【XWBOO Industry News】 Compared with passenger cars, long-distance trunk transport trucks, because the high-speed transportation environment is closed and single, are more suitable for autonomous driving systems. In this area, Pony.ai has been laying out for a long time.
On November 1, Pony.ai released the third-generation autonomous truck software and hardware integration system.
The system solution is designed for the needs of trunk logistics business, and has been first applied to the first autonomous driving heavy truck product jointly created by Pony.ai and Sany Heavy Truck, which is produced by Yiji Zhika, a joint venture company established by the two parties, and delivered the first batch of smart trucks to Qingqiao Logistics on the same day.
According to reports, the sensor scheme of the third-generation autonomous driving truck system follows the multi-sensor deep fusion technology, with an overall number of 20 sensors, mainly using vehicle-level sensor devices, and has made breakthroughs in the fields of ultra-long-distance perception of automatic driving, 360° panoramic no blind zone, and long-tail scene processing.
Under the business requirements of high-speed driving and high load, the sensor solution consists of an ultra-long-range perception module consisting of one ultra-long-range camera, two long-range cameras, one mass-produced automotive-grade long-range lidar, and one long-range millimeter-wave radar, which can cover forward 200 meters to 1000 meters of obstacle detection.
Based on the truck's driving speed of 90 km/h, the ultra-long-range perception module allows the autonomous truck to accurately identify the faulty vehicle in front of it 30 seconds in advance, so as to calmly avoid obstacles.
At the same time, in order to ensure the safe recall of obstacles within 200 meters around the car body, in particular the identification of fallen cone barrels, potholes or throwing objects.
The solution includes a 360° panoramic perception module, which is composed of 2 360° lidars, 3 blinding lidars, 3 cameras, and 2 millimeter wave radars, which are distributed in the front and rear of the vehicle and on both sides, solving the industry pain points of the truck's close blind spot.
Similar to the passenger car system solution released this year, Pony.ai has also added a Sensor Cleaning System to the truck system.
The aerodynamic principle is integrated into the industrial design of the sensor contact surface, which effectively reduces the retention of dirt, reduces the impact of rain, fog, dust, ice and snow, sludge, etc. on the sensitivity of the sensor common in trunk line transportation, and can be applied to various working conditions.
In terms of software development, the new generation of system solutions adopts new sensor schemes and algorithm designs, so as to flexibly compatible with various types of freight hanging boxes; In addition, the algorithm system can accurately adjust the sensitivity of vehicle horizontal and longitudinal control according to the type of goods and transportation requirements to ensure the safe and smooth transportation of fragile products such as glass and tiles.
It is reported that Pony.ai was established in Silicon Valley in December 2016, with dual headquarters in Silicon Valley and Guangzhou, and is currently conducting autonomous driving project tests in Fremont, Irvine, California, and Beijing and Guangzhou, China.
Original title: Truck autonomous driving is coming! Pony.ai: It can identify the faulty vehicle ahead 30 seconds in advance.
