CN113465728A - Terrain perception method, terrain perception system, storage medium and computer equipment - Google Patents
Terrain perception method, terrain perception system, storage medium and computer equipment Download PDFInfo
- Publication number
- CN113465728A CN113465728A CN202110710851.5A CN202110710851A CN113465728A CN 113465728 A CN113465728 A CN 113465728A CN 202110710851 A CN202110710851 A CN 202110710851A CN 113465728 A CN113465728 A CN 113465728A
- Authority
- CN
- China
- Prior art keywords
- robot
- terrain
- algorithm
- path
- inspection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention belongs to the technical field of terrain perception, and discloses a terrain perception method, a terrain perception system, a storage medium and computer equipment, wherein a Kinect depth camera is used for obtaining data information related to terrain parameters, so that automatic identification of road surface danger levels is realized; removing the motion distortion of the laser radar by combining a speedometer auxiliary method with a Kalman filtering algorithm; and (4) SLAM mapping in ROS and optimization of a navigation algorithm. In the invention, the distance error of the global positioning of the robot on the X axis and the Y axis is less than 10cm, and the angle error is less than 0.2 rad; the error between the grid map and the real environment is less than 1 cm; the deviation degree of the real navigation path of the robot and the algorithm estimated path is less than 10 cm; the mobile robot can carry out loop returning when establishing images in the environment with similar structure; the variance of the point cloud data collected by the laser radar after pretreatment is less than 0.1.
Description
Technical Field
The invention belongs to the technical field of terrain perception, and particularly relates to a terrain perception method, a terrain perception system, a storage medium and computer equipment.
Background
At present, coal resources in China are rich, and coal is still the main energy source in China. In recent years, the coal industry successively puts forward ideas such as mechanization for people, intellectualization for nobody and the like. In 2019, in 1 month, the national coal mine safety administration publishes "coal mine robot key research and development catalogue", and 5 types of 38 coal mine robots for key research and development applications of coal enterprises, scientific research institutions and manufacturing enterprises are published, wherein the inspection robot is one of security control robots.
In recent years, the nation has increased the strength to renovate and standardize the intrinsically safe management of coal mines, and simultaneously, the development of coal mine enterprises to the direction of digitalization and nobody is greatly promoted. In any industry, the inspection work of equipment is generally finished manually, a large amount of human resources are consumed, the work flow is complicated, especially in high-risk industries, risks may exist in the inspection process, and the working environment of personnel is also severe. The underground main drainage system of the coal mine is indispensable important equipment in coal production, the normal production of the mine and the life safety of workers are directly influenced by the operating condition of the underground main drainage system, and in order to ensure the normal operation of a water pump, inspection personnel need to regularly check the operating condition of the equipment, such as the conditions of a water pump packing, a water sump, a motor and the water pump, whether the water pump is abnormal or not. Generally, a water pump room needs several people to take care of and operate, and the working efficiency is low.
With the progress of science and technology, in the power and petrochemical industries, wheel type inspection robots, crawler type inspection robots or rail type hanging inspection robots have numerous application cases, mobile robots perform highly targeted inspection on detected equipment in the inspection process, and the working quality is even more professional than that of people.
Coal mine disasters are frequent, serious damage is caused, risks are large, underground personnel are dense, dangerous posts are multiple, the coal mine water pump house inspection robot can replace inspection workers to inspect equipment and environment, labor intensity of the workers can be effectively relieved, potential safety hazards existing in the inspection process are reduced, inspection quality is improved, and meanwhile the essential safety level of a coal mine enterprise is improved to the maximum extent. The method has important significance for promoting the coal mining technology revolution, realizing the high-quality development of the coal industry, promoting the intelligent process of the coal mine and the national energy safety supply.
From the application environment of the robot, experts at home and abroad divide the robot into two categories, namely an industrial robot in a manufacturing environment and a special robot in a non-manufacturing environment. Research and development of special robots at home and abroad are mainly focused on the fields of exploration and disaster relief, military explosion prevention, reconnaissance and detection and the like. The research and development process of the special mobile robot for realizing the specific functions in the mine is slow due to the special working environment of the coal mine and high-standard requirements on the mobile performance, the communication performance and the explosion-proof performance.
(1) Coal mine detection type robot, in the last 90 th century, the australian federal scientific organization (CSIRO) designed coal mine detection type robot Numbat, and the gas environment under logging is the main work of this robot. The underground information is transmitted back to the ground through the visible light and infrared image sensors, and the underground latest state is informed to rescue team members so as to make a rescue scheme. The power source of the robot is a 140Ah nickel-cadmium battery, the robot walks in a differential eight-wheel structure formed by 750W motors respectively assembled on two sides, the size of the robot is 2.5 multiplied by 1.65m, the speed can reach two kilometers per hour at the fastest speed, and the robot has the cruising ability of 8 hours. The Groundohg coal mine detection robot is developed by the American Kanai-Meilong university robot research institute, is mainly used for underground environment detection and underground three-dimensional map drawing, and is loaded with a laser sensor, a night vision camera, a somatosensory sensor, a gyroscope and the like. Driven by hydraulic pressure, four-wheel differential operation has pivot steering function. Thun et al used it to explore the main roadways of martis mine, california, inc. at 30/5/2003 and completed three-dimensional mapping. In 2005, the first coal mine detection robot CUMT-I of our country was successfully developed by the institute of rescue and equipment, which can detect the environment of the scene after a disaster, be controlled in a remote control manner by being matched with a hazardous gas sensor, a low-illuminance camera and a two-way voice intercom system, and be capable of randomly loading various disaster relief materials (medicines, physical objects or rescue tools), and is a good helper for the rescue team to search and rescue after the disaster. In 2007, a coal mine detection type robot is developed by a Harbin industrial university robot research institute and Tangshan Kaicheng electric appliance Co Ltd, and the robot can detect the environment of a post-disaster site and is matched with a dangerous gas sensor, a low-illumination camera and a two-way voice intercom system. The walking mode is crawler type, and the crawler is divided into three parts of driving, swinging arms and swinging legs. Remote control operation is supported, and remote sensing and control key pressing are realized.
(2) The Ratler coal mine rescue robot is researched and developed by the Ministry of Mine Safety and Health Administration (MSHA) of the U.S. Ministry of labor, a Sangya intelligent system and a robot center (ISRC) together, is mainly used for post-disaster investigation, is provided with an infrared camera, a gyroscope and a dangerous gas sensor, and can be remotely controlled at a maximum distance of 76 meters by a wireless radio frequency device. The suitability test of the robot in Willow Greek coal mine fire rescue in 1998 month shows that the robot can not reach the standard of the coal mining industry for rescue robots. The second generation mobile coal mine disaster relief robot platform Cave Crawler is designed by the university of Carnai Meilong robot research institute, a gear differential mechanism similar to a Mars detection vehicle with a Yongqi number is used in the robot, a rocker type left and right wheel moving system is adopted, and a left rocker and a right rocker are connected with a robot body through the differential mechanism, so that the swing angles of the two rockers are linearly averaged, the swing angles are further converted into the swing angle of the robot body, and the balance of the robot body is kept. When a certain side wheel is lifted, the swing amplitude of the whole vehicle is only half of the lifting amplitude of the wheel, so that the obstruction of the movement of the robot caused by the relief of the terrain is weakened. In addition, such design evenly with on each wheel of automobile body weight distribution robot, and the wheel can be according to its relative position of topography adjustment, make the robot motion more steady, difficult upset, have stronger obstacle-surmounting ability.
