Gasgoo Awards 2022 Applicant: Full Stack Fusion Computing Solution from JueFX Technology

For the Gasgoo Awards 2022, JueFX Technology’s Full Stack Fusion Computing Solution has entered the Top 100 Players of China’s New Automotive Supply Chain.

Gasgoo Awards 2022 Applicant: Full Stack Fusion Computing Solution from JueFX Technology

Photo credit: JueFX

Product: Full Stack Fusion Computing Solution

Description

2022 is the window period of intelligent driving from L2 to L3/L4. More and more car manufacturers are starting to develop intelligent mass production at a higher level, and the era of automotive intelligence has quietly arrived. With the improvement of LiDAR hardware technology and the decrease of mass production and cost at the vehicle regulation level, the high-level intelligent driving function promotes the mass production of LiDAR in the passenger car field. For passenger cars, using LiDAR as a sensor and merging other detection data is a new topic, and there is still a large technology gap across the industry in integrating detection and computing technologies. To solve the problem of mass production of high-level intelligent driving system (NOA) for passenger cars in the main engine factory, and to achieve safe and reliable high-level intelligent driving with the trend of superior LiDAR vehicles, JueFX Technology has launched the “Autopilot Full Stack Fusion Computing Solution”. This scheme can provide customized front-loading and loading positioning algorithms, multi-sensor fusion sensing algorithms and dynamic traffic information services for different scenarios and customers, meeting the needs of all phases of automated driving and upgrading vehicles from low-level driving assistant to NOA.

Gasgoo Awards 2022 Applicant: Full Stack Fusion Computing Solution from JueFX Technology

Photo credit: JueFX

Unique benefits

JueFX Technology’s Full Stack Fusion Computing solution can provide custom front-loading and rear-loading positioning algorithms, multi-sensor fusion perception algorithms and dynamic traffic information services for different scenarios and customers, meeting the needs of all stages of automated driving and upgrading vehicles from low-threshold assistant driving to NOA.

The scheme can provide pure vision-based fusion perception and fusion positioning services for the L2+ automatic drive system, which can adapt to the mainstream vision SOC and pose sensors. For high-level automatic driving, it can also integrate Huawei MDC, Horizon J5, Nvidia Orin and other high-performance platforms, and implement products and solutions such as fusion perception and fusion positioning according to different computing needs.

The core competency of this scheme is the fusion perception technology, which is also the core technology line that JueFX has adhered to since its inception. The fusion perception algorithm combines the original data from vision, point cloud, and millimeter wave, then performs 3D tracking to produce more accurate and complete perception results. At the same time, the behavioral trajectory of road users is accurately predicted using highly accurate maps and global end-of-road sampling.

Through extensive fusion sensing practices, JueFX has developed a number of point cloud algorithms, which can enable larger models to achieve more accurate fusion sensing of lidar + multi-channel vision on the built-in controller of mass production vehicles, including environmental awareness, situational awareness, and behavioral prediction.

JueFX Technology has also launched a high-precision fusion positioning terminal system “Minghong” for automated driving vehicles. The built-in environmental awareness algorithm, FPGA vehicle-level computer chip and other engineering capabilities can match features with high-precision maps on the vehicle and use visual and feature matching results to provide key information input for inertial navigation and satellite navigation. Especially in urban scenes with multiple paths, multi-layer overpasses or tunnels and other scenes where satellite navigation and inertial navigation are seriously disturbed, it can maintain accurate and stable output of vehicle positioning.

At the same time, JueFX Technology builds a data-closed loop for the target perception and prediction of automated driving by integrating vehicle perception and roadside data model, and provides full-stack technology services and empowerment for self-update data.

Application

Commercial vehicles/passenger cars; highway, urban roads, residential areas, etc.; lane change, long tunnel, under viaduct, AVP, etc.

Expectation

As a core technology that can greatly improve the decision-making speed and correctness of automatic drive system, “multi-sensor fusion perception” has become the top priority of industrial development. Through the key technological advances in integrating perception, JueFX Technology will continue to work with industry colleagues to build a prosperous ecology, continue to accelerate technological strength and help China’s autopilot mass production achieve “acceleration”.

Leave a Comment

Your email address will not be published. Required fields are marked *