Nullmax

Last week, we were pleased to receive the "Best Technical Practice Award" from Gasgoo 盖世汽车 at the 6th Gasgoo Awards for our platform-based autonomous driving solution, MaxDrive. This recognition highlights the excellence of our products. https://lnkd.in/g6YmQpSF #Nullmax #GasgooAwards #Innovation #AutonomousDriving #AI #MaxDrive

Driving like a human and making human-like decisions have long been considered the ideal direction for autonomous driving and robotics. At Nullmax, we believe that for machines to truly understand and interact with the physical world, the ability to "see" is essential. Nullmax's vision-only technology, driven by AI and cameras, enables machines to recognize colors, shapes, textures, and spatial relationships just like humans, allowing them to accurately perceive their surroundings and opening up new possibilities for the future of autonomous driving and intelligent robotics. Discover how our vision-only technology enables autonomous driving and robotics to explore the world. Read the full article to learn more: https://lnkd.in/gVuRZ77q #AutonomousDriving #AI #ComputerVision #Innovation #Robotics #FutureMobility #Technology #ArtificialIntelligence #Nullmax

How does the world look through the "eyes" of an autonomous vehicle (AV)? Meet Nullmax's vision-only AV, equipped with 7 cameras and powered by our end-to-end autonomous driving model. In this video, you'll see: - Real-time generation of local maps - Superior obstacle detection - Planned driving trajectories Nullmax's end-to-end autonomous driving model empowers vehicles to handle any driving scenario, supporting various sensor setups and easy deployment, while operating without geographical restrictions. #AutonomousDriving #VisionOnly #AI #MachineLearning #Innovation #Technology #E2E #Nullmax

On July 16th, #Nullmax officially unveiled the next generation of autonomous driving technology, Nullmax Intelligence (NI). NI features vision only, map-free, and end to end multimodal capabilities to advance automotive intelligence. Moreover, NI utilizes brain-inspired neural network for safety. To this end, the NI system capable of outputting visual perception results, scene descriptions, and driving behavior information. More details about Nullmax Intelligence: https://lnkd.in/gfAntgN4 #nullmax #AI #nullmaxintelligence #NI #autonomousdriving

See you tomorrow at the Nullmax 2024 Tech Conference.

When #AI enables machines to see, understand, and integrate into the physical world through vision like humans do, what does this mean for autonomous driving? How can we imagine the future of intelligence? Join us on July 16th for the #Nullmax 2024 Tech Conference to find out. #Nullmax #AI #AIGC #AutonomousDriving

Nullmax's latest research, "SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras," has been accepted at #ECCV In this paper, Nullmax's research team presents a single model termed SimPB, which simultaneously detects 2D objects in the Perspective view and 3D objects in the BEV space from multiple cameras. Key Contributions: 1.    Proposing a novel unified query-based detector that can simultaneously detect 2D objects in the perspective view and 3D objects in the BEV space from multiple cameras. 2.    Introducing a hybrid decoder for 2D and 3D object detection, utilizing a Dynamic Query Allocation and an Adaptive Query Aggregation module to continuously update and refine the interaction between 2D and 3D results in a cyclic 3D-2D-3D scheme. 3.    The approach achieves promising performance in both multi-view 3D object detection in the BEV space and 2D box detection in image space on the nuScenes dataset. Read the full paper here: https://lnkd.in/g6iUQ3dS #AutonomousDriving #MachineLearning #ComputerVision #Innovation #ECCV2024 #Nullmax

QAF2D: Nullmax Earns #CVPR 2024 Recognition for Innovative 3D Object Detection #Nullmax Perception Team's research paper on the QAF2D method was accepted at CVPR 2024! This paper highlights several key contributions: • The team propose generating 3D query anchors from 2D bounding boxes so that the results of the more reliable 2D detector can be directly used to improve 3D detection performance. • The team shares the image feature extraction backbone between the 3D and 2D detectors by visual prompts for efficiency and successfully train the network in two stages. • Consistent performance improvement is achieved on the nuScenes dataset when the proposed #QAF2D is integrated into three query-based 3D object detectors, and it shows the effectiveness and generalization ability of the proposed approach. Explore more details about the paper: https://lnkd.in/gHBxQFX4 #CVPR #AutonomousDriving #AI #Innovation #Technology #Nullmax #CVPR2024

At Nullmax, we've been exploring autonomous driving by combining advanced AI software with hardware to create intelligent vehicles capable of performing diverse tasks in real-world environments. Unlike smartphones, cars can become powerful super terminals due to their larger energy capacity, space, sensors, and chips, enabling more complex AI applications. Autonomous driving represents a prime field for AI applications, and the technologies we are developing at #Nullmax are poised to have wide-ranging applications and immense value in the future. Stay tuned for more updates! #AutonomousDriving #AI #Innovation #Technology #Nullmax

Explore Autonomous Driving with MLF: More Efficient and Easier to Scale-Up   In recent years, autonomous driving has made remarkable strides. However, many systems struggle with generalization and unseen scenarios. To deal with these challenges, Nullmax introduces the Machine Learning First (MLF) strategy.   Key Benefits of MLF: - Automation and Intelligence: ML reduces the need for manual programming. - Adaptability: Models refine themselves with new data. - Efficient Big Data Processing: Quick analysis for real-time decision-making. Details about MLF: https://lnkd.in/g2JrRiTh   #AutonomousDriving #MachineLearning #AI #Innovation #Nullmax #MobilityTransformation