Hesai's Lidar Powers Didi and GAC Aion's L4 Robotaxi
Hesai Group has announced that its AT128 lidar technology will be used in the first mass-produced Level 4 (L4) Robotaxi, developed in collaboration with Didi Autonomous Driving and GAC Aion. In a press release, the company detailed that the Robotaxi will debut at the 2025 GAC Tech Day and GAC Intelligent Safety Summit in Guangzhou, with mass production slated for this year and initial deployment in 2026.
The Robotaxi model incorporates four Hesai AT128 lidar sensors, which are integral to its 360-degree blind-spot-free perception system. The AT128 offers a high resolution of 1200×128, capturing 1.53 million data points per second, and features a long detection range of up to 200 meters with a 120-degree field of view. This setup enhances the vehicle's ability to detect obstacles early, improving safety in both urban and highway environments.
This vehicle is the result of a strategic collaboration between Didi Autonomous Driving and GAC Aion, combining GAC Aion's safety redundancy platform with Didi's advanced hardware and software for autonomous driving. The Robotaxi integrates a total of 33 sensors, utilizing a heterogeneous sensor fusion architecture for real-time, 360-degree situational awareness.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Robotics Brief or Daily AI Brief.
Also, consider following us on social media:
More from Robotics
Oct 16 Rareview and Tuttle Launch Humanoid Robotics ETF HOID Oct 16 Element to Manage Waymo's Toronto Fleet for 2028 Launch Oct 16 RoboParty launches open source RP1 humanoid robot Oct 16 Jodell Robotics Unveils Dexterous Hand and Tactile Sensors Oct 16 Saab Completes Sea Trials of Large Uncrewed Underwater VehicleRobotics Brief
Weekly coverage of AI-driven robotics advances in industrial automation, autonomous vehicles, and robotic systems.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Delta and NVIDIA Collaborate on Level 4 Autonomous Driving
SAIC Roewe Starts Mass Production of JIAYUE 07 With Doubao AI
TIER IV and Partners to Hold Autonomous Driving Event for Tokyo Students
AITO Plans European Electric Vehicle Launch for 2027
Chery Plans AI and Green Technology Showcase for October Summit
Daily AI Brief: the AI news that matters, in your inbox.