CN117762134A - Inspection navigation method and system in cage chicken house, mobile robot and storage medium - Google Patents
Inspection navigation method and system in cage chicken house, mobile robot and storage medium Download PDFInfo
- Publication number
- CN117762134A CN117762134A CN202311714749.8A CN202311714749A CN117762134A CN 117762134 A CN117762134 A CN 117762134A CN 202311714749 A CN202311714749 A CN 202311714749A CN 117762134 A CN117762134 A CN 117762134A
- Authority
- CN
- China
- Prior art keywords
- mobile robot
- target point
- angle
- teaching
- point
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000007689 inspection Methods 0.000 title claims abstract description 47
- 241000287828 Gallus gallus Species 0.000 title claims abstract description 31
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 39
- 230000009471 action Effects 0.000 claims abstract description 35
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 230000007613 environmental effect Effects 0.000 claims abstract description 12
- 238000005096 rolling process Methods 0.000 claims description 13
- 230000006698 induction Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 101100030351 Schizosaccharomyces pombe (strain 972 / ATCC 24843) dis2 gene Proteins 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 244000144977 poultry Species 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000001125 extrusion Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 101100039010 Caenorhabditis elegans dis-3 gene Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a method, a system, a mobile robot and a storage medium for navigation of patrol in a cage chicken house, wherein the method comprises the following steps: according to pose information obtained in the teaching process, position and angle information of a current point and a next target point are obtained; executing a corner action according to the difference between the current point offset angle and the target point offset angle; correcting the angle of the connecting line of the target point and the starting point in the process of advancing to the target point by adopting a PID algorithm according to the distance between the two points, and tracking the straight line segment between the two points; in the process of advancing to the target point, when an obstacle enters the range of the detection area of the mobile robot, obstacle avoidance is realized; after reaching the target point, the yaw angle consistent with the key point of the action data is adjusted, the track tracking of the current patrol area is completed, and the target point of the next patrol area is tracked. The invention realizes the stable and reliable navigation inspection function in the cage chicken house with higher environmental complexity, thereby better solving the partial navigation problem in the cage chicken house.
Description
Technical Field
The invention relates to a cage chicken house interior inspection navigation method, a cleaning navigation control system and medium navigation. Belongs to the technical field of automation of livestock and poultry breeding equipment.
Background
China is a large agricultural country, and rapid development of large-scale cage poultry cultivation technology and house agricultural technical equipment has prompted birth of house autonomous mobile robots, wherein development of mobile robots bearing house inspection functions is rapid.
The house inspection robot has the capability of acquiring the distributed information of the whole environment in the house and the specific information of a specific position, and the current cage poultry house inspection robot faces more problems in practical application, such as:
1) The problem of path planning for mobile robots in henhouses is that the henhouse environment belongs to a structured scene, so that the path is usually fixed, and the problem of path planning in the process of the inspection is different from the problem of general searching for an optimal path, for example: particle swarm algorithm, genetic algorithm, artificial neural network method, etc., are less proposed at present for path planning methods of inspection robots in cage chicken house environments, and the existing methods also face some practical control algorithm problems.
2) And (3) determining the initial pose of the mobile robot in the house. In the house environment, the track pushing algorithm based on the inertial device often has higher requirements on the acquisition of the position and the attitude information of the starting point, the initial attitude information is lost due to the existence of accumulated errors after the robot is patrolled and examined for one round, and the problem that the robot gradually deviates from the original running route due to larger deviation from the original initial point attitude after entering the next patrol task is solved, so that long-time and multi-round patrol cannot be performed.
3) The method for inspecting the fixed route in the environment of the chicken house by the mobile robot in the house comprises the problems of path tracking, multi-sensor fusion ranging and obstacle avoidance algorithm facing to multiple types of obstacles. In the house environment, the mobile robot has limited working space, static barriers such as densely distributed chicken cages, material lines, numerous material tanks and narrow space occupied by feeding grooves entering the passageway, dynamic barriers such as feeding personnel are mixed in the static barriers, and the multi-sensor ranging accuracy and fusion algorithm are extremely high in requirements for the multi-sensor ranging accuracy and fusion algorithm, so that the problems often cause abnormal inspection of the inspection robot.