(3) The coal mine inspection robot mainly researches a mechanical body of the underground roadway suspension inspection robot in a comprehensive way, and deeply researches a control system of the inspection robot on the basis of carrying out detailed analysis on the body structure, autonomous motion and inspection process control requirements of the suspension inspection robot. The Wangzhi designs a coal mine detection robot which can automatically extend the communication distance and retract automatically to break the limit that the underground coal mine detection robot receives the working stroke. Upon detecting a weakening of the wireless control signal, the robot-mounted repeater ejection system can operate to extend the wireless communication distance. If the wireless signal is terminated, the robot is changed back to start a withdrawing program, and withdraws through the original path according to the sensor data recorded in the operation, so as to return to the safe position with smooth communication. The robot realizes a withdrawing program by using a data integration method of an encoder and a laser sensor, and doubly matches data by relying on an ICP (inductively coupled plasma) algorithm to correct the coordinate and the orientation of the robot so as to achieve sufficient withdrawing precision. From experimental results, the robot is characterized by long working stroke and withdrawing capability, which means that the robot can replace rescuers to go deep into a mine to finish the initial work of danger detection when the safety of a coal mine disaster site is unknown.
The coal mine roadway suspension line inspection robot capable of getting rid of the influence of the complex environment of an underground roadway and the distribution of personnel and equipment is designed by Jiangjunying and the like, so that the problems that the structure and the control of the conventional coal mine roadway wheeled or tracked robot are complex, the reliability is low, the cost is high, and the occupied space is large are solved. They mainly describe the mechanism design of the robot, and a model of a virtual prototype is built in Adams software for simulation analysis so as to evaluate the capability of crossing obstacles in three motion states of horizontal walking and ascending and descending. The result shows that the robot is relatively stable in the three motion states, particularly the robot always keeps constant-speed linear motion in the horizontal direction, and fluctuation within an allowable range can be generated in the vertical and horizontal side-swinging directions. Zhongming quiet and so on designs a rail type unmanned inspection device for solving the problems of inspection and monitoring of the underground belt conveyor, and describes the overall design scheme, capability characteristics and software of the robot. Hardware development approach. The inspection of large-scale equipment such as a belt conveyor, a scraper conveyor and the like in a coal mine can be completed through the inspection robot, so that unattended operation is really and fundamentally realized, the burden of inspection personnel is reduced, and the safety management of the coal mine is improved to the greatest extent.
On the basis of research on problems of workers in a coal mine underground water pump house during patrol, Zxin designs an automatic patrol robot device capable of replacing the workers in patrol, emphatically describes design basis, composition and functions of the robot system, describes implementation modes of software and hardware, data acquisition modes and the like of the robot, can find the problems possibly occurring in the underground water pump house in real time, and guarantees stable and safe operation of the underground water pump house. Under the research of patrolling and inspecting key implementation and supervising problem generation of a coal mine underground water pump room, an intelligent robot which is high in reliability, can replace multiple functions of manual patrolling and inspecting, information acquisition, video patrolling and inspecting, obstacle reporting and the like and integrates is designed, the structure and the action characteristics of the robot equipment are further described, the automatic patrolling and inspecting functions of the robot under different conditions are further described in a research conclusion, and therefore a new mode is opened for unmanned duty and automatic management under a coal mine.
However, the problems of map building and autonomous navigation exist in the prior art; the inspection robot for the water pump house for the mine meets severe natural conditions and complex geological environments, such as a roadway which often has various barriers such as accumulated water, cables, falling rocks, broken coal and the like; the surface gradient of the roadway is large, and the like, so how the inspection robot establishes a two-dimensional map of surrounding obstacles is realized, and meanwhile, a two-dimensional map of rugged terrain is also established.
The robot inevitably meets a slope road section in the walking process, and because the two-dimensional laser radar is used for establishing a map aiming at an obstacle on a horizontal plane in space, the slope is regarded as the obstacle, so that the robot cannot pass through the slope road section, and therefore the inspection robot combines laser radar data (two-dimensional) and depth camera data (three-dimensional) to establish a two-dimensional environment map of the slope.
The autonomous navigation problem: the inspection robot is provided with a camera or an infrared thermal imager to observe equipment, and the size of the electrical equipment in the observation field of view determines the data acquisition precision, so that the inspection robot only embodies the characteristics of avoiding obstacles, having the shortest walking path, having the least time consumption and the like when carrying out global path planning, and also needs to select an appropriate observation distance and an appropriate observation angle to determine the appropriate observation range of each electrical equipment.
The inspection robot starts to avoid static obstacles in a map from an inspection starting point on the premise of ensuring the inspection safety, and safely reaches a target point.
When the robot executes global path planning, rollover can happen inevitably in the process of passing through a dangerous place, and at the moment, the inspection work of the robot is stopped due to rollover, so that the robot automatically turns over to a normal state without human intervention, and continues to navigate to complete the inspection work.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) how to build a two-dimensional map of surrounding obstacles and a two-dimensional map of rugged terrain by the inspection robot.
(2) How to combine laser radar data (two-dimensional) and depth camera data (three-dimensional) by the inspection robot to establish a two-dimensional environment map of a slope.
(3) When the inspection robot carries out global path planning, the inspection robot only reflects the characteristics of obstacle avoidance, shortest walking path, least time consumption and the like, and an appropriate observation range of each electrical device needs to be determined by selecting an appropriate observation distance and an appropriate observation angle.
(4) The inspection robot solves the problem of the staged path planning, namely, a new path is re-planned to reach the next target point by taking the target point which is just reached as a new starting point.
(5) How to automatically turn over the robot to a normal state under the condition of no human intervention, and continue to navigate to finish the inspection work.
The difficulty in solving the above problems and defects is: at present, most inspection robots adopt a radar technology to survey surrounding conditions, but the detection means can only be applied to large, high and static obstacles or obstacles with slow moving speed, and the inspection means cannot be used when the inspection robots encounter obstacles (pedestrians) with more obstacles and fast moving obstacles and lower obstacles (small pits or small holes). However, if the image technology is applied to road condition identification, the problems can be easily solved, because the vision is more comprehensive and more intuitive compared with the laser ranging.
Various obstacles such as a reservoir, a deep well, a cable, falling rocks, crushed coal and the like exist on the ground in the water pump room environment, and the ground is bulged, collapsed, torn and the like due to the movement of a rock stratum. The ground condition can not be detected by the laser radar, and the inspection robot directly passes through the road section, so that the collision or the rollover accident can possibly happen. In a complex ground environment, if the robot wants to independently walk and complete the inspection work of equipment, the information of the road condition of the robot in advance needs to be detected, which is the premise of ensuring the motion safety of the robot.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a terrain awareness method, a terrain awareness system, a terrain awareness storage medium and a terrain awareness computer device.
