Back to list
Hesai Technology Unveils EXT Sensor: The Industry's First Lidar Combining Spatial and Color Detection
Product LaunchLidarAutonomous DrivingHesai

Hesai Technology Unveils EXT Sensor: The Industry's First Lidar Combining Spatial and Color Detection

Chinese lidar manufacturer Hesai has announced the launch of its new EXT sensor, marking a significant technological milestone in the autonomous driving and robotics sector. Powered by the company's proprietary in-house Picasso chip, the EXT sensor is distinguished as the industry's first lidar solution to integrate both spatial and color detection capabilities. According to Hesai co-founder Sun Kai, this dual-functionality allows the sensor to provide a more comprehensive data set for environmental perception. The development highlights Hesai's commitment to vertical integration through its custom chip design, aiming to enhance the precision of object recognition by adding a color dimension to traditional 3D spatial mapping.

Tech in Asia

Key Takeaways

  • Innovative Dual-Detection: The EXT sensor is the first in the lidar industry to offer simultaneous spatial and color detection.
  • Proprietary Technology: The sensor is powered by Hesai's in-house developed Picasso chip.
  • Enhanced Perception: By combining color with spatial data, the sensor aims to provide more detailed environmental mapping.
  • Industry Leadership: Co-founder Sun Kai positions this as a pioneering move for the lidar market.

In-Depth Analysis

The Integration of Spatial and Color Data

Traditional lidar sensors primarily focus on measuring distances to create 3D point clouds, which represent the physical structure of the surroundings. Hesai's EXT sensor introduces a significant shift by incorporating color detection into this process. According to co-founder Sun Kai, this makes the EXT the industry's first lidar to bridge the gap between spatial awareness and visual color identification. This integration is designed to help autonomous systems better distinguish between objects that might have similar shapes but different visual characteristics, potentially improving the reliability of computer vision systems.

Powering Innovation with the Picasso Chip

A critical component of this technological advancement is the use of Hesai's proprietary Picasso chip. By developing its own silicon, Hesai maintains tighter control over the hardware-software integration required to process complex color and spatial data simultaneously. The transition to in-house chip design suggests a strategic move toward vertical integration, allowing the company to optimize performance and efficiency specifically for the EXT sensor's unique dual-detection requirements.

Industry Impact

The introduction of a color-detecting lidar sensor could redefine standards for environmental perception in the autonomous vehicle and robotics industries. By providing a richer data stream that includes both depth and color, Hesai is addressing one of the historical limitations of lidar—its inability to perceive visual information like traffic lights or road signs without the aid of secondary camera systems. This breakthrough may lead to more streamlined sensor suites and more robust object classification algorithms, reinforcing China's position in the global lidar market.

Frequently Asked Questions

Question: What makes the Hesai EXT sensor different from traditional lidar?

Unlike traditional lidar that only measures spatial distance to create 3D maps, the EXT sensor is the first to combine spatial detection with color detection in a single unit.

Question: What technology powers the new EXT sensor?

The EXT sensor is powered by the Picasso chip, which was developed in-house by Hesai.

Question: Who announced the launch of this new technology?

The announcement was made by Hesai, with co-founder Sun Kai highlighting the sensor's unique capabilities as an industry first.

Related News

Gemini API Tool Retrieval Preview Gives Agents Access to Hundreds of Tools With Fewer Tokens
Product Launch

Gemini API Tool Retrieval Preview Gives Agents Access to Hundreds of Tools With Fewer Tokens

Google AI Blog announced that Tool Retrieval is now in preview in the Gemini API. The feature is presented as a way to give agents access to hundreds of tools while using fewer tokens. The announcement pairs those two points: the breadth of tool access and lower token use. It does not explain how Tool Retrieval works, specify how token use was measured, or quantify the reduction. It also does not provide an exact tool count beyond describing access to hundreds of tools. The stated release status is preview, and the announcement does not give a timeline for general availability.

LangSmith Tool Gateway Enters Public Beta for Secure, Governed AI Agent Tool Use
Product Launch

LangSmith Tool Gateway Enters Public Beta for Secure, Governed AI Agent Tool Use

LangChain announced that LangSmith Tool Gateway is in Public Beta. The gateway handles credentials, identity, and access for every agent tool call, with policies, approvals, and traces. The announcement frames secure, governed tool use around the individual call: its focus is on how agents access tools, rather than on what those tools or agents can do. The update identifies what the gateway covers but does not explain how credentials are managed, how access decisions are made, when approvals apply, or what information traces contain. The Public Beta is the only release status stated in the announcement.

Google’s Gemini Decision 1 Picks Answers Instead of Writing Them Across Five Input Types
Product Launch

Google’s Gemini Decision 1 Picks Answers Instead of Writing Them Across Five Input Types

Google’s Gemini Decision 1 is a model designed to pick answers rather than write them, according to Shittu Olumide’s report for KDnuggets. It reads text, images, video, audio, and PDFs in a single forward pass and supports up to 262,144 input tokens per request. The central distinction is between what the model reads and what it does with that input: it accepts several kinds of material, but its stated task is answer selection, not answer writing. The token figure describes the maximum input per request, not how much the model outputs. The report does not explain how answers are presented for selection or provide results showing how well the model performs.