April 18, 2024 - After four years, the 2024 Beijing International Automobile Exhibition will return from April 25 to May 4. As the first company in the industry to propose a general model for autonomous driving with integrated perception and decision-making, SenseTime will present the first demonstration of UniAD, a true end-to-end autonomous driving solution for mass production, as well as a product matrix of AI large model cockpit with multi-modal scene brain as the core and a new cockpit 3D interaction.
At present, general artificial intelligence is deeply integrated with the intelligent automobile industry, based on the company's years of technology accumulation to create a series of original ecological car vertical models, SenseTime will bring a number of AI large model products and functions covering intelligent driving and intelligent cockpit at the Beijing Auto Show, showing the public a new experience of flexible and adaptive, deeply personalized, safe and reliable, and humanistic care for the future of travel.
The industry's first universal autonomous driving model with integrated perception and decision-making, UniAD, made its debut on the car
At the end of 2022, SenseTime and its joint laboratory proposed the industry's first universal autonomous driving model with integrated perception and decision-making, UniAD, which won the best paper at the 2023 International Conference on Computer Vision and Pattern Recognition (CVPR) the following year, leading the trend of end-to-end autonomous driving in academia and industry.
Recently, Tesla began to push the FSDV12 version based on end-to-end algorithms to users, which has attracted wide attention in the industry. At this year's Beijing Auto Show, SenseTime will also bring UniAD, a true end-to-end autonomous driving solution that integrates perception and decision-making for mass production, and show the results of UniAD's real-vehicle road demonstration to the public for the first time.
With the continuous evolution of autonomous driving technology, rule-based intelligent driving solutions require multi-sensor fusion perception and a large amount of resources to deal with complex road conditions such as unprotected left turns and mixed traffic between people and vehicles. The ¬SenseTime UniAD solution can cope with the complex environment of urban areas through data learning and driving without the visual perception of cameras and the need for high-precision maps. Not only that, on rural roads without a center line, which are difficult to break through with traditional solutions, UniAD can also drive freely, completing a series of difficult operations including turning left on the bridge at a large angle, avoiding vehicles occupying the road and construction areas, and bypassing running pedestrians, so as to truly "drive like a human".
In order to enhance the interpretability and interaction capabilities of the end-to-end autonomous driving solution, relying on the multi-modal large model, SenseTime has developed a new generation of autonomous driving large model DriveAGI, which is suitable for a wider range of scenarios, higher performance, lower threshold, and can be perceived, interacted with, and trusted in terms of experience. As the next generation of autonomous driving technology, DriveAGI will also be previewed during the auto show.
SenseTime creates a multi-modal scenario brain with keen insight, deep thinking, and efficient execution
Recently, Xiaomi SU7, which has attracted much attention, has begun to bring AI large models into the cockpit. SenseTime has created an AI large model cockpit product matrix with the "multi-modal scene brain" as the core, injecting powerful environmental understanding, logical thinking, and content generation capabilities into the intelligent cockpit through the combination of multi-modal large models, large language models, and Wensheng graph models.
SenseTime's AI model will be able to recommend restaurants that meet users' preferences based on geographical location, introduce external natural scenery that users are interested in, and recommend high-quality scenic spots. Not only that, based on the powerful multi-modal perception capability, vehicles equipped with SenseTime's Jueying solution can accurately perceive and recognize information outside the vehicle, including the models of surrounding vehicles, landmark buildings, etc., and provide more accurate and comprehensive content for the cabin personnel in the form of voice, pictures or videos, etc., to help users understand and master the external environment information.
With the multi-modal scene brain as the core, SenseTime has promoted the mass production of a series of AI large-scale model cockpit products with panoramic perception, active care and creativity, such as "Travel Doctor", "Magic Brush", "Children's Companion" and other innovative functions, so that the public will be able to experience a new experience of deeply personalized and humanistic smart travel at the SenseTime booth.
VisionPro "gets on the car with the naked eye", and SenseTime's world's first 3D line of sight interaction in the cockpit will be unveiled soon
In 2023, the advent of AppleVisionPro will give people a taste of the charm of 3D interaction, and SenseTime will bring two new cockpit 3D interactive demonstrations at the auto show through its deep technical research and development strength and efficient innovation and iteration efficiency: 3DGaze high-precision gaze interaction and 3D dynamic gesture interaction.
As the world's first intelligent cockpit technology that can interact with on-screen icons through gaze positioning, SenseTime's 3DGaze high-precision gaze interaction will allow users to control the central control icon through their eyes. 3D Dynamic Gesture Interaction is an industry-leading intelligent cockpit technology that supports dynamic gestures and hand micro-motion recognition, allowing users to interact with various cockpits through gestures "in the air".
The two in-cabin 3D interactive functions of SenseTime cooperate with each other, just like "VisionPro" naked-eye on the car, creating a natural interactive experience that is more in line with human intuition for users.
At the time of the collision and integration of AI large models and the automotive industry, SenseTime will give full play to the leading technological advantages and product innovation capabilities accumulated over the years, and continue to inject new vitality into the intelligent automobile industry. From April 25th, welcome to visit SenseTime's booth to explore the future travel mode of smart cars in the AGI era.
SenseTime Booth: China International Exhibition Center (Shunyi Pavilion) E1-W09.
###
About SenseTime - Inspire AGI's creativity and lead smart cars into the future
SenseTime is a core technology partner that accelerates the entry of smart cars into the AGI era.
Relying on the deep computing power reserves of SenseTime's large device, the native automotive vertical model, the leading software and hardware architecture and the four technical bases of the full-stack data production pipeline, SenseTime has deeply integrated the most cutting-edge artificial intelligence technology with the automotive industry, built a general artificial intelligence (AGI) technology architecture of the trinity of driving, cockpit and cloud, and created a diversified product system of intelligent driving, intelligent cockpit and AI cloud, and is committed to providing everyone with flexible and adaptive, deeply personalized, safe and reliable, The future of mobility with humanity.
Starting from China, SenseTime's business has been deployed globally, and R&D centers have been set up in China (Shanghai, Beijing, Shenzhen, Guangzhou), Germany, Japan and other places.
As of December 2023, SenseTime has cooperated with more than 30 domestic and foreign car companies such as Honda, BYD, Great Wall, GAC, Hongqi, Zeekr, Nezha, Chery, and NIO, covering more than 90 models and delivering a total of 1.95 million smart cars.