With the rapid development of artificial intelligence technology, intelligent robots have gradually sprung up in recent years. In addition to intelligent functions such as face recognition and voice interaction, the seemingly most basic walking ability is also the foundation for the realization of the value of service robots. At present, autonomous mobile robot has become an important research direction in the field of robot. Autonomous mobile robot has the ability to perceive complex environment and make action decision quickly.
The concrete manifestation of “intelligence” of autonomous mobile robot
1. The autonomous mobile robot can realize autonomous positioning and mapping
The map creation of the robot in the known environment is relatively simple, but it is not easy to achieve autonomous positioning and mapping in the completely unknown environment. In many complex environments, if the robot cannot use the global positioning system for positioning, it is very difficult or even impossible to obtain the map of the robot’s working environment. The robot needs to create a map under the condition of complete unknown and uncertain position, and use the map for autonomous positioning and navigation. Slam technology is considered to be the key to solve this problem.
In an unknown environment, the robot starts to move from an unknown position, locates itself according to the position estimation and sensor data, and gradually improves and constructs a perfect map, which is a slam process. In slam, the robot uses its own sensor to identify the feature mark in the unknown environment, and then estimates the global coordinates of the robot and the feature mark according to the relative position between the robot and the feature mark and the odometer reading. This online positioning and map creation needs to maintain the detailed information between the robot and the feature mark. In recent years, the research of slam technology has made a great breakthrough and has been widely used in many fields, such as robot, AR, VR, UAV, autopilot and so on.
2. Autonomous mobile robot can achieve autonomous path planning
Path planning is also an important link for the robot to realize autonomous movement. It refers to how to find an appropriate motion path from the starting point to the end point in the working environment with obstacles, so that the robot can bypass all obstacles safely and without collision. This is different from the shortest path obtained by dynamic programming, but refers to that the mobile robot can make comprehensive judgment and intelligent decision on the static and dynamic environment.
According to the degree of mastering environmental information, robot path planning can be divided into global path planning and local path planning.
Global path planning is to plan a path for the robot in a known environment. The accuracy of path planning depends on the accuracy of environment acquisition. Global path planning can find the optimal solution, but it needs to know the accurate information of the environment in advance. When the environment changes, such as unknown obstacles, this method is powerless. It is a kind of prior planning, so it does not require high real-time computing power of the robot system. Although the planning result is global and better, it has poor robustness to the error and noise of the environmental model.
The local path planning is completely unknown or partially known. It focuses on considering the current local environmental information of the robot, so that the robot has good obstacle avoidance ability. The working environment of the robot is detected through sensors to obtain the information such as the location and nature of obstacles. This planning needs to collect environmental data, Moreover, the dynamic update of the environment model can be corrected at any time. The local planning method integrates the modeling and search of the environment. The robot system is required to have high-speed information processing ability and computing ability, have high robustness to environmental errors and noise, and can feed back and correct the planning results in real time. However, due to the lack of global environment information, Therefore, the planning result may not be optimal, or even the correct path or complete path may not be found.
There is no essential difference between global path planning and local path planning. Many methods suitable for global path planning can also be used for local path planning after improvement, and the methods suitable for local path planning can also be used for global path planning after improvement. Working together, the robot can better plan the walking path from the starting point to the end point.
Autonomous mobile robots have emerged in many fields
Today, autonomous mobile robots have “emerged” in restaurants, shopping malls, hotels, banks, hospitals and other major service places. Especially in the fight against the epidemic, autonomous mobile robots have stood on the “cusp of the storm”. For a time, medical assistant robots, cleaning and disinfection robots, transportation and distribution robots appeared in the front line of various fields, reducing the close contact between people and ensuring the safety of relevant personnel to the greatest extent.
Among them, there are many food delivery robots of Qinglang technology, disinfection and nursing robots of Dake technology, drug delivery robots of Purdue technology, etc. Most of the service robots involved in autonomous mobile use the robot positioning and navigation products of Silan technology, and the medical assistant robot of Dazhong technology is one of them. It can effectively help medical staff to undertake inquiry, guidance and other work. In the new pneumonia epidemic, non-contact 24-hour consultation and guidance services were also provided for many hospitals in Beijing, Shanghai and Wuhan, reducing the safety risk of medical staff, with comments, jokes, stories and soothing music to soothe patients’ emotions.
The medical assistant robot is mainly developed based on the Apollo mobile robot chassis of Silan technology. It can independently scan the surrounding environment information, and achieve the functions of independent positioning, mapping, path planning and so on. Even in the face of a hospital with complex environment, the robot can walk freely without manual intervention. Even if it encounters obstacles with high permeability materials such as glass and mirror, it will not hit it like a headless fly.
It is understood that the Apollo mobile robot chassis adopts the high-performance laser slam technology independently developed by Silan technology, and integrates a variety of sensors such as ultrasonic, anti drop and depth camera. It can complete positioning and draw high-precision map in real time even in an unknown environment. Its sharpedgetm fine composition technology can build high-precision and centimeter level maps with ultra-high resolution and no cumulative error. The constructed map is regular and fine, which can be used directly without secondary optimization and modification, and can directly meet the use expectation. When walking in complex and changeable application places with uncontrolled environment (such as hospitals, shopping malls, office buildings and other places with large traffic), people or moving obstacles in the environment can be dynamically identified in real time, and flexible avoidance and route planning can be carried out.
At the same time, the Apollo mobile robot chassis has elevator adaptation and multi floor positioning system, which can interact with most elevator systems in the market. There is no need to worry about the problem of robots getting on and off the elevator independently. In addition, it can cooperate with Robo studio robot management software of Silan technology to set POI and other parameters, which can not only deepen the robot’s understanding of the map and reach the designated place to perform tasks. It is also convenient for end users to view and understand the use of the robot at any time.
Autonomous movement is the most basic value embodiment of service robots. Compared with industrial robots, there is no fixed scene deployment in the service industry, so it is difficult to guide robots to move by laying magnetic strips or beacons on the ground. At present, among the robots applied in the service field on the market, reception, guidance, distribution and other robots are more common, and their working scenes are more complex. However, mobile robots with autonomous positioning and navigation technology can effectively avoid dynamic or static obstacles in the path and independently plan the optimal walking path.