety across a range of industries and applications.

AEye said that 4Sight M performance in real time can be found at its site. It and Seoul Robotics will offer demonstrations at the Intetra booth, No. B5431, during the ITS World Congress next week in Hamburg, Germany.


Email Sign Up

Get news, papers, media and research delivered
Stay up-to-date with news and resources you need to do your job. Research industry trends, compare companies and get market intelligence every week with Robotics 24/7. Subscribe to our robotics user email newsletter and we'll keep you informed and up-to-date.


AEye

The 4Sight M lidar is software-configurable and built on a modular architecture.


Robot Technologies