Self-driving technology company Deeproute.ai has released a video showcasing the results of a driverless test of its Driver 2.0 L4 autonomous driving solution in Shenzhen, China.
The video was released to demonstrate the solution’s ability to navigate congested and challenging traffic environments.
The self-driving car travelled just under 14 miles (22.5km) in one hour and manoeuvred around double-parked cars, e-scooters, pedestrians, negotiated with oncoming vehicles, passed through busy intersections and made 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 claims to have made significant improvements to achieve driverless capability, including an updated safety mechanism. In the case of long tail scenarios, the system is designed to send an alert to the company’s remote monitoring centre to intervene.
The solution, which Deeproute.ai says is production-ready, reportedly includes five lidars, eight cameras and other sensors and a computing platform integrated with its proprietary inference engine.
The company reports that its perception algorithm can achieve precise object detection up to nearly 220 yards (183m). The planning and control algorithm, which is based on game theory, is designed to find optimal routes and to make decisions based on real-time situations when navigating traffic.
The solution was produced to use deep learning to help it optimise resources.
Deeproute.ai said it is now working with automakers to mass produce consumer vehicles integrated with Driver 2.0 that will be available for consumer purchase from 2025, including use for robotaxi operations.
