Full-stack visual intelligence company PerceptIn has launched a 1,000m visual perception module for semi-autonomous high-speed trains.
This module can also cover a 300m range, thereby making it suitable for universal deployment in industrial and commercial autonomous vehicles such as logistics trucks.
With safety as a focus, PerceptIn’s module’s stereo visual perception solution can accurately calculate distances and identify obstacles at` long distances. These characteristics enable autonomous driving systems to gain more reaction time so that they can prevent clashing with obstacles.
Through a collaboration with high-speed trains manufacturer CRRC, PerceptIn will deploy a customised long-range visual perception module on a high-speed railway system in China, where trains travel up to 300km per hour.
“With our 1,000m visual perception technology, we’ve created the longest range visual perception capabilities for high-speed rail while ensuring safety with critical functions.”
PerceptIn founder and CEO Shaoshan Liu said: “LiDAR sensors, which are commonly used in autonomous driving scenarios, suffer from a lack of detection range and semantic information, making them unsuitable for high-speed applications. Visual perception is currently the best solution that can be used in high-speed scenarios.
“With our 1,000m visual perception technology, we’ve created the longest range visual perception capabilities for high-speed rail while ensuring safety with critical functions such as obstacle avoidance and object detection.”
PerceptIn CTO Bo Yu said: “While developing our1,000m visual perception module, we ensured it remained flexible enough to be applied to any autonomous vehicle. Based on our ongoing discussions with global automotive manufacturers, we designed it to have a shorter 300m perception range, the common requirement for commercial vehicles such as trucks.
“To solve this challenging problem of producing reliable stereo visual sensors, we perfected seven different layers of technologies, including lens, image signal processing, image sensing, mechanical design, calibration, computing units and algorithms. The end result is a perception module that can be used for any autonomous vehicle scenario, including high-speed rail and commercial transport.”
The 1,000m visual perception module is based on the DragonFly Computer Vision Module, which allows outdoor autonomous vehicles and robots to have perception and localisation features. Therefore, the module can be tuned to meet the particular requirements of different vehicles.
The module is first being deployed on high-speed trains. Eventually, PerceptIn plans to deploy this technology on other commercial vehicles.