Disclosure of Invention
In view of the above, the invention provides a method, a system, a mobile robot and a storage medium for navigation of inspection in a cage chicken house, which realize stable inspection path tracking and obstacle avoidance functions in the cage chicken house with higher environmental complexity; meanwhile, the sensor device of the mobile robot is utilized to compensate the problem of initial pose correction, so that the problem that the mobile robot deviates from an original driving path possibly occurring after multiple rounds of inspection is solved, and the inspection navigation task of the mobile robot when facing multiple types of obstacles in a house is realized.
The first aim of the invention is to provide a navigation method for patrol in a cage chicken house.
The second aim of the invention is to provide a navigation system for patrol in the cage chicken house.
A third object of the present invention is to provide a mobile robot.
A fourth object of the present invention is to provide a computer-readable storage medium.
The first object of the present invention can be achieved by adopting the following technical scheme:
a method for navigating patrol in a cage chicken house, the method comprising:
path planning is conducted based on teaching learning;
obtaining the position and angle information of the current point and the next target point according to the pose information of a series of action data key points recorded in the teaching process;
Executing a corner action according to the difference value between the deflection angle of the current point and the deflection angle of the target point, so that the mobile robot turns to a yaw angle consistent with the deflection angle between the two points;
correcting the angle of the connecting line of the target point and the starting point in the process of advancing to the target point by adopting a PID algorithm according to the distance between the two points, and tracking the straight line segment between the two points;
in the process of advancing to the target point, when an obstacle enters the range of the detection area of the mobile robot, obstacle avoidance is realized;
after reaching the target point, the yaw angle consistent with the key point of the action data is adjusted, the track tracking of the current patrol area is completed, and the target point of the next patrol area is tracked.
Further, the path planning based on teaching learning specifically includes:
determining starting point and end point information of the mobile robot, and acquiring a plurality of teaching tracks of the mobile robot;
learning to acquire action data and environment data of a plurality of teaching tracks, dividing key points of the action data according to the inspection area, and acquiring teaching track information of a plurality of sub-areas;
removing track points which are easy to collide with the obstacle according to the acquired environmental data, and correcting and fitting teaching tracks of a plurality of sub-areas;
And generating a patrol teaching track suitable for the henhouse environment according to the corrected tracks.
Further, the performing correction fitting on the teaching tracks of the plurality of sub-areas specifically includes:
correcting the teaching tracks of the plurality of sub-areas by using a Gaussian mixture model and Gaussian mixture regression, and eliminating track noise to obtain a smooth teaching track;
and learning the modified teaching tracks of the plurality of sub-areas by using the dynamic primitive parameterized model, so that the generalization capability under the strong environmental constraint of the henhouse is enhanced, and the fitted teaching tracks are generated.
Further, the implementation of the obstacle avoidance specifically includes:
measuring the angle and the position of an obstacle in a detection range by using a ranging sensor, and establishing a polar coordinate system;
and dividing the fused rolling detection window data which surrounds the mobile robot into different area ranges according to the degrees, performing secondary treatment on the intervals, processing the intervals which do not meet the motion constraint, calculating the interval with the minimum cost from the rest intervals, and outputting the intermediate angle of the interval as the speed direction.
Further, after the path planning based on the teaching learning, the method further includes:
obtaining the included angle position between the mobile robot and the vertical wall according to the distance value obtained by the laser ranging sensor;
Obtaining the distance between the mass center of the mobile robot and the walls on two sides by utilizing the geometric relationship to obtain the position information of the robot;
comparing the current position information with the target position information, establishing a moving distance, and moving from the current position to the target point position by using a pure tracking algorithm;
obtaining an included angle between the mobile robot and a vertical wall according to a distance value obtained by the laser ranging sensor, rotating the included angle to a position parallel to the left wall, updating state information of the mobile robot to the pose sensor, and completing initial pose correction;
and (3) carrying out real-time processing on the data of the ranging sensor polled for one circle by using a Kalman filtering algorithm, and eliminating periodic saw-tooth disturbance of the ranging sensor on the hollowed-out surfaces of the cage meshes on two sides or the uneven surface under the feeding trough.
