Today's robots have the same body and sensory functions as human beings, with a certain degree of intelligence, flexible movement procedures, and can work without relying on human manipulation. And all this without the achievement of sensor, the sensor is one of the important helper robot perceive the outside world, they are like human sensory organs, robot vision, feel, touch, smell, taste and such external environment awareness are provided by the sensors, at the same time, the sensor also can be used to detect the working state of the robot, robot and intelligent detection work external ring Context and object state. And can be converted into a usable output signal in accordance with certain rules of a device, in order to make the robot to achieve the highest possible sensitivity, in its body structure will be installed with a variety of sensors, so how many kinds of sensors can the robot as sensitive as possible to do as human beings?
According to the different detection objects, robot sensors can be divided into internal sensors and external sensors.
The internal sensor is mainly used to detect the status of the robot's internal systems, such as the position of each joint, speed, acceleration and temperature, motor speed, motor load, battery voltage, etc., and the measured information is sent to the controller as feedback information, forming a closed-loop control.
The external sensor is used to obtain information about the robot's operating object and external environment, and is the information channel for the robot to interact with its surroundings. It is used to perform sensors such as vision, proximity, touch and force, such as distance measurement, sound and light.
Detailed introduction is as follows:
1. Vision sensor
Machine vision is a system that enables robots to have perceptual functions. It obtains images for analysis through visual sensors, so that robots can replace human eyes to identify objects, measure and judge, and achieve positioning and other functions. Industry insiders point out that smart vision sensors, which are easy to use in China, account for about 60% of the market share of machine vision systems. The advantages of visual sensors are wide detection range and rich information acquisition. In practical applications, multiple visual sensors are often used or used with other sensors. Through a certain algorithm, the shape, distance, speed and many other information of the object can be obtained.
The computational vision field based on the depth camera has become one of the hottest investment and entrepreneurship hot spots in the whole high-tech industry. Interestingly, many of the best advances in this field have been made by startups and then acquired by giants, such as Intel's acquisition of RealSense cameras and Apple's purchase of PrimeSense, the maker of Kinect technology, Oculus bought Pebbles Interfaces, an Israeli technology firm that specialises in high-precision gesture recognition. Although the entrepreneurial teams in the field of computational vision in China have not yet entered the mainstream vision of investors on a large scale, the outstanding ones among them have begun to achieve remarkable results.
Deep cameras were first conceptualized in the 1980s by IBM, the mega-company that holds the underlying data on almost every hard drive past, present and future. PrimeSense, an Israeli company founded in 2005, has been a pioneer in making the technology commercially available. At that time, the promotion of depth cameras in the consumer market was still in the conceptual stage. Previously, depth cameras were only used in the industrial field to provide graphics and vision services for robotic arms and industrial robots. Microsoft Kinect, which provides the technical solution, became the pioneering work of the depth camera in the consumer field, and led the whole industry to develop the technology for civilian use.
