Autonomous Driving Algorithm Research: BEV Drives Algorithm Revolution, AI Large Model Promotes Algorithm Iteration
The core of the autonomous driving algorithm technical framework is divided into three parts: environment perception, decision planning, and control execution.
Environment perception: convert sensor data into machine language of the scenario where the vehicle is located, which can include object detection, recognition and tracking, environment modeling, motion estimation, etc.;
Decision planning: Based on the output results of perception algorithm, the final behavioral action instructions are given, including behavioral decisions (vehicle following, stopping and overtaking), action decisions (car steering, speed, etc.), path planning, etc.;
Control actuation: according to the output results of decision-making level, the underlying modules are mobilized to issue instructions to the core control components such as accelerator and brake, and promote vehicle to drive according to the planned route.
BEV drives algorithm revolution
In recent years, BEV perception has received extensive attention. BEV model mainly provides a unified space to facilitate the fusion of various tasks and sensors. It has following advantages:
BEV unifies the multimodal data processing dimension and makes multimodal fusion easier
The BEV perception system converts the information obtained from multiple cameras or radars to a bird's-eye view, and then do tasks such as object detection and instance segmentation, which can more intuitively display the dimension and direction of objects in BEV space.
In 2022, Peking University & Ali proposed a fusion framework of LiDAR and vision - BEVFusion. The processing of radar point clouds and image processing are carried out independently, using neural networks to encode, project to a unified BEV space, and then merge the two in BEV space.
Realize timing information fusion and build 4D space
In the 4D space, the perception algorithm can better complete the perception tasks such as speed measurement, and can transmit the results of motion prediction to the decision and control module.
PhiGent Robotics proposed BEVDet4D in 2022, which is a version based on BEVDet to increase timing fusion. BEVDet4D extends BEVDet by retaining intermediate BEV features of past frames, and then fuses features by aligning and splicing with the current frame, so that time clues can be obtained by querying two candidate features.
Imagine occluded objects to realize object prediction
In the BEV space, the algorithm can predict the occluded area based on prior knowledge, and imagine whether there are objects in the occluded area.
FIERY, proposed by Wayve in cooperation with the University of Cambridge in 2021, is an end-to-end road dynamic object instance prediction algorithm that does not rely on high-precision maps and is only based on aerial views of monocular cameras.
Promoting development of an end-to-end autonomous driving framework
In the BEV space, perception and prediction can be directly optimized end-to-end through neural networks in a unified space, and the results can be obtained at the same time. Not only the perception module, but also the BEV-based planning decision-making module is also the direction of academic research.
In 2022, autonomous driving team of Shanghai Artificial Intelligence Laboratory and the team of associate professor Yan Junchi of Shanghai Jiao Tong University collaborated on paper ST-P3 to propose a spatiotemporal feature learning solution that can simultaneously provide a set of more representative features for perception, prediction and planning tasks.
AI large model drives algorithm iteration
After 2012, deep learning algorithms are widely applied in autonomous driving field. In order to support larger and more complex AI computing needs, AI large models with the characteristics of "huge data, huge computing power, and huge algorithms" were born, which accelerated the iteration speed of algorithms.
Large Model and Intelligent Computing Center
In 2021, HAOMO.AI launched research and landing attempts on large-scale Transformer model, and then gradually applied it on a large scale in projects including multi-modal perception data fusion and cognitive model training. In December 2021, HAOMO.AI released autonomous driving data intelligence system MANA (Chinese name "Snow Lake"), which integrates perception, cognition, labeling, simulation, computing and other aspects. In January 2023, HAOMO.AI together with Volcano Engine unveiled MANA OASIS, a supercomputing center with a total computing power of 670 PFLOPS. After deploying HAOMO.AI's training platform, OASIS can run various applications including cloud large-scale model training, vehicle-side model training, annotation, and simulation. With the help of MANA OASIS, the five major models of HAOMO.AI have ushered in a new appearance and upgrade.
In August 2022, based on Alibaba Cloud intelligent computing platform, Xpeng Motors built an autonomous driving intelligent computing center "Fuyao", which is dedicated to training of autonomous driving models. In October 2022, Xpeng also announced the introduction of Transformer large model.
In November 2022, Baidu released Wenxin Big Model. Leveraging more than 1 billion parameters, it recognizes thousands of objects, helping to enlarge the scope of semantic recognition. At present, it is mainly used in three aspects: distance vision, multimodality and data mining.