The second object of the invention can be achieved by adopting the following technical scheme:
a navigation system for patrol in a cage chicken house, the system comprising:
the path planning module is used for planning paths based on teaching learning;
the acquisition module is used for acquiring the position and angle information of the current point and the next target point according to the pose information of a series of action data key points recorded in the teaching process;
The execution module is used for executing a corner action according to the difference value between the deflection angle of the current point and the deflection angle of the target point, so that the mobile robot is turned to a yaw angle consistent with the deflection angle between the two points;
the tracking module is used for correcting the angle of the connecting line of the target point and the starting point in the process of advancing to the target point by adopting a PID algorithm according to the distance between the two points, and tracking the straight line segment between the two points;
the obstacle avoidance module is used for avoiding an obstacle when the obstacle enters the detection area range of the mobile robot in the process of travelling to the target point;
and the adjusting module is used for completing track tracking of the current patrol area after the yaw angle consistent with the key point of the action data is adjusted after the target point is reached, and starting tracking of the target point of the next patrol area.
The third object of the present invention can be achieved by adopting the following technical scheme:
the mobile robot comprises a robot platform, wherein a controller, a ranging sensor, a pose sensor and a safe touch sensor are mounted on the robot platform, and the ranging sensor, the pose sensor and the safe touch sensor are respectively connected with the controller;
the distance measuring sensor is used for sensing the distance, the size and the direction of the obstacle;
The pose sensor is used for estimating the absolute position and the pose of the mobile robot at the current moment;
the safety touch edge sensor is used for stopping movement of the mobile robot in an emergency;
the controller is used for executing the inspection navigation method in the cage chicken house.
Further, the ranging sensor comprises a single-wire mechanical laser radar, six ultrasonic ranging sensors and four laser ranging sensors;
the single-line mechanical laser radar is arranged at the center of the robot platform, performs two-dimensional scanning measurement on the surrounding 360-degree environment by adopting a light time flight method, and is connected with the controller through a serial port;
six ultrasonic sensors are arranged at the determined orientation position of the robot platform in a hexagonal arrangement mode and form a fusion rolling detection window with the single-wire mechanical laser radar, and the six ultrasonic sensors are connected and communicated with the controller in an RS485 bus mode;
four laser rangefinder sensors are arranged in the front and back position and the left and right position of the rear side of the left side of the robot platform respectively, keep parallel with the side edge of the robot platform, and communicate with the controller by adopting an RS485 bus.
Further, the pose sensor comprises a pose reference system and an incremental photoelectric encoder, wherein the pose reference system is composed of a gyroscope, an accelerometer and a magnetometer based on MEMS, the pose reference system transmits heading, rolling and pitching angle data to the controller through a serial port DMA, the encoder is connected with an electric drive controller on a motor through a signal wire, and the controller obtains mileage information of the mobile robot through operation by reading pulse feedback signals of the incremental encoder on the corresponding motor;
The safety touch edge sensor comprises a safety contact and an induction signal belt, wherein the safety contact is arranged on the surface around the robot platform, the induction signal belt wraps the surface of the robot platform provided with the safety contact through a flexible belt, the safety touch edge sensor is in contact with the safety contact through a conducting strip inside the induction signal belt, and then the current and the resistance of the safety contact are changed, and a corresponding collision signal is sent to the controller.
The fourth object of the present invention can be achieved by adopting the following technical scheme:
a computer readable storage medium storing a program which, when executed by a processor, implements the above-described in-house patrol navigation method.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention provides a path tracking and obstacle avoidance algorithm, which is used for guiding a mobile robot to travel towards the direction of a target point by utilizing the position information and the angle information of the current point and the target point in a structured henhouse scene. And the mobile robot can timely avoid and adjust when detecting different obstacles, so that the stability and reliability of the inspection process are ensured.
