DeepRoute.ai completes L4 driverless test in busy Shenzhen, China

The company tested Driver 2.0, a Level 4 production-ready autonomous driving solution

New video highlights navigating heavy traffic safely and efficiently

Photo: DeepRoute.ai

DeepRoute.ai, an international autonomous driving technology company, has announced the results of its latest fully driverless test of its Driver 2.0 Level 4 production-ready autonomous driving solution.

DeepRoute.ai released a video exhibiting a driverless vehicle retrofitted with the solution on Central Business District roads in Shenzhen, demonstrating its advanced capacity in complex and challenging traffic environments. It was the first legal driverless test in China — Shenzhen unveiled China’s first regulation on intelligent connected vehicles on July 6.

The fully driverless vehicle drove just under 14 miles in one hour, navigating through significant traffic and narrow lanes safely and efficiently. The vehicle:

• intelligently maneuvered around double-parked cars and counterflow e-scooters and pedestrians
• negotiated with oncoming vehicles to calculate the right timing and trajectory to pass busy intersections
• conducted multiple lane changes and unprotected left turns.

“The recent legislation permitting driverless robotaxis in Shenzhen is the first of its kind, a major milestone in advancing autonomous driving technology to wider and faster adoption,” said Maxwell Zhou, CEO of DeepRoute.ai. “As we advance our mission for commercial deployment of autonomous driving vehicles, we will collaborate with automakers to refine our L4 solution to make it as safe and efficient as possible.”

DeepRoute.ai has made significant improvements to achieve driverless capability, with both software and hardware meeting auto-grade standards. The safety mechanism was also upgraded to guarantee driverless safety on the road. In the case of long tail scenarios, the system will alert the remote monitoring center to intervene or take other safety measures.

The Driver 2.0 System

Driver 2.0 includes five solid-state lidar units, eight cameras and other sensors, and a computing platform integrated with its proprietary inference engine. The perception algorithm with sensor fusion can achieve precise object detection up to nearly 220 yards. The planning and control algorithm based on game theory can choose optimal routes and make decisions based on real-time situations when negotiating with oncoming vehicles and other road agents.

With its deep learning approach, the inference engine optimizes compute resources, allowing the algorithm to run on its low-cost and power-efficient computing platform effectively and stably. As a result, Driver 2.0 can be priced at $3,000 for automakers in mass production and the algorithm can work with 2 to 5 solid-state lidars for automakers’ customization needs.

The latest legal and regulatory framework is aligned with autonomous-driving industry developments and is considered the prelude to mass production and commercialization of autonomous-driving vehicles. DeepRoute.ai is working with automakers to mass produce consumer vehicles integrated with Driver 2.0, expected to be available for consumer purchase in 2025. It is also being integrated into robotaxi operations.

Photo: DeepRoute.ai