China Automotive Fragrance and Air Purification Systems Research Report, 2023
Automotive fragrance and air purification systems: together to create a comfortable and healthy cockpitTechnology trend: intelligence of fragrance system and integration of air purification system
In...
Global and China Solid State Battery Industry Report, 2023
Solid state battery research: semi-solid state battery has come out, is all-solid state battery still far away?In recent years, the new energy vehicle market has been booming, and the penetration of n...
Global and China Passenger Car T-Box Market Report, 2023
T-Box industry research: the market will be worth RMB10 billion and the integration trend is increasingly clear.
ResearchInChina released "Global and China Passenger Car T-Box Market Report, 2023", w...
Analysis Report on Auto Shanghai 2023
Analysis on 75 Trends at Auto Shanghai 2023: Unprecedented Prosperity of Intelligent Cockpits and Intelligent Driving Ecology
After analyzing the intelligent innovation trends at the Auto Shanghai 20...
Chinese Emerging Carmakers’ Telematics System and Entertainment Ecosystem Research Report, 2022-2023
Telematics service research (III): emerging carmakers work on UI design, interaction, and entertainment ecosystem to improve user cockpit experience.
ResearchInChina released Chinese Emerging Carmake...
China Passenger Car Cockpit-Parking Industry Report, 2023
Cockpit-parking integration research: cockpit-parking vs. driving-parking, which one is the optimal solution for cockpit-driving integration?Cockpit-parking vs. driving-parking, which one is the optim...
Automotive Sensor Chip Industry Report, 2023
Sensor chip industry research: driven by the "more weight on perception" route, sensor chips are entering a new stage of rapid iterative evolution.
At the Auto Shanghai 2023, "more weight on percepti...
Automotive Electronics OEM/ODM/EMS Industry Report, 2023
Automotive electronics OEM/ODM/EMS research: amid the disruption in the division of labor mode in the supply chain, which auto parts will be covered by OEM/ODM/EMS mode? Consumer electronic manu...
China Automotive Smart Glass Research Report, 2023
Smart glass research: the automotive smart dimming canopy market valued at RMB127 million in 2022 has a promising future.Smart dimming glass is a new type of special optoelectronic glass formed by com...
Automotive Ultrasonic Radar and OEM Parking Roadmap Development Research Report, 2023
Automotive Ultrasonic Radar Research: as a single vehicle is expected to carry 7 units in 2025, ultrasonic radars will evolve to the second generation.
As a single vehicle is expec...
Autonomous Driving SoC Research Report, 2023
Research on autonomous driving SoC: driving-parking integration boosts the industry, and computing in memory (CIM) and chiplet bring technological disruption.
“Autonomous Driving SoC Research ...
China ADAS Redundant System Strategy Research Report, 2023
Redundant System Research: The Last Line of Safety for Intelligent VehiclesRedundant design refers to a technology adding more than one set of functional channels, components or parts that enable the ...
Intelligent Steering Key Components Report, 2023
Research on intelligent steering key components: four development trends of intelligent steering
The automotive chassis consists of four major systems: transmission system, steering system, driving ...
Automotive Digital Instrument Cluster Operating System Report, 2023
Digital Instrument Cluster Operating System Report: QNX commanded 71% of the Chinese intelligent vehicle cluster operating system market.
Amid the trend for the integration of digital cluster and cen...
800V High Voltage Platform Research Report, 2023
How to realize the commercialization of 800V will play a crucial part in the strategy of OEMs.
As new energy vehicles and battery technology boom, charging and battery swapping in the new energy vehi...
Automotive Intelligent Cockpit Platform Research Report, 2023
Intelligent cockpit platform research: the boundaries between vehicles and PCs are blurring, and there are several feasible paths for cockpit platforms.
Automotive Intelligent Cockpit Platform Resea...
Global and China Automotive Wireless Communication Module Industry Report，2023
Vehicle communication module research: 5G R16+C-V2X module, smart SiP module and other new products spring up.
In 2022, 4G modules swept 84.3% of the vehicle communication module market....
Intelligent Vehicle Cockpit-Driving Integration Research Report, 2023
Cockpit-Driving Integration Research: many companies are making layout and may implement it during 2024-2025.
1. What is the real cockpit-driving integration?
At present, automotive electroni...