2. The invention provides a path planning algorithm based on teaching learning, which utilizes the pose information obtained by the pose sensor and the incremental encoder arranged on the mobile robot to realize the acquisition of the position points of the key path, improves the inspection efficiency and better helps the mobile robot to promote the path planning capability under a complex scene.
3. According to the invention, the laser ranging sensor and the laser radar which are mounted on the mobile robot are utilized to acquire the position relation between the mobile robot and the vertical corner according to the geometric relation, so that the target point is moved to the initial position, and the pose information of the robot is updated, thereby improving the precision of the initial pose in the next inspection process and reducing the accumulated deviation problem caused by inertial navigation.
4. According to the invention, the Kalman filtering algorithm is utilized to carry out filtering fusion on the rolling detection window, so that the situation that the data fluctuation occurs on the hollowed-out surfaces of the cage meshes at the two sides after the mobile robot enters the inspection aisle is further improved, and the ranging accuracy is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained from the structures shown in these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a patrol block diagram of a mobile robot according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of a method for navigating patrol in a cage chicken house according to embodiment 1 of the present invention.
Fig. 3 is a schematic diagram of a pose self-correcting algorithm according to embodiment 1 of the present invention.
Fig. 4 is a flowchart of a path tracking algorithm according to embodiment 1 of the present invention.
Fig. 5 is a schematic diagram of a path tracking algorithm according to embodiment 1 of the present invention.
Fig. 6 is a schematic diagram of an obstacle avoidance algorithm according to embodiment 1 of the present invention.
Fig. 7 is a block diagram of the inspection navigation system in the cage chicken house according to embodiment 2 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by persons of ordinary skill in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
Example 1:
as shown in fig. 1, the present embodiment provides a mobile robot, which includes a robot platform, on which a controller, a ranging sensor, a pose sensor, and a safety touch sensor are mounted, where the ranging sensor, the pose sensor, and the safety touch sensor are respectively connected with the controller.
The mobile robot of this embodiment is the rectangle automobile body, has two driving motor of bilateral symmetry, and left and right sides two-wheeled is independent control, adjusts mobile robot motion through left and right sides wheel differential.
The distance measuring sensor is used for sensing the distance, the size and the direction of the obstacle; further, the ranging sensor comprises a single line mechanical laser radar, six ultrasonic ranging sensors and four laser ranging sensors, wherein:
the single-wire mechanical laser radar is arranged at the center of the robot platform and is connected with the controller through a serial port.
Specifically, the laser radar can perform two-dimensional scanning measurement on the surrounding 360-degree environment by adopting a light time flight method (TOF), and the measurement repetition frequency is 20KHZ; the ranging principle of the optical time flight method is to measure the relative distance between an object and a sensor by measuring the emission and return time difference of modulated laser; the laser transmitter sends out the modulation pulse laser, and internal timer begins to calculate time from t1 moment, and after laser irradiation target object, partial energy returns, and when the radar received the laser signal that returns, stops internal timer timing at t2 moment, light velocity C, and laser radar reaches object's distance D is:
D＝C*(t2-t1)
Six ultrasonic sensors are arranged at the determined orientation position of the robot platform in a hexagonal arrangement mode and form a fusion rolling detection window with the single-wire mechanical laser radar, and the six ultrasonic sensors are connected and communicated with the controller in an RS485 bus mode.
Specifically, according to the respective arrangement directions of six paths of ultrasonic sensors around the movable platform, and by taking the geometric center of the movable platform as a center point, a hexagon formed by connecting lines between the end points of the maximum ranging range of each path of ultrasonic sensor is set as a rolling detection window; and when the obstacle exists in the rolling detection window, adopting an avoidance strategy for the obstacle.
