Artificial Intelligence + Robots: New Opportunities for Manufacturing Efficiency Improvement

In 2018, Chinese AI investment and startups are continuing to increase. The investment and financing cases of “Artificial Intelligence + Manufacturing” are also numerous.

"AI" can be seen everywhere, and has become a popular word for many people. The machine learning guru, Michael I. Jordan, thinks this phenomenon makes him very upset: "AI is just a way for them to sell their own concepts to VC, business, media and the public. As for true AI, we are fundamental Not yet implemented."

In the past, in the industrial field of pursuing cost performance and practicality, "artificial intelligence is only a small supporting role on the stage of intelligent manufacturing." Nowadays, with regard to specific application scenarios, people in the industry generally believe that artificial intelligence will greatly improve the efficiency of industrial robots.

So far, what artificial intelligence has been discovered by the robotics industry in the “New World” of industrial application scenarios? Where is the future direction of artificial intelligence technology combined with robot technology?

AI = + traditional industrial robot intelligent robot

Traditional industrial robots are highly integrated with mechanical design and manufacturing technology, automatic control technology, and computer hardware and software technology.

Artificial intelligence is a collection of data and algorithms, and the continual rise in computing power (chip) is the basis for the widespread application of artificial intelligence. At present, artificial intelligence is still in the stage of weak artificial intelligence, and the areas that form breakthroughs are still relatively limited. The combination of artificial intelligence technology and robot technology to realize robots with both robotic bodies and human intelligence is the ultimate goal of artificial intelligence and robot technology development. Intelligent robots are the result of the integration of artificial intelligence technology and traditional industrial robot technology.

Zheng Yong, Geek+ CEO, said that if artificial intelligence is defined to the extent of “deep learning”, there is almost no application at present. He believes that current artificial intelligence can be defined as "autonomous ability brought by relatively complex algorithms."

Geek+, which focuses on the field of robotic intelligent logistics, empowers the logistics and warehousing industry through artificial intelligence and robotics. Through the optimization of warehousing and logistics links such as intelligent picking, handling and sorting, and highly flexible human-computer interaction, it can improve warehouse efficiency and reduce labor. The purpose of cost and labor intensity.

Cooper CEO Li Wei pointed out that “sorting, grinding, assembly and testing” are the most urgent and extensive areas for artificial intelligence and robot landing applications. Therefore, Cooper's self-developed system can be applied to the disorderly sorting of loading and unloading, force-controlled grinding of mobile phones or aviation blades, intelligent teaching, intelligent labeling, and parts assembly through core learning algorithms and special control software. .

"In the AI ​​era, industrial robots will be defined by new core technologies, including deep learning, path planning, task-level programming, flexible control, etc." said Mecamand CEO Shao Tianlan. In his view, the sorting of mixed objects is the most obvious and application-oriented part of the current demand. Many companies can display a certain degree of demo, but the products that can be used on a large scale have not yet appeared.

In addition, there is a combination point for “operation planning”, that is, people only need to specify the installation requirements of multiple workpieces, and the robot can calculate the grab and install solution by itself, saving a lot of programming time.

In the standard scene, industrial robots produce large quantities of products, have a lot of repetitive work, and require high-frequency trajectory optimization, such as machine tool processing, parts installation and other applications. At this point, the small sample can be supervised and learned, so that the robot has adaptive and evolutionary functions.

Previously, Elite showed the demo of “Robot Stacking Clothes”, showing that robot trajectory optimization can not only target rigid objects, but also flexible bodies such as clothes. Elite's robot stacking system accurately locates the clothing fold points through deep intensification learning algorithms and depth vision sensors, automatically finding the best motion trajectory and achieving the stacking effect. The system also uses simulation environment rapid modeling and migration learning methods to speed up learning, reduce data acquisition costs, and ultimately map simulation results to real robot operations.

In addition to the above-mentioned applications that focus on improving the efficiency of industrial robots, machine vision as a branch of artificial intelligence is both an opportunity and a challenge.

In the intelligent manufacturing process, machine vision mainly uses computer to simulate human visual function, that is, extracts, processes and understands the image information of objective things, and finally uses it for actual detection, measurement and control.

Huang Bufu, CEO of Yi Shizhi, believes that machine vision detection is a major “training ground” for artificial intelligence. Yi Shi Zhi Zhi high-precision visual dispensing system integrates the functions of visual perception, motion control and dispensing execution of the dispensing process, which can be easily integrated with various actuators to form a terminal dispensing machine in one step to meet various productions. The demand for line dispensing can also be evolved from stand-alone intelligence to multi-machine interconnection through deep learning.

In addition, equipment fault monitoring and early warning is also a major application of artificial intelligence in industrial scenes. This type of program can supervise every robot in the factory building and predict the abnormal condition of the robot. Before the robot has problems, add technicians to carry out maintenance work. .

In addition, if a robot fails, this type of solution can also allow adjacent robots to automatically assume tasks on their production lines to avoid or reduce equipment loss.

The application scenarios of artificial intelligence in manufacturing are mostly similar or related to the above. Industry insiders agree that the combination of artificial intelligence technology and robotics technology will change the traditional robot industry landscape, just like the subversion of smart phones to traditional mobile phones.

Insert the wings of artificial intelligence, can domestic robots bend over the road?

When it comes to industrial robots, you will definitely mention ABB, KUKA, FANUC, and Yaskawa. Insiders analyzed that the conditions for oligopoly are:

First, the expansion of market space is not enough to accommodate more similar manufacturers. The production capacity of a few large companies has basically met the total demand of all customers;

Second, the technology is very mature, and it is difficult to produce disruptive new technologies. It is difficult for companies in the catch-up position to achieve “curve overtaking” through technological breakthroughs.

For domestic robots, for the international giants have been in a state of catching up, under such a market structure, domestic robots began to choose to enter from the subdivision, trying to win in the local battlefield through "the skill of one skill." There are two major opportunities for China to change the situation of catching up:

First, China is a huge market for incremental applications of robots.

According to statistics, in the 3C field, China's annual output of mobile phones exceeds 2 billion, and the output of TV, refrigerators, and air conditioners ranks first in the world. In the field of logistics and e-commerce, the number of express parcels per year exceeds 40 billion, that is, With a per capita number of 30, it ranks first in the world; in the field of food and chemical industry, fertilizer production ranks first in the world. A huge amount of actual industrial demand provides a huge training ground for artificial intelligence.

Second, China's talents and technology are in the first echelon.

Compared with robot ontology technology, China is relatively leading in the field of artificial intelligence, which is reflected in the number and quality of papers published in the field of AI in the world's top two; making important contributions to the infrastructure of deep learning; well-known research institutes and universities In the world, it belongs to the first echelon; it is used in various AI competitions.

In the specific practice, with the improvement of the cost performance of domestic robots, the recognition of domestic robots by the industry, robot enterprises for the actual needs of specific industries or application scenarios, creative application of artificial intelligence technology and robot technology, propose solutions and achieve The corresponding products have huge space, which is also the key direction of entrepreneurial innovation.

However, the road of "overtaking in a corner" will certainly not be a smooth river. Shao Tianlan pointed out that in order to truly move towards the new era of AI+ robots, Chinese robots still face challenges, such as shallow accumulation in the direction of trajectory planning and compliance control; they need to compete with the Internet, autopilot, face recognition and other fields for super-class talents. In addition to this, long-term investment in all aspects requires great determination and ability.

Similarly, Deng Xiaobai, CEO of the blue fat robot, has given the industry a "vaccination": concepts and stories are easy to say, things are not easy to do, ideals can be achieved, and dreams cannot be realized. He believes that in hardware, the process needs time to accumulate; in software, the development and education of robot software is far behind Europe and the United States. "China has a market with hope, but it has a long way to go. Whether it is robots or artificial intelligence, it needs to be applied to market segments and scale up." Deng Xiaobai said.

Is “artificial intelligence + manufacturing” on the tuyere a real prosperity or a carnival before the bubble bursts? The answer to this question is probably that the artificial intelligence that can be successfully landed will have great value; and the narrow "air castle" based on AI algorithm or technology will not be able to adapt to the industry situation, and will soon see the bursting of the bubble.

Pristine Auction

Auction is a kind of spot trading mode in which an auction house specializing in auction business accepts the entrustment of the owner of the goods, displays the goods to be auctioned to the buyer at a specified time and place in accordance with certain rules and regulations, bids publicly, and finally the auctioneer sells the goods to the buyer with the highest bid.

Pristine Auction,Online Auction Antique Furniture,Antique Online Auction,Online Auction Art

The universe in the stone is great , https://www.zdartwork.com