The invention is realized in such a way that a terrain perception method comprises the following steps:
the method comprises the steps that firstly, a Kinect depth camera is used for obtaining depth information of road surface conditions, a Digital Elevation Model (DEM) is established, grids are divided on the basis of the DEM, danger grade values of terrain information are divided, and automatic identification of road surface danger grades is achieved;
secondly, by combining an odometer auxiliary method with a Kalman filtering algorithm, firstly, propagating the pose of the robot by using odometer data, and realizing pose error correction according to the matching of laser radar data and an environment map;
and step three, SLAM mapping and navigation algorithm optimization in the ROS.
Further, in the first step, the calculated terrain information is used as a main index of the path planning of the robot.
Further, in the third step, the SLAM mapping and navigation algorithm in the ROS are optimized, and the specific process is as follows:
establishing constraints among the pose, the natural features and the artificial features of the robot in a graph optimization mode, and then carrying out global optimization to obtain a map with global consistency; heuristic information is added into a path planning algorithm to guide the searching direction; and then, formulating a test environment design and performance evaluation standard, carrying out comparative analysis on experimental results in the aspects of mapping efficiency, navigation strategy and the like aiming at the improved algorithm and the original algorithm, and finally optimizing the ROS system and the program related to the single chip microcomputer.
Another object of the present invention is to provide a terrain awareness system for implementing the terrain awareness method, the terrain awareness system being provided with:
a main body;
the two sides of the main body are provided with rollers which are sleeved with tracks; the main part front side is installed laser radar and Kinect camera.
Another object of the present invention is to provide a program storage medium for receiving a user input, the stored computer program causing an electronic device to execute the terrain awareness method, comprising the steps of:
the method comprises the steps that firstly, data information related to terrain parameters is obtained by using a Kinect depth camera, and automatic identification of road surface danger levels is achieved;
step two, removing the motion distortion of the laser radar by combining a speedometer auxiliary method with a Kalman filtering algorithm;
and step three, SLAM mapping and navigation algorithm optimization in the ROS.
It is a further object of the invention to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing said terrain awareness method when executed on an electronic device.
By combining all the technical schemes, the invention has the advantages and positive effects that: in the invention, the distance error of the global positioning of the robot on the X axis and the Y axis is less than 10cm, and the angle error is less than 0.2 rad; the error between the grid map and the real environment is less than 1 cm; the deviation degree of the real navigation path of the robot and the algorithm estimated path is less than 10 cm; the mobile robot can carry out loop returning when establishing images in the environment with similar structure; the variance of the point cloud data collected by the laser radar after pretreatment is less than 0.1.
The invention establishes a terrain perception system which can identify the obstacles in the traveling direction of the inspection robot; establishing a motion planning model taking the path length of a rugged ground and the danger level of the robot as indexes when the robot passes through the road surface, and planning the shortest path between a starting point and an end point under the condition of ensuring the safety of a walking route of the inspection robot; calibrating the odometer by adopting an iterative least square method to reduce the accumulated error of the robot odometer, establishing constraints among the pose, natural features and artificial features of the robot by using a graph optimization mode, and then performing global optimization on the map to finally obtain a map with global consistency; the underground coal mine inspection robot can carry out inspection work on water pump room equipment under the conditions of unmanned control, no track, cable and GPS assistance through SLAM image building and navigation algorithms.
Drawings
Fig. 1 is a flowchart of a terrain awareness method according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a terrain awareness system according to an embodiment of the present invention.
In fig. 2: 1. a main body; 2. a roller; 3. a crawler belt; 4. a laser radar; 5. kinect camera.
Fig. 3 is a schematic view of ground sensing of an unmanned vehicle according to an embodiment of the present invention.
Fig. 4 is a schematic view of sensing the ground of the water pump house inspection robot provided by the embodiment of the invention.
Fig. 5 is a schematic diagram of a path planning index of the ROS algorithm without ground sensing according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of a path planning index of the ROS algorithm in the presence of ground awareness according to an embodiment of the present invention.
Fig. 7 is a schematic diagram of topographic information provided by the embodiment of the present invention.
Fig. 8 is a constraint schematic diagram of a pose of a robot in SLAM mapping provided in an embodiment of the present invention.
Fig. 9 is a schematic diagram of a principle of an a shortest path search algorithm according to an embodiment of the present invention.
Fig. 10 is a block diagram of a technical route provided by an embodiment of the present invention.
Fig. 11 is a schematic diagram illustrating an effect of path planning by combining terrain factors according to an embodiment of the present invention.
Fig. 12 is a schematic diagram illustrating comparison of before and after effects of laser radar motion distortion removal according to an embodiment of the present invention.
Fig. 13 is a schematic diagram for comparing before and after the optimization effect provided by the embodiment of the present invention.
Fig. 14 is a schematic diagram of a simulation result of the PRM path planning algorithm provided in the embodiment of the present invention.
Fig. 15 is a schematic path diagram generated by the PRM path planning algorithm according to the embodiment of the present invention.
Fig. 16 is a schematic diagram of a simulation result of the Pure Persuit path tracking algorithm provided in the embodiment of the present invention.
Fig. 17 is a schematic diagram of path tracking process analysis of the Pure Persuit algorithm according to the embodiment of the present invention.
Fig. 18 is a schematic diagram of a simulation result of an obstacle avoidance algorithm according to an embodiment of the present invention.
Fig. 19 is a schematic diagram of process analysis of an obstacle avoidance algorithm according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In view of the problems in the prior art, the present invention provides a terrain awareness method, system, storage medium, and computer device, and the present invention is described in detail below with reference to the accompanying drawings.
Those skilled in the art can also implement the terrain awareness method provided by the present invention by using other steps, and the terrain awareness method provided by the present invention in fig. 1 is only one specific embodiment.
As shown in fig. 1, a terrain sensing method provided in an embodiment of the present invention includes:
s101: and obtaining data information related to terrain parameters by using a Kinect depth camera, and realizing automatic identification of the road surface danger level.
S102: and removing the motion distortion of the laser radar by combining a speedometer auxiliary method with a Kalman filtering algorithm.
S103: and (4) SLAM mapping in ROS and optimization of a navigation algorithm.
In S101 provided by the embodiment of the present invention, the calculated terrain information is used as a main index for path planning of the robot.
In S103 provided by the embodiment of the present invention, the SLAM mapping and the navigation algorithm in the ROS are optimized, and the specific process is as follows:
establishing constraints among the pose, the natural features and the artificial features of the robot in a graph optimization mode, and then carrying out global optimization to obtain a map with global consistency; heuristic information is added into a path planning algorithm to guide the searching direction and reduce the time of global path planning; and then, formulating a test environment design and performance evaluation standard, carrying out comparative analysis on experimental results in the aspects of mapping efficiency, navigation strategy and the like aiming at the improved algorithm and the original algorithm, and finally optimizing the ROS system and the program related to the single chip microcomputer.
As shown in fig. 2, in the terrain awareness system provided by the embodiment of the present invention, rollers 2 are disposed on two sides of a main body 1, and a track 3 is sleeved on each roller 2; the main body 1 is provided with a laser radar 4 and a Kinect camera 5 on the front side.
The technical solution of the present invention is further described with reference to the following specific examples.
1. The problem of robot navigation is the technique and method of guiding a mobile robot from a starting point to a target point. In recent years, scholars at home and abroad summarize the navigation problem into three problems: (1) a positioning problem; (2) identification of the target; (3) and (4) path planning.
The positioning problem is the most basic problem of the mobile robot for realizing the autonomous ability and is the core of the robot navigation problem. The following three types are generally classified according to the positioning mode:
(1) and (4) relative positioning. Dead-Reckoning (DR), which mainly depends on body sensors such as encoders, gyroscopes and accelerometers, and estimates information such as the current time position and attitude of the mobile robot by measuring information such as relative distance, angular velocity and linear acceleration according to initial state information;
(2) and (6) absolute positioning. The principle of the absolute positioning is that the absolute position information of the robot is determined by using technical methods such as navigation beacons, map matching or satellite positioning;
(3) and (6) positioning in a combined mode. The relative positioning is carried out according to a robot kinematic model and an internal sensor, signals are not interfered by the outside, and errors are accumulated along with time.
The development trend of mobile robot navigation mainly includes the following aspects:
(1) real-time, accurate and stable navigation. There are many common navigation methods, but each has certain limitations. Therefore, the accuracy of the sensor is improved, and meanwhile, some intelligent algorithms are added to be applied to the navigation task.
(2) And various navigation modes are matched for use. The single navigation technology often has its inherent limitation, and not only must perfect single navigation mode, but also must comprehensively use multiple navigation modes to combine together, adopt multiple sensors, compensate respective shortcoming each other, it is that navigation system has more stable, can accomplish the navigation task in more complicated changeable environment.
(3) With the maturity of network technology and wireless technology, the remote control of the robot can be realized by using the network and wireless technology, which is also a development direction of the mobile robot navigation technology.
(4) The modularization problem of the system. Because the navigation system can be divided into a plurality of modules of different levels, in order to achieve a certain degree of uniformity and universality, the problem of researching the modularization of navigation and the uniformity of interfaces thereof is also the key point of future research.
2. Content providing method and apparatus
(1) Mobile robot platform kinematics and dynamics analysis
According to the research foundation of the main technical indexes and parameters of the existing inspection robot for the mining water pump house, the following relevant researches are firstly carried out on the inspection robot.
1) Design wheeled mining water pump room inspection robot simulation platform
The UG three-dimensional model of the water pump room inspection robot is designed according to the size of a sensor carried on the water pump room inspection robot and the size of each part of the inspection robot, the whole inspection robot is subjected to static finite element analysis, and finally the stress and strain diagram of each part is obtained, so that whether the type selection of each part is reasonable or not is determined.
2) Robot platform model kinematics and dynamics analysis
The UG three-dimensional model is imported into ADAMS software, and the robot platform model is subjected to kinematic analysis, so that whether each part of the robot conflicts in the motion process is determined, and whether the part type selection is reasonable is further determined; the change of the driving force of the robot in the processes of walking, obstacle crossing and stair climbing can be obtained by performing dynamics analysis on the robot platform, so that reference is provided for the selection of the power of the driving wheel motor of the robot.
(2) Terrain perception method
For better path planning of the robot, the following related studies are to be performed:
1) collecting data information about terrain parameters
The water pump room ground and the ground conditions in the laboratory have obvious differences, the former ground has various obstacles such as a reservoir, a deep well, a cable, falling rocks, crushed coal and the like, and rock stratum movement can cause the ground to bulge, collapse, tear and the like. If the height of the ground bulge is smaller than that of the vehicle body, the ground bulge cannot be detected by the laser radar, and the inspection robot can directly pass through the road section, so that collision or rollover accidents are possible; if the ground is sunken, the inspection robot passes through the road section during navigation, possibly being clamped in the sunken part and being incapable of advancing. Therefore, in order to autonomously walk and complete equipment inspection work under a complex ground environment, the ground condition information of the environment where the robot is located must be considered, which is a precondition for ensuring the motion safety of the robot. Data information on the terrain parameters needs to be collected, and morphological characteristics of the raised ground and the depressed ground are specifically analyzed.
2) Method and process for researching and realizing automatic identification of pavement danger level
Unmanned vehicle ground sensing
A laser radar sensor downward sloping 15 installs at vehicle the place ahead bumper for the barrier is kept away to the place ahead, leaves ground 1.2m, can be to the state on the tunnel ground of the 4.5m within range in the place ahead. From the picture can know that the whole plane of strafing of laser is 15 with the contained angle on road surface and is used for installing the top central point at the vehicle to the CCD camera sensor of the recognition of place ahead object, ground clearance 1.6m, because the visual angle of camera is 30, for jointly discerning with the laser radar sensor, so need let the installation of camera downward sloping 17, guarantee that the identification point of camera can be synchronous with laser radar sensor perception point, be used for better discernment to the place ahead object, correspond with laser radar discernment road surface, can be better to the ground obstacle discernment in the preceding 4.5m of vehicle, as shown in figure 3.
Second, the ground sensing of the inspection robot of the water pump house
And designing a ground sensing scheme of the ROS inspection robot according to the ground sensing scheme of the unmanned automobile. The ROS inspection robot is provided with the two-dimensional laser, the radar cannot detect the ground condition like a three-dimensional laser radar, so that the two-dimensional laser radar can be loaded on the upper part of a vehicle body, a diagram is built for surrounding obstacles higher than the vehicle body, a Kinect depth camera is arranged in front of the vehicle body of the inspection robot, and the Kinect depth camera is used for detecting the ground condition, as shown in figure 4.
Thirdly, establishing a map of complex ground conditions
As shown in fig. 5, the general algorithm in the ROS does not consider the ground condition factor, the established map only contains obstacle information with a height greater than the height of the ROS body, and the reference index during path planning is only the shortest path and has no obstacle. Considering that the inspection robot may pass through a raised road section and a depressed road section of the ground during the course of executing the path, causing accidents of rollover and trucks, it is necessary to map a complicated ground condition.
Therefore, in the robot mapping process, the two-dimensional laser radar is responsible for building a surrounding two-dimensional obstacle map, the Kinect installed at the front end of the ROS inspection robot is responsible for building a ground map, the trafficability of the robot to a walking area is evaluated through three indexes of a flat ground, the shortest path and no obstacle, the passable area and the non-passable area are divided, and the robot path is ensured to be planned to obtain the optimal path, as shown in FIG. 5.
3) Calculation method and implementation of terrain information perception obtained by research and calculation
The geomorphic morphology is measured by considering three aspects of height, ground surface inclined orientation and degree, ground plane shape and area. In the process of the robot technology research, the terrain is not only in a state of undulation, but also in consideration of contents such as ground material. Therefore, the problems of robot obstacle avoidance, path planning and the like can be researched. The representation of the terrain features comprises the contents of terrain relief degree, terrain texture, terrain gradient and the like, and the contents of the three aspects can effectively represent the terrain information features. The terrain information is mainly represented by a digital elevation model DEM which is mainly based on regular grids, and each grid has an average elevation corresponding to a grid area. The grids are divided on the basis of the DEM, so that the D value is obviously influenced by the terrain slope S (slip constraint), the undulation H (step height and obstacle edge constraint) and the roughness R (body stability constraint), and under the ordinary condition, the 3 multiplied by 3DEM grid is used for numerical calculation, and the specific situation is shown in figure 7, wherein e0To e8Is the height value of the grid in this area.
(3) Lidar data preprocessing research
To remove the lidar motion distortion, the following correlation studies are to be performed:
1) high-precision and high-adaptability filter algorithm research
In the process of collecting two-dimensional point cloud data, the laser radar is influenced by interference, so that certain noise can appear when the data are obtained. Therefore, in actual work, besides the self-measurement error, the method can be influenced by external environment, such as the sheltered target, the material of the surface of the obstacle and the measured target, and other influencing factors, in addition, some local large-scale noises are far away from the target point cloud, and the local large-scale noises cannot be filtered by using the same method, so that a high-precision and high-adaptability filtering algorithm is required to be selected for filtering the two-dimensional point cloud data.
2) Odometer auxiliary method and Kalman filtering combined algorithm research
The single chip microcomputer is used for reading the laser radar data, the pose of the robot at that time can be obtained when the laser point data is read every time, motion distortion is eliminated according to the pose of the robot, and a frame of complete data is obtained and uploaded to the processor. Motion distortion is eliminated on a single chip microcomputer layer, the time synchronization problem does not need to be considered, data needs to be compressed, and otherwise, large delay is generated.
Solving the robot pose corresponding to each laser point in the current frame laser data, namely solving the { t }s,ts+Δt,…teAnd converting all laser points to the same coordinate system according to the pose solved by the pose of the robot at the moment, repackaging the laser points into a frame of laser data, and issuing the frame of laser data. Let psAnd ps+1Between which there are N poses { ps,ps1,…,ps(n-2),psn,ps+1And then: n laser points of a frame of laser data, and the corresponding pose { p of each laser point1,p2,…,pnIs interpolated by the method described above to obtain xi as the coordinate before conversion, x'iTo coordinates after transformation, thenAnd converting the converted coordinates into laser data to be issued:
(4) SLAM mapping and navigation algorithm optimization design in ROS system
1) The position and posture, the natural characteristics and the artificial characteristics of the robot are researched to carry out constraint and global optimization so as to obtain a map with global consistency
As shown in fig. 8, the laser radar can extract features such as angular points, line segments, and arcs as natural beacons for positioning and navigation of the robot. Among the features formed by various geometric elements, the line segment feature is a simple and easily recognized feature, and can effectively describe the structured environment. After natural features in the laser radar scanning data are extracted, the features in the scanning data at adjacent moments are matched to solve the coordinate transformation relation among the features, so that the position of the robot can be determined in an incremental mode, and the positioning purpose of the robot is achieved. Besides extracting natural features such as points and line segments existing in the environment for data association, the front-end algorithm of the laser SLAM can also extract artificial features for data association. Artificial features are some markers, also called artificial beacons, that are artificially arranged in the environment. Compared with natural features, the artificial features have the characteristics of easy extraction and easy matching, and can be applied to complex unstructured environments. When the natural features in the working environment of the robot are not rich enough, some artificial beacons can be arranged in the environment, and the SLAM algorithm can perform positioning navigation by extracting the artificial features, so that the robustness of the SLAM algorithm can be effectively improved.
2) Researching a path planning algorithm integrated with heuristic information to acquire a guidance search direction and reduce the time of global path planning
The cost value is evaluated to search for the nearest path through a heuristic search A algorithm. For any point, F is G + H; f denotes the cost to the target point, G denotes the distance to move from the starting point to the point, and H denotes the distance from the point to the target point, the distance being calculated using manhattan distance, i.e. the sum of the number of horizontal and vertical squares between the current grid and the target grid. The principle of the shortest path search algorithm is shown in fig. 9.
3. Target
(1) By researching a mapping algorithm (SLAM), the inspection robot can be accurately positioned in the water pump room, and a two-dimensional grid map of the water pump room is established on the basis.
(2) By researching a path planning algorithm (PRM), a path passing through all the water pump room equipment can be planned in the water pump room with the built two-dimensional grid map.
(3) By researching a path tracking algorithm (Pure Persui), the robot can be controlled to move according to a planned path, and meanwhile, obstacles can be avoided in time when the obstacles suddenly appear on the planned path.
4. Key problem to be solved
(1) Problem of drawing
Firstly, the inspection robot for the water pump house for the mine meets severe natural conditions and complex geological environments, such as roadways which often have various barriers such as accumulated water, cables, fallen rocks and broken coal; the surface gradient of the roadway is large, and the like, so that how to establish a two-dimensional map of surrounding obstacles and a two-dimensional map of rugged terrain is also established by the inspection robot is one of the key problems to be solved by the invention.
Secondly, the robot inevitably meets a slope section in the walking process, and because the two-dimensional laser radar is used for establishing a map aiming at an obstacle on a horizontal plane in the space, the slope is regarded as the obstacle, so that the robot cannot pass through the slope section, and therefore how the inspection robot combines laser radar data (two-dimensional) and depth camera data (three-dimensional) to establish a two-dimensional environment map of the slope is the second key problem to be solved by the invention.
(2) Problem of autonomous navigation
The inspection robot is provided with a camera or an infrared thermal imager to observe equipment, and the size of the electrical equipment in an observation visual field determines the data acquisition precision, so that the inspection robot only shows the characteristics of avoiding obstacles, having the shortest walking path, using the least time and the like when carrying out global path planning, and an appropriate observation distance and an observation angle are required to be selected to determine the appropriate observation range of each electrical equipment, which is the third key problem to be solved by the invention.
Secondly, the inspection robot avoids static obstacles in a map from the starting point of inspection and safely reaches a target point on the premise of ensuring the inspection safety, and because a plurality of devices are generally arranged in a factory building, a plurality of target points exist, so that the inspection robot solves the problem of staged path planning, namely, the target point which is just reached is taken as a new starting point, and a new path is re-planned to reach the next target point, which is the fourth key problem to be solved by the invention.
And thirdly, when the robot performs global path planning, rollover can inevitably occur in the process of passing through a dangerous place, and at the moment, the inspection work of the robot is stopped because of rollover, so that the robot automatically turns to a normal state without human intervention and continues to navigate to finish the inspection work.
5. Method, technical route, experimental scheme and feasibility analysis
5.1 methods
The invention aims to carry out a research method combining theoretical analysis, algorithm design, experimental research and simulation so as to solve the key problem when the positioning and navigation algorithm in the ROS is applied to the inspection of the underground equipment of the coal mine. According to the composition structure of the ROS inspection robot, main research contents are perfected according to a working process and a real-time environment, a three-dimensional model of the ROS robot is established, physical parameters of the model are set, simulation of an algorithm is achieved by combining Matlab and Gazebo, and an optimal algorithm suitable for the inspection of the ROS inspection robot in the underground coal mine water pump house is found out.
5.2 technical route, as shown in FIG. 10;
5.3 protocol
(1) Platform kinematics and dynamics analysis of water pump house inspection robot
According to main technical indexes and parameters of the water pump house inspection robot, a wheeled coal mine water pump house inspection robot simulation platform is designed, and kinematics and dynamics analysis is carried out on a robot platform model. The method comprises the steps of three-dimensional model design, kinematic model establishment and dynamic model establishment. A three-dimensional model of a motion chassis of the water pump room inspection robot is shown in figure 2.
(2) Study of terrain awareness method
And obtaining data information related to terrain parameters by using a Kinect depth camera, and realizing automatic identification of the road surface danger level. And taking the calculated terrain information as a main index of the path planning of the robot. The effect of path planning in combination with terrain factors is shown in fig. 11.
(3) Pre-processing of lidar data
And removing the motion distortion of the laser radar by combining a speedometer auxiliary method with a Kalman filtering algorithm. The laser radar motion distortion removal front-to-back effect pair is shown in fig. 12.
(4) SLAM mapping and navigation algorithm optimization in ROS
Establishing constraints among the pose, the natural features and the artificial features of the robot in a graph optimization mode, and then carrying out global optimization to obtain a map with global consistency; heuristic information is added into a path planning algorithm to guide the searching direction and reduce the time of global path planning; and then, formulating a test environment design and performance evaluation standard, carrying out comparative analysis on experimental results in the aspects of mapping efficiency, navigation strategy and the like aiming at the improved algorithm and the original algorithm, and finally optimizing the ROS system and the program related to the single chip microcomputer. The map-creation effect pair before and after map optimization is shown in fig. 13.
6. Feasibility analysis
6.1 feasibility of theoretical study
The established three-dimensional model of the water pump house inspection robot is subjected to statics, kinematics and dynamics simulation in the aspect of a robot body, so that the motion characteristics of the inspection robot can be continuously optimized, the inspection robot can reach performance indexes required by the water pump house inspection robot, in the aspect of algorithm, the project adopts SLAM mapping and navigation algorithm which are open in ROS, the algorithm is widely applied to indoor floor-sweeping robots, and if the algorithm is used for the underground coal mine water pump house equipment inspection robot, the original SLAM mapping and navigation algorithm must be properly adjusted due to the change of working environment.
Meanwhile, the design of the invention is scientific and reasonable, the research of the construction and navigation algorithm of the water pump house inspection robot can liberate the water pump house inspection personnel from the daily simple, mechanical and repetitive work, so that the invention is convenient for people to concentrate on processing more important and complex work, and has important significance for strengthening the safety management of coal mine production and really realizing personnel reduction, efficiency improvement, energy conservation and consumption reduction.
6.2 feasibility of practical study
The national and local united engineering laboratory for mine fluid control has been equipped with a variety of electromechanical equipment testing conditions, with experience in many years in industrial automation. Existing equipment has NI, can be tested and measured, provides a modular hardware platform and system design software (LabVIEW). Can be used for carrying out experiments to meet the overall requirements.
7. The method is researched aiming at SLAM mapping and autonomous navigation algorithm of the underground coal mine water pump house inspection robot, and has the following main innovation points:
(1) and a terrain perception system is established, so that obstacles, slopes, roughness and danger levels in the traveling direction of the inspection robot can be identified.
(2) Based on terrain perception information of the inspection robot, a motion planning model which takes the optimized length of a path on the rugged ground and the danger level of the robot passing through the road as indexes is established, and meanwhile, the shortest path between a starting point and a terminal point is planned under the condition that the safety of the walking route of the inspection robot is guaranteed.
(3) The method comprises the steps of calibrating the odometer by a linear least square method to reduce accumulated errors of the robot odometer, establishing constraints among the pose, natural features and artificial features of the robot by using a graph optimization mode, and then performing global optimization on a map to finally obtain a map with global consistency.
(4) A two-dimensional grid map of the water pump room is established by using a laser radar through a SLAM algorithm, then a path passing through all the water pump room devices is obtained in the grid map through a path planning algorithm, and finally the robot is controlled to track the path through a path tracking algorithm to reach the position of each water pump room device. The underground inspection robot for the coal mine can inspect the water pump house equipment under the conditions of unmanned control, no track, no cable and GPS assistance.
The technical solution of the present invention is further described below with reference to simulation experiments.
1. Work foundation
The structural design of a prototype of the water pump house inspection robot is already completed, meanwhile, the simulation of a path planning algorithm, a path tracking algorithm and an obstacle avoidance algorithm is completed in Matlab, and the simulation of an SLAM mapping algorithm is completed in the next step.
1.1 PRM Path planning Algorithm simulation
Before path planning, firstly expanding a two-dimensional grid map of a water pump room according to the size of the robot to prevent the robot from colliding with obstacles at corners during path tracking, then sending the expanded map to a PRM path planning algorithm, and setting starting points (1.2, 2.4) and end points (2.7, 3.3) of a planned path, wherein the number of random points generated by the PRM path planning algorithm is 800, and the simulation result of the PRM path planning algorithm is shown in FIG. 14. In fig. 15, it can be seen that the path is composed of a series of coordinate points, and these coordinate points play an important role in the following path tracking.
1.2 Pure Persutit Path tracking Algorithm simulation
Before path tracking, a two-wheel differential robot model is generated in the matlab, the diameter of the robot is set to be 0.2m, the robot can obtain the pose under a world coordinate system at any moment through a speedometer, and the pose can judge whether the robot reaches a target point or not; storing the planned path from the point 4 to the point 6 into a Pure Persutit path tracking algorithm, wherein the planned path from the point 4 to the point 6 is formed by connecting lines of a plurality of coordinate points, the coordinate points are generated by a PRM algorithm and are target points to be tracked by the Pure Persutit algorithm; the linear velocity of the robot during path tracking is set to 0.1m/s, the maximum angular velocity is set to 1rad/s, the distance threshold is set to 0.01m, and the simulation result obtained by executing the Pure Persut algorithm is shown in FIG. 16.
Figure 17 shows the change of attitude angle, angular velocity and linear velocity at each moment when the Pure Persuit path tracking algorithm controls the robot to track the path 4 and the path 5, in the interval 1, the robot is at the starting point, the pose (X, y, theta) is (1.2, 2.4, 0), the original path pose angle (the included angle between the original path and the X axis of the world coordinate system) is greater than the pose angle of the robot (the included angle between the X axis of the robot coordinate system and the X axis of the world coordinate system), therefore, the rotation angular velocity of the robot given by the Pure Persutit path tracking controller is more than 0, the robot rotates in the anticlockwise direction, the attitude angle of the robot is increased, in the interval 2, the attitude angle of the robot is equal to the attitude angle of the original path, the rotation angular velocity of the robot given by the Pure Persutit path tracking controller is equal to 0, the linear velocity is 0.1m/s and remains unchanged, and the robot moves along the original path. In the section 3, since the attitude angle of the original path is further increased, the rotation angular velocity of the robot given by the Pure Persuit path tracking controller is greater than 0, the robot rotates counterclockwise, and the attitude angle of the robot is also increased. In the interval 4, the attitude angle of the robot is equal to the attitude angle of the original path, the rotation angular velocity of the robot given by the Pure Persutit path tracking controller is equal to 0, the linear velocity is still unchanged, and the robot moves along the original path. In the same way, the attitude angle of the original path is changed in the section 5, and meanwhile, the Pure Persutit path tracking controller also gives different rotation angular velocities of the robot, so that the attitude angle of the robot is finally equal to the attitude angle of the original path. In the interval 6, the robot reaches the final end point of the original path, the linear velocity and the angular velocity are both 0, and the final attitude angle of the robot is still equal to the attitude angle of the original path.
1.3 simulation of obstacle avoidance algorithm
The obstacle avoidance of the robot means that when the robot carries out path tracking, if the laser radar detects that an obstacle exists in front of the robot, an obstacle avoidance algorithm is operated to control the robot to bypass the obstacle, and then the original path is continuously tracked. And tracking a path 2 and a path 3 by a Pure Persuit path tracking algorithm, and setting an obstacle on the path 2 for simulating an obstacle avoidance algorithm. The simulation results are shown in fig. 18.
FIG. 19 shows the attitude angle of the robot and the distance between the front, right and left sides of the robot and the obstacle at each time during obstacle avoidance, with a distance threshold of 0.1m being set, the lidar sensor being turned on, the distance between each position of the robot and the obstacle being obtained by analyzing the data of the lidar sensor, the robot being in a path tracking stage when the distance is greater than the distance threshold, with the path tracking algorithm controlling the robot to move along the original path, and the robot being in an obstacle avoidance stage when the distance between the front or left side of the robot and the obstacle is less than the distance threshold, starting to execute the obstacle avoidance algorithm and stopping executing the path tracking algorithm, with the right side of the robot and the obstacle being significantly greater than the front and left sides, the robot turning right (clockwise rotation), the attitude angle of the robot being reduced, the robot turning left after moving forward a distance, and when the distance between each position of the robot and the obstacle is detected to be larger than the distance threshold value, the robot is indicated to bypass the obstacle, the robot returns to the path tracking stage, the obstacle avoidance algorithm is stopped, and the path tracking algorithm is continuously executed.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. A terrain perception method, comprising:
data information related to terrain parameters is obtained by using a Kinect depth camera, and automatic identification of road surface danger levels is achieved;
removing the motion distortion of the laser radar by combining a speedometer auxiliary method with a Kalman filtering algorithm;
and (4) SLAM mapping in ROS and optimization of a navigation algorithm.
2. The terrain awareness method of claim 1, wherein the calculated terrain information is used as a primary indicator for path planning of the robot.
3. The terrain awareness method of claim 1, wherein SLAM mapping and navigation algorithm optimization in ROS comprises: establishing constraints among the pose, the natural features and the artificial features of the robot in a graph optimization mode, and then carrying out global optimization to obtain a map with global consistency; heuristic information is added into a path planning algorithm to guide the searching direction; and then, formulating a test environment design and performance evaluation standard, carrying out comparative analysis on experimental results in the aspects of mapping efficiency, navigation strategy and the like aiming at the improved algorithm and the original algorithm, and finally optimizing the ROS system and the program related to the single chip microcomputer.
4. A terrain awareness system for implementing the terrain awareness method according to any one of claims 1 to 3, wherein the terrain awareness system is provided with:
a main body;
the two sides of the main body are provided with rollers which are sleeved with tracks; the main part front side is installed laser radar and Kinect camera.
5. A program storage medium for receiving user input, the stored computer program causing an electronic device to perform the terrain awareness method of any of claims 1-3, comprising the steps of:
the method comprises the steps that firstly, data information related to terrain parameters is obtained by using a Kinect depth camera, and automatic identification of road surface danger levels is achieved;
step two, removing the motion distortion of the laser radar by combining a speedometer auxiliary method with a Kalman filtering algorithm;
and step three, SLAM mapping and navigation algorithm optimization in the ROS.
6. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing a terrain awareness method as claimed in any one of claims 1 to 3 when executed on an electronic device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110710851.5A CN113465728B (en) | 2021-06-25 | 2021-06-25 | Terrain awareness method, system, storage medium and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110710851.5A CN113465728B (en) | 2021-06-25 | 2021-06-25 | Terrain awareness method, system, storage medium and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113465728A true CN113465728A (en) | 2021-10-01 |
CN113465728B CN113465728B (en) | 2023-08-04 |
Family
ID=77872965
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110710851.5A Active CN113465728B (en) | 2021-06-25 | 2021-06-25 | Terrain awareness method, system, storage medium and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113465728B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114004874A (en) * | 2021-12-30 | 2022-02-01 | 贝壳技术有限公司 | Acquisition method and device of occupied grid map |
CN114863657A (en) * | 2022-05-20 | 2022-08-05 | 深圳市威宇智通科技有限公司 | Vehicle traffic accident remote taking-over rescue system based on 4G and 5G internet of vehicles |
CN114952867A (en) * | 2022-07-26 | 2022-08-30 | 中国工业互联网研究院 | Control method and device for industrial robot, electronic equipment and readable storage medium |
CN116543018A (en) * | 2023-05-08 | 2023-08-04 | 重庆市二零八地质环境研究院有限公司 | High-steep dangerous rock collapse movement analysis method based on video feature point dynamic tracking |
CN117270576A (en) * | 2023-11-22 | 2023-12-22 | 自然资源部第三地形测量队(黑龙江第二测绘工程院) | Control method and control terminal of terrain measurement unmanned aerial vehicle |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105865449A (en) * | 2016-04-01 | 2016-08-17 | 深圳杉川科技有限公司 | Laser and vision-based hybrid location method for mobile robot |
CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
WO2018121448A1 (en) * | 2016-12-30 | 2018-07-05 | 深圳市杉川机器人有限公司 | Topology map creation method and navigation method for mobile robot, programmable device, and computer readable medium |
CN109729322A (en) * | 2019-02-20 | 2019-05-07 | 重庆工程职业技术学院 | Coal mine visual monitor system and method |
CN109798909A (en) * | 2019-02-01 | 2019-05-24 | 安徽达特智能科技有限公司 | A kind of method of global path planning |
CN109839118A (en) * | 2017-11-24 | 2019-06-04 | 北京京东尚科信息技术有限公司 | Paths planning method, system, robot and computer readable storage medium |
CN109900280A (en) * | 2019-03-27 | 2019-06-18 | 浙江大学 | A kind of livestock and poultry information Perception robot and map constructing method based on independent navigation |
CN111582123A (en) * | 2020-04-29 | 2020-08-25 | 华南理工大学 | AGV positioning method based on beacon identification and visual SLAM |
CN112347840A (en) * | 2020-08-25 | 2021-02-09 | 天津大学 | Vision sensor laser radar integrated unmanned aerial vehicle positioning and image building device and method |
US20210080263A1 (en) * | 2019-09-17 | 2021-03-18 | Baidu Usa Llc | Estimated time of arrival based on history |
CN112525202A (en) * | 2020-12-21 | 2021-03-19 | 北京工商大学 | SLAM positioning and navigation method and system based on multi-sensor fusion |
CN112518739A (en) * | 2020-10-22 | 2021-03-19 | 新兴际华集团有限公司 | Intelligent self-navigation method for reconnaissance of tracked chassis robot |
CN112985410A (en) * | 2021-03-02 | 2021-06-18 | 哈尔滨理工大学 | Indoor robot self-map-building navigation system based on laser SLAM |
CN112987763A (en) * | 2021-05-11 | 2021-06-18 | 南京理工大学紫金学院 | ROS-based intelligent trolley of autonomous navigation robot control system |
-
2021
- 2021-06-25 CN CN202110710851.5A patent/CN113465728B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105865449A (en) * | 2016-04-01 | 2016-08-17 | 深圳杉川科技有限公司 | Laser and vision-based hybrid location method for mobile robot |
WO2018121448A1 (en) * | 2016-12-30 | 2018-07-05 | 深圳市杉川机器人有限公司 | Topology map creation method and navigation method for mobile robot, programmable device, and computer readable medium |
CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
CN109839118A (en) * | 2017-11-24 | 2019-06-04 | 北京京东尚科信息技术有限公司 | Paths planning method, system, robot and computer readable storage medium |
CN109798909A (en) * | 2019-02-01 | 2019-05-24 | 安徽达特智能科技有限公司 | A kind of method of global path planning |
CN109729322A (en) * | 2019-02-20 | 2019-05-07 | 重庆工程职业技术学院 | Coal mine visual monitor system and method |
CN109900280A (en) * | 2019-03-27 | 2019-06-18 | 浙江大学 | A kind of livestock and poultry information Perception robot and map constructing method based on independent navigation |
US20210080263A1 (en) * | 2019-09-17 | 2021-03-18 | Baidu Usa Llc | Estimated time of arrival based on history |
CN111582123A (en) * | 2020-04-29 | 2020-08-25 | 华南理工大学 | AGV positioning method based on beacon identification and visual SLAM |
CN112347840A (en) * | 2020-08-25 | 2021-02-09 | 天津大学 | Vision sensor laser radar integrated unmanned aerial vehicle positioning and image building device and method |
CN112518739A (en) * | 2020-10-22 | 2021-03-19 | 新兴际华集团有限公司 | Intelligent self-navigation method for reconnaissance of tracked chassis robot |
CN112525202A (en) * | 2020-12-21 | 2021-03-19 | 北京工商大学 | SLAM positioning and navigation method and system based on multi-sensor fusion |
CN112985410A (en) * | 2021-03-02 | 2021-06-18 | 哈尔滨理工大学 | Indoor robot self-map-building navigation system based on laser SLAM |
CN112987763A (en) * | 2021-05-11 | 2021-06-18 | 南京理工大学紫金学院 | ROS-based intelligent trolley of autonomous navigation robot control system |
Non-Patent Citations (6)
Title |
---|
JUNG, SUNGWOOK: "Toward Autonomous Bridge Inspection: A framework and experimental results", 2019 16TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS (UR) * |
SHIBO HAN: "Monocular SLAM and Obstacle Removal for Indoor Navigation", 《2018 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND DATA ENGINEERING (ICMLDE) 》 * |
SHIBO HAN: "Monocular SLAM and Obstacle Removal for Indoor Navigation", 《2018 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND DATA ENGINEERING (ICMLDE) 》, 17 February 2019 (2019-02-17) * |
潘祥生: "矿用智能巡检机器人关键技术研究", 工矿自动化 * |
罗进等: "标准电阻自动巡检装置的研发", 《浙江省计量科学研究院 信息科技》 * |
罗进等: "标准电阻自动巡检装置的研发", 《浙江省计量科学研究院 信息科技》, 15 July 2011 (2011-07-15) * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114004874A (en) * | 2021-12-30 | 2022-02-01 | 贝壳技术有限公司 | Acquisition method and device of occupied grid map |
CN114863657A (en) * | 2022-05-20 | 2022-08-05 | 深圳市威宇智通科技有限公司 | Vehicle traffic accident remote taking-over rescue system based on 4G and 5G internet of vehicles |
CN114863657B (en) * | 2022-05-20 | 2023-09-29 | 深圳市威宇智通科技有限公司 | Remote taking over rescue system for vehicle traffic accident based on 4G and 5G Internet of vehicles |
CN114952867A (en) * | 2022-07-26 | 2022-08-30 | 中国工业互联网研究院 | Control method and device for industrial robot, electronic equipment and readable storage medium |
CN116543018A (en) * | 2023-05-08 | 2023-08-04 | 重庆市二零八地质环境研究院有限公司 | High-steep dangerous rock collapse movement analysis method based on video feature point dynamic tracking |
CN116543018B (en) * | 2023-05-08 | 2023-12-19 | 重庆市二零八地质环境研究院有限公司 | High-steep dangerous rock collapse movement analysis method based on video feature point dynamic tracking |
CN117270576A (en) * | 2023-11-22 | 2023-12-22 | 自然资源部第三地形测量队(黑龙江第二测绘工程院) | Control method and control terminal of terrain measurement unmanned aerial vehicle |
CN117270576B (en) * | 2023-11-22 | 2024-02-02 | 自然资源部第三地形测量队(黑龙江第二测绘工程院) | Control method and control terminal of terrain measurement unmanned aerial vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN113465728B (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113465728B (en) | Terrain awareness method, system, storage medium and computer equipment | |
CN113485325A (en) | SLAM mapping and autonomous navigation method for underground coal mine water pump house inspection robot | |
Thrun et al. | Autonomous exploration and mapping of abandoned mines | |
Baker et al. | A campaign in autonomous mine mapping | |
CN106313086B (en) | A kind of coalmine rescue robot remote control system and control method | |
CN103064416B (en) | Crusing robot indoor and outdoor autonomous navigation system | |
CN109917786A (en) | A kind of robot tracking control and system operation method towards complex environment operation | |
CN109656251B (en) | Inspection robot for detecting soil in abandoned land of mining area and working method | |
CN104881027A (en) | Autonomic barrier-crossing system for wheel-track transformer station inspection robot and control method thereof | |
CN113867334B (en) | Unmanned path planning method and system for mobile machinery | |
CN202216696U (en) | Coal mine disaster relief robot navigation device based on information integration | |
CN102768361A (en) | GPS/INS combined positioning method based on genetic particle filtering and fuzzy neural network | |
CN205950750U (en) | Transformer station inspection robot control system that navigates based on inertial navigation | |
CN205426176U (en) | Coal -winning machine positioner that inertial navigation and laser scanning fuse | |
CN204557216U (en) | Wheel-track combined Intelligent Mobile Robot active obstacle system | |
CN209634595U (en) | A kind of novel mine detection robot with automatic obstacle avoiding function | |
CN112033400A (en) | Intelligent positioning method and system for coal mine mobile robot based on combination of strapdown inertial navigation and vision | |
CN113487583A (en) | Underground roadway surface deformation detection system based on 3D point cloud slice | |
CN204331465U (en) | A kind of machine system carrying out complex environment detection | |
Xiao et al. | Research status and development trend of underground intelligent load-haul-dump vehicle—a comprehensive review | |
CN116560357A (en) | Tunnel inspection robot system based on SLAM and inspection control method | |
CN114954525A (en) | Unmanned transport vehicle system suitable for phosphorite mining roadway and operation method | |
Androulakis et al. | Navigation system for a semi-autonomous shuttle car in room and pillar coal mines based on 2D LiDAR scanners | |
Lamon et al. | The SmartTer-a vehicle for fully autonomous navigation and mapping in outdoor environments | |
CN116352722A (en) | Multi-sensor fused mine inspection rescue robot and control method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |