“What kind of edge artificial intelligence system is successful? “Accurate perception, rapid decision-making, human-machine collaboration, high efficiency and energy saving, safe and reliable”, this is the answer given by Howard Jiang, director of embedded product systems and applications in Texas Instruments (TI) China. As we all know, perception, decision-making and execution are the three links of edge artificial intelligence, and with the development of edge artificial intelligence, the requirements for embedded perception and decision-making technology are more stringent and more differentiated than non-artificial intelligence.
“
Edge artificial intelligence is here, TI core technology empowers artificial intelligence in China’s new infrastructure
In 1956, when McCarthy of Stanford University proposed “artificial intelligence”, he must not have imagined that this concept would be in full swing in China decades later. Artificial intelligence is not only high hopes for triggering a new industrial revolution, it is also integrated into everyone’s daily life and is triggering social changes. In fact, in April 2020, when the National Development and Reform Commission determined the three aspects of new infrastructure, it mentioned artificial intelligence in both the information infrastructure and the converged infrastructure, which was nothing but to clearly inform the public about the changes that are taking place.
With the development of computing power, data, and the Internet, artificial intelligence is at a node from quantitative change to qualitative change, especially the edge is showing explosive development. Gartner predicts that by 2025, at least 75% of data processing will be done in the cloud or outside the data center. The tide of artificial intelligence is both an opportunity and a challenge for Semiconductor companies. Unlike the cloud, the most important demand for chips on the edge side is still returning to the eternal topic of performance, cost, and power consumption. In addition, because the development cycle of edge artificial intelligence products is short and the iteration window is fast, a friendly development environment is also critical.
Howard Jiang, Director of Embedded Products Systems and Applications, Texas Instruments (TI) China
What kind of edge artificial intelligence system is successful? “Accurate perception, rapid decision-making, human-machine collaboration, high efficiency and energy saving, safe and reliable”, this is the answer given by Howard Jiang, director of embedded product systems and applications in Texas Instruments (TI) China. As we all know, perception, decision-making and execution are the three links of edge artificial intelligence, and with the development of edge artificial intelligence, the requirements for embedded perception and decision-making technology are more stringent and more differentiated than non-artificial intelligence.
Perception-the data source of edge artificial intelligence
Data is the foundation of edge artificial intelligence, and perception is the source of data. Just as a person needs more than just eyes to feel the world, ears are also important organs to perceive the natural world, so machines also need ears and eyesight, and various sensors have emerged with the development of technology. TI’s single-chip millimeter-wave radar can circumvent the disadvantages of traditional cameras in many applications, and support multiple data fusion of the system, so that the machine can better obtain data and achieve accurate target perception.
Using millimeter-wave radar to transmit and receive, the distance and relative speed of objects and obstacles in the field of view can be measured with extremely high accuracy. Compared with sensors based on vision and lidar, an important advantage of millimeter wave sensors is that they are not easily affected by environmental conditions such as rain, dust, smoke, fog, or frost. In addition, the millimeter wave sensor can work in complete darkness or under direct sunlight. These sensors can be installed directly behind a plastic housing without external lenses, vents or sensor surfaces. They are very sturdy and durable, and can meet the protection level (IP) 69K standard.
TI’s single-chip millimeter-wave radar uses CMOS manufacturing process technology to achieve cost-effective advantages that traditional radars do not have. At the same time, combined with ASIC back-end processing, it can directly reduce BOM costs, reduce product size, and reduce the need for processors. Dependence. The product volume based on TI millimeter wave radar design is one-third of the miniature lidar rangefinder, and its weight is half.
More importantly, in addition to the field of autonomous driving, millimeter-wave radar can also be applied to a wider range of industries and smart homes, smart buildings, medical and other fields. For example, through the combination of millimeter wave radar and air conditioner, multiple intelligent functions such as wind following the movement of people, attitude perception of the target human body, and automatic switching can be realized. In other applications, such as safety monitoring for robotic arm operators, obstacle avoidance detection for logistics robots/drones, and falls for the elderly, millimeter-wave radar has the advantages of accuracy and rapid sensing that previous image sensors did not have. At the same time, it meets the data desensitization requirements of many applications (can be installed in bedrooms, bathrooms, etc.).
In addition to millimeter-wave radar, TI also provides a wide range of products such as temperature sensors, DLP® technology, and ToF, which further enriches the interaction between machines and humans.
Decision-making-the brain of edge artificial intelligence
Edge artificial intelligence devices need a smart “brain” for data processing and decision-making. Integrated SoC is usually a good choice for edge artificial intelligence, because in addition to accommodating various processing elements that can perform deep learning inference, SoC also integrates many necessary components for the entire embedded application. Some integrated SoCs include display, graphics, video acceleration, and industrial networking functions, making single-chip solutions not limited to running ML/AI.
TI’s Jacinto™ 7 series processors are just such a highly integrated SoC. The chip includes high-performance computing, deep learning engines, and dedicated accelerators for signal and image processing. It complies with functional safety ASIL-D/SIL-3 standards. . In addition to advanced driver assistance systems (ADAS), the processor can also be used in robotics, machine vision, radar and other fields.
The integrated dedicated accelerator includes the “C7x” new-generation DSP core, which combines TI’s industry-leading DSP and EVE cores, adds vector floating-point calculation functions, and supports backward compatible code. With the rise of edge artificial intelligence, DSP, based on the Harvard architecture, can significantly improve the efficiency of matrix operations, which is very suitable for neural network computing acceleration. At the same time, the newly added “MMA” deep learning accelerator can achieve a computing performance of 8 TOPS with low power under typical working conditions.
General-purpose cores include multi-core Arm Cortex-A72, Cortex-R5F, and 8XE GE8430 GPU.
The multi-core heterogeneous processor architecture design of the Jacinto 7 series can maximize the selection and optimization of tasks, thereby achieving better performance improvement and cost control. In addition, TI will also hardware mature algorithms, coupled with the evolution of the semiconductor process, so as to achieve the best cost performance and power consumption ratio. For example, TI’s ISP can automatically realize wide dynamic adjustment, image pyramid scaling, stereo depth vision, and dense optical flow algorithm acceleration based on the hardware acceleration unit embedded in the chip.
The Jacinto 7 series processors provide a comprehensive security solution involving hardware and software, which is an important focus of the automotive and industrial markets. The Jacinto 7 series processors use a hardware development process certified by an independent functional safety assessment agency (such as TÜV SÜD) to design a system for ASIL-D functions. In response to the new challenges of high-bandwidth multi-port brought by ADAS data fusion, the Jacinto 7 series also integrates multi-channel ports such as CSI-2, which can ensure the interconnection with multi-channel sensors and support high-bandwidth data requirements. The Jacinto 7 series also integrates PCIe hubs and Gigabit Ethernet switches, which can be used in domain controllers to achieve a higher level of integration.
In order to facilitate user development, TI launched TI-Edge-AI-Cloud, which evaluates cloud tools for AI inference on Jacinto processors and supports many industry-wide and popular deep learning frameworks (including TensorFlow Lite, ONNX Runtime, OpenGL ES, etc.) ) To help easily compile and deploy models and accelerate inference.
In addition to the CNN commonly used for visual recognition, the Jacinto 7 processor also provides corresponding support for the RNN required by edge artificial intelligence scenarios such as predictive maintenance. In addition, TI’s industrial application processor SitaraTM series, which integrates the Arm Cortex-A series core, can also realize edge artificial intelligence applications with relatively low computing power requirements through Arm NN, such as predictive maintenance in industrial applications.
From madness to fast landing
In addition to perception and decision-making, TI also has many processors, motor drives, and various analog devices in the execution link, which shows that TI can provide support for the key aspects needed to realize edge AI through a wide range of product portfolios. Technology serves people. As a 90-year-old semiconductor company, TI’s secret is to continuously study changes in social life, to perceive and meet people’s needs, and thus to constantly change itself.
In the 35 years since TI entered China, TI has helped Chinese customers realize innovation time and time again. In the field of artificial intelligence, Howard sees that China’s development has taken the lead in some places. For example, in the field of 4D imaging radar, foreign countries are still at the stage of laboratory concept verification, while domestic automakers have proposed specific time points for mass production. At the same time, Chinese customers are also actively introducing in markets such as smart industry, robotics, smart home, and medical image analysis. Sometimes Howard also uses innovations adopted by Chinese clients to inspire his American colleagues.
When TI is making product definitions, it will conduct in-depth cooperation with some customers, so that the demand for innovation is reflected in the product architecture. This is not only to meet the existing use, but more importantly, to jointly foresee future needs. The rich imagination of Chinese customers also enables the demand from China to be quickly reflected in the development of TI’s next-generation products, and is oriented to global innovative industries.
Thirty-five years ago, TI entered China. In many markets such as industry, consumption, communications, and automobiles, TI started from scratch and jointly innovated with Chinese local partners. Today, as new infrastructure projects represented by artificial intelligence and edge artificial intelligence have begun to expand, TI has joined hands with partners to once again step into a new field, through a complete range of analog and embedded processing products, strong local manufacturing and research and development Ability, product distribution and sales network across the country to solve the new challenges brought by edge artificial intelligence and meet the new requirements of Chinese customers’ product design. In TI, there are a group of outstanding engineers like Howard, with the vision of “core to China, science and technology world”, and strive to make the world a better place through semiconductor technology.
Not long ago, Midea Group’s Kitchen and Water Heater Division and TI jointly established the “Perception and Interaction Joint Laboratory”, which aims to help Midea use TI’s millimeter wave radar technology and a wide range of simulation and embedded processing products to accelerate Midea’s kitchen Development of thermal appliance applications. Howard hopes TI can help support more companies like Midea to turn ideas into reality.
Edge artificial intelligence is real, TI core technology empowers artificial intelligence in China’s new infrastructure
In 1956, when McCarthy of Stanford University proposed “artificial intelligence”, he must not have imagined that this concept would be in full swing in China decades later. Artificial intelligence is not only high hopes for triggering a new industrial revolution, it is also integrated into everyone’s daily life and is triggering social changes. In fact, in April 2020, the National Development and Reform Commission mentioned artificial intelligence in the information infrastructure and converged infrastructure when determining the three aspects of the new infrastructure. This is just to clearly inform the public about the changes that are taking place.
With the development of computing power, data, and the Internet, artificial intelligence is at a node from quantitative change to qualitative change, especially the edge is showing explosive development. Gartner predicts that by 2025, at least 75% of data processing will be done in the cloud or outside the data center. The tide of artificial intelligence is both an opportunity and a challenge for semiconductor companies. Unlike the cloud, the most important demand for chips on the edge side is still returning to the eternal topic of performance, cost, and power consumption. In addition, because the development cycle of edge artificial intelligence products is short and the iteration window is fast, a friendly development environment is also critical.
Howard Jiang, Director of Embedded Products Systems and Applications, Texas Instruments (TI) China
What kind of edge artificial intelligence system is successful? “Accurate perception, rapid decision-making, human-machine collaboration, high efficiency and energy saving, safe and reliable”, this is the answer given by Howard Jiang, director of embedded product systems and applications in Texas Instruments (TI) China. As we all know, perception, decision-making and execution are the three links of edge artificial intelligence, and with the development of edge artificial intelligence, the requirements for embedded perception and decision-making technology are more stringent and more differentiated than non-artificial intelligence.
Perception-the data source of edge artificial intelligence
Data is the foundation of edge artificial intelligence, and perception is the source of data. Just as a person needs more than just eyes to feel the world, ears are also important organs to perceive the natural world, so machines also need ears and eyesight, and various sensors have emerged with the development of technology. TI’s single-chip millimeter-wave radar can circumvent the disadvantages of traditional cameras in many applications, and support multiple data fusion of the system, so that the machine can better obtain data and achieve accurate target perception.
Using millimeter-wave radar to transmit and receive, the distance and relative speed of objects and obstacles in the field of view can be measured with extremely high accuracy. Compared with sensors based on vision and lidar, an important advantage of millimeter wave sensors is that they are not easily affected by environmental conditions such as rain, dust, smoke, fog, or frost. In addition, the millimeter wave sensor can work in complete darkness or under direct sunlight. These sensors can be installed directly behind a plastic housing without external lenses, vents or sensor surfaces. They are very sturdy and durable, and can meet the protection level (IP) 69K standard.
TI’s single-chip millimeter-wave radar uses CMOS manufacturing process technology to achieve cost-effective advantages that traditional radars do not have. At the same time, combined with ASIC back-end processing, it can directly reduce BOM costs, reduce product size, and reduce the need for processors. Dependence. The product volume based on TI millimeter wave radar design is one-third of the miniature lidar rangefinder, and its weight is half.
More importantly, in addition to the field of autonomous driving, millimeter-wave radar can also be applied to a wider range of industries and smart homes, smart buildings, medical and other fields. For example, through the combination of millimeter wave radar and air conditioner, multiple intelligent functions such as wind following the movement of people, attitude perception of the target human body, and automatic switching can be realized. In other applications, such as safety monitoring for robotic arm operators, obstacle avoidance detection for logistics robots/drones, and falls for the elderly, millimeter-wave radar has the advantages of accuracy and rapid sensing that previous image sensors did not have. At the same time, it meets the data desensitization requirements of many applications (can be installed in bedrooms, bathrooms, etc.).
In addition to millimeter-wave radar, TI also provides a wide range of products such as temperature sensors, DLP® technology, and ToF, which further enriches the interaction between machines and humans.
Decision-making-the brain of edge artificial intelligence
Edge artificial intelligence devices need a smart “brain” for data processing and decision-making. Integrated SoC is usually a good choice for edge artificial intelligence, because in addition to accommodating various processing elements that can perform deep learning inference, SoC also integrates many necessary components for the entire embedded application. Some integrated SoCs include display, graphics, video acceleration, and industrial networking functions, making single-chip solutions not limited to running ML/AI.
TI’s Jacinto™ 7 series processors are just such a highly integrated SoC. The chip includes high-performance computing, deep learning engines, and dedicated accelerators for signal and image processing. It complies with functional safety ASIL-D/SIL-3 standards. . In addition to advanced driver assistance systems (ADAS), the processor can also be used in robotics, machine vision, radar and other fields.
The integrated dedicated accelerator includes the “C7x” new-generation DSP core, which combines TI’s industry-leading DSP and EVE cores, adds vector floating-point calculation functions, and supports backward compatible code. With the rise of edge artificial intelligence, DSP, based on the Harvard architecture, can significantly improve the efficiency of matrix operations, which is very suitable for neural network computing acceleration. At the same time, the newly added “MMA” deep learning accelerator can achieve 8 TOPS computing performance with low power under typical working conditions.
General-purpose cores include multi-core Arm Cortex-A72, Cortex-R5F, and 8XE GE8430 GPU.
The multi-core heterogeneous processor architecture design of the Jacinto 7 series can maximize the selection and optimization of tasks, thereby achieving better performance improvement and cost control. In addition, TI will also hardware mature algorithms, coupled with the evolution of the semiconductor process, so as to achieve the best cost performance and power consumption ratio. For example, TI’s ISP can automatically realize wide dynamic adjustment, image pyramid scaling, stereo depth vision, and dense optical flow algorithm acceleration based on the hardware acceleration unit embedded in the chip.
The Jacinto 7 series processors provide a comprehensive security solution involving hardware and software, which is an important focus of the automotive and industrial markets. The Jacinto 7 series processors use a hardware development process certified by an independent functional safety assessment agency (such as TÜV SÜD) to design a system for ASIL-D functions. In response to the new challenges of high-bandwidth multi-port brought by ADAS data fusion, the Jacinto 7 series also integrates multi-channel ports such as CSI-2, which can ensure the interconnection with multi-channel sensors and support high-bandwidth data requirements. The Jacinto 7 series also integrates PCIe hubs and Gigabit Ethernet switches, which can be used in domain controllers to achieve a higher level of integration.
In order to facilitate user development, TI launched TI-Edge-AI-Cloud, which evaluates cloud tools for AI inference on Jacinto processors and supports many industry-wide and popular deep learning frameworks (including TensorFlow Lite, ONNX Runtime, OpenGL ES, etc.) ) To help easily compile and deploy models and accelerate inference.
In addition to the CNN commonly used for visual recognition, the Jacinto 7 processor also provides corresponding support for the RNN required by edge artificial intelligence scenarios such as predictive maintenance. In addition, TI’s industrial application processor SitaraTM series, which integrates the Arm Cortex-A series core, can also realize edge artificial intelligence applications with relatively low computing power requirements through Arm NN, such as predictive maintenance in industrial applications.
From madness to fast landing
In addition to perception and decision-making, TI also has many processors, motor drives, and various analog devices in the execution link, which shows that TI can provide support for the key aspects needed to realize edge AI through a wide range of product portfolios. Technology serves people. As a 90-year-old semiconductor company, TI’s secret is to continuously study changes in social life, to perceive and meet people’s needs, and thus to constantly change itself.
In the 35 years since TI entered China, TI has helped Chinese customers realize innovation time and time again. In the field of artificial intelligence, Howard sees that China’s development has taken the lead in some places. For example, in the field of 4D imaging radar, foreign countries are still at the stage of laboratory concept verification, while domestic automakers have proposed specific time points for mass production. At the same time, Chinese customers are also actively introducing in markets such as smart industry, robotics, smart home, and medical image analysis. Sometimes Howard also uses innovations adopted by Chinese clients to inspire his American colleagues.
When TI is making product definitions, it will conduct in-depth cooperation with some customers, so that the demand for innovation is reflected in the product architecture. This is not only to meet the existing use, but more importantly, to jointly foresee future needs. The rich imagination of Chinese customers also enables the demand from China to be quickly reflected in the development of TI’s next-generation products, and is oriented to global innovative industries.
Thirty-five years ago, TI entered China. In many markets such as industry, consumption, communications, and automobiles, TI started from scratch and jointly innovated with Chinese local partners. Today, as new infrastructure projects represented by artificial intelligence and edge artificial intelligence have begun to expand, TI has joined hands with partners to once again step into a new field, through a complete range of analog and embedded processing products, strong local manufacturing and research and development Ability, product distribution and sales network across the country to solve the new challenges brought by edge artificial intelligence and meet the new requirements of Chinese customers’ product design. In TI, there are a group of outstanding engineers like Howard, with the vision of “core to China, science and technology world”, and strive to make the world a better place through semiconductor technology.
Not long ago, Midea Group’s Kitchen and Water Heater Division and TI jointly established the “Perception and Interaction Joint Laboratory”, which aims to help Midea use TI’s millimeter wave radar technology and a wide range of simulation and embedded processing products to accelerate Midea’s kitchen Development of thermal appliance applications. Howard hopes TI can help support more companies like Midea to turn ideas into reality.
The Links: 2DI100Z-100 MIG15J503H