Specifically, the six ultrasonic sensors are respectively arranged as d towards the front, the front oblique left, the front oblique right, the front rear, the rear oblique left and the rear oblique right front 、d front_left 、d front_right 、d back 、d back_right 、d back_right The method comprises the steps of carrying out a first treatment on the surface of the Because the ultrasonic detection has certain divergence and has detection dead zones at short distance, the distance measurement range of each ultrasonic sensor is set to be 10cm and 200cm]The method comprises the steps of carrying out a first treatment on the surface of the When the return distance measured by any ultrasonic sensor is greater than 200cm, the return distance is treated as 200cm, so that the directivity in the distance measurement process is ensured.
Four laser rangefinder sensors are arranged in the front and back position and the left and right position of the rear side of the left side of the robot platform respectively, keep parallel with the side edge of the robot platform, and communicate with the controller by adopting an RS485 bus.
Specifically, the laser ranging sensor mounting positions are the positions of the left side, the front side and the back side of the mobile robot platform and are parallel to the side positions of the robot, the same laser ranging sensor is mounted at the positions of the left side and the right side of the robot, the distance between the front laser sensor and the back laser sensor mounted on the left side is L1, and the distance between the two laser sensors mounted on the left side and the right side of the back side is L2. Let the distance value read by the laser ranging in front of the left side be dis1, the distance value read by the laser ranging in back of the left side be dis2, the distance value read by the laser ranging in back left side be dis3, and the distance value read by the laser ranging in back right side be dis4.
The pose sensor is used for estimating the absolute position and the pose of the mobile robot at the current moment; further, the pose sensor comprises a pose reference system and an incremental photoelectric encoder, wherein the pose reference system is composed of a gyroscope, an accelerometer and a magnetometer based on MEMS, the pose reference system transmits heading, roll, pitching angle and other data to the controller through a serial port DMA, the incremental photoelectric encoder is connected with the motor controller through a signal wire, and the controller obtains mileage information of the mobile robot through operation by reading pulse feedback signals of the corresponding incremental photoelectric encoder on the motor.
The safety touch edge sensor is used for stopping the movement of the mobile robot in an emergency; further, the safety touch edge sensor comprises a safety contact and an induction signal belt, the safety contact is arranged on the surface around the robot platform, the induction signal belt wraps the surface of the robot platform provided with the safety contact through a flexible belt, the safety touch edge sensor is in contact with the safety contact through a conducting strip inside the induction signal belt, and then the current and the resistance of the safety contact are changed, and a corresponding collision signal is sent to the controller.
Specifically, the safety touch edge sensor is fixed on the front side, the side edge and the rear side of the movable platform through aluminum guide rails; when the induction signal belt and the flexible belt-shaped object on one side are extruded, the conducting strip inside the induction signal belt is caused to be in contact with the safety contact, and then the current and the resistance of the safety contact are changed, so that a corresponding collision signal is sent to the controller, wherein the controller controls the motor to stop running and gives an alarm; after being moved away from the extrusion source or the extrusion source, the mobile robotic platform will continue to operate.
As shown in fig. 2, the embodiment also provides a method for navigating patrol in a cage chicken house, which is mainly realized by the controller of the mobile robot, and comprises the following steps:
S201, path planning is conducted based on teaching learning.
Aiming at the problems of low inspection efficiency and low inspection coverage rate in the inspection process caused by uncertain inspection paths in the cage-rearing chicken houses, the embodiment provides a path planning algorithm based on teaching so as to improve the realization of the rapid planning and path point generation of the operation paths in the cage-rearing chicken houses, and improve the environment applicability of the mobile robot, wherein the specific process is as follows: determining starting point and end point information of the mobile robot, and acquiring a plurality of teaching tracks of the mobile robot; learning to acquire action data and environment data of a plurality of teaching tracks, dividing key points of the action data according to the inspection area, and acquiring teaching track information of a plurality of sub-areas; removing track points which are easy to collide with the obstacle according to the acquired environmental data, and correcting and fitting teaching tracks of a plurality of sub-areas; and generating a patrol teaching track suitable for the henhouse environment according to the corrected tracks.
Further, the teaching track of the embodiment is based on a remote control teaching method, and motion data is obtained by controlling the mobile robot according to the multi-channel remote controller; the remote controller is provided with at least four signal channels capable of generating different signal values, including a first channel for controlling the forward/backward movement of the robot, a second channel for controlling the left/right rotation of the robot, a third channel for controlling the running state of the robot and a fourth channel for controlling the initialization state of the robot, namely, the first channel and the second channel control the plane moving direction of the robot.
Further, the first channel and the second channel are controlled through a self-resetting rocker, channel values of the first channel and the second channel of the robot remote controller are mixed and converted, PWM (Pulse Width Modulation ) values of a left motor and a right motor of the mobile robot are output, and control of the robot is achieved; the third channel is controlled by a three-section type self-locking deflector rod switch, and the fourth channel is controlled by a two-section type self-resetting deflector rod switch; the remote controller is matched with the receiver for use, the receiver is connected with the controller through a serial port, channel values of all channels of the remote controller are transmitted into the controller, and the controller executes corresponding control instructions by identifying and monitoring the channel values of all channels of the remote controller.
Further, the information of the starting point and the end point of the mobile robot is determined, and a plurality of teaching tracks of the mobile robot are obtained, specifically: the method comprises the steps of controlling a mobile robot to move in a henhouse by using a remote controller, continuously acquiring state information of the mobile robot in a certain time interval during traveling according to a pose sensor and an incremental photoelectric encoder on a mobile robot platform, wherein the state information comprises position information and attitude information, the position information is obtained by acquiring a real-time yaw angle value of the mobile robot by the pose sensor and an odometer distance of the mobile robot in unit time by the incremental photoelectric encoder, and a relative position coordinate is obtained according to a dead reckoning algorithm, and the specific formula is as follows:
Wherein the position coordinate vector of the mobile robot known at the moment is P t ＝(x t ,y t ) The movable platform is controlled to move from P within one sampling period delta t of the controller t ＝(x t ,y t ) Move to P t+1 ＝(x t+1 ,y t+1 ) The yaw angle of the distribution is theta t And theta t+1 The abscissa increment is deltax t The ordinate increment is deltay t According to theta t+1 And theta t Obtaining the increment delta theta of the yaw angle t The curve distance travelled by the movable platform is deltas t The method comprises the steps of carrying out a first treatment on the surface of the Due to smaller Δt, Δθ t The predicted position coordinate of the movable platform at the time t+1 is P because the predicted position coordinate is smaller than the predicted position coordinate t+1 ＝(x t+1 ,y t+1 )。
In this embodiment, the motion data and the environmental data include a channel value sampled at a certain time interval in the teaching process and a surrounding environmental distance value sampled according to the ranging sensor; the key points of the action data comprise corresponding position coordinates and navigation deflection angles when the mobile robot generates deflection angles exceeding a threshold value in the teaching process, the new inspection area is executed by the mobile robot, after the action is finished, a finished time node is obtained, the information (a channel value and an environment distance value) is respectively stored in the sequence positions of two arrays (a channel array and an environment array), and each environment distance value corresponds to a corresponding position point; the inspection area is divided into a plurality of inspection passageways, and each passageway corresponds to different transverse coordinate values under a Cartesian coordinate system established by the henhouse, so that the repeated inspection is avoided.
Further, track points which are easy to collide with the obstacle are removed according to the acquired environmental data, and the method specifically comprises the following steps: when data which is perceived to be smaller than the range threshold value of the obstacle at a certain point exists, the current environment array and the corresponding pose information are cleared.
Further, correction fitting is performed on the teaching tracks of the plurality of sub-areas, as shown in fig. 3, specifically: correcting the teaching tracks of the plurality of sub-areas by using a Gaussian mixture model and Gaussian mixture regression, and eliminating track noise to obtain a smooth teaching track; and learning the modified teaching tracks of the plurality of sub-areas by using the dynamic primitive parameterized model, so that the generalization capability under the strong environmental constraint of the henhouse is enhanced, and the fitted teaching tracks are generated.
After the path planning is completed, the mobile robot can be driven to move along the fitted teaching track to reach the final target point, and the henhouse inspection task is completed.
When the mobile robot is started, the pose self-correcting algorithm is adopted, and specifically comprises the following steps: obtaining the included angle position between the mobile robot and the vertical wall according to the distance value obtained by the laser ranging sensor; obtaining the distance between the mass center of the mobile robot and the walls on two sides by utilizing the geometric relationship to obtain the position information of the robot; comparing the current position information with the target position information, establishing a moving distance, and moving from the current position to the target point position by using a pure tracking algorithm; obtaining an included angle between the mobile robot and a vertical wall according to a distance value obtained by the laser ranging sensor, rotating the included angle to a position parallel to the left wall, updating state information of the mobile robot to the pose sensor, and completing initial pose correction; the pose self-correcting algorithm of the embodiment can also be used for returning to the starting point after the inspection is finished, and the situation that the mobile robot has deviation from the original starting point is easy to occur.
Specifically, the magnitudes of dis1 and dis2 are firstly judged to determine the deflection direction of the mobile robot platform relative to the left side wall, if dis1> dis2, the mobile robot platform needs to be deflected rightwards relative to the wall for adjustment, if dis1< dis2, the opposite is carried out, and delta dis= |dis2-dis1| is obtained, the angle value which the robot needs to adjust is further obtained according to the geometric relationship, the distance value between the center of the mobile robot platform and the vertical walls on the two sides is obtained according to the deflection angle value at the moment, the distance value between the center of the mobile robot platform and the left side is expressed as D1, the distance value between the center of the mobile robot platform and the rear side is expressed as D2, and the position state of the mobile robot at the moment is obtained; the geometric relationship is shown as follows:
θ＝tan -1 (Δdis/L1)
D1＝cosθ×(dis1±tanθ×L1/2)
D2＝cosθ×(dis2±tanθ×L2/2)
and comparing the current point with a target point (the starting position of the robot) to obtain a transverse deviation delta x and a longitudinal deviation delta y between the two points, tracking the target point by using a pure tracking method, obtaining a track deflection angle according to the pose self-correcting algorithm, and turning to be parallel to the left side edge to finish the adjustment of the pose of the mobile robot.
Specifically, the pure tracking method is a method of calculating the angular velocity of movement so that the mobile robot reaches the look-ahead point from the current position given the linear velocity, and is input as the actual linear velocity v= [ V ] of the left and right driving wheels L ,v R ] T The output is the pose vector q= [ x, y, θ ] of the robot] T The kinematic model of the double-wheel differential robot can be expressed as follows according to the kinematic and coordinate change relation:
determining the position of a target point, wherein Ld represents the distance value from the current position of the current mobile robot to the target point, alpha represents the included angle between the gesture of the current mobile robot and the target point, and the transverse error from the target point is defined as e, and the method comprises the following formula:
specifically, updating the state information of the mobile robot to the pose sensor, and completing initial pose correction is as follows: and setting the position and posture information obtained by dead reckoning at the moment to zero, feeding back initial declination information to a dead reckoning reference system, and updating the declination information so as to correct the posture state of the starting point of the mobile robot.
In the inspection process, when the henhouse walkway advances, the obstacles on two sides sensed by the ranging sensor arranged on the mobile robot platform are irregular or hollowed-out object surfaces, such as a henhouse net surface, a feeding trough and the like, so that the ranging sensor is inaccurate in ranging, large in fluctuation and large in error with a true value, and a cage net sensing algorithm for the henhouse hollowed-out surface is designed.
The implementation process of the cage network sensing algorithm of the embodiment is as follows: when the henhouse aisle advances, the controller polls the numerical value of the six paths of ultrasonic sensors at 8Hz frequency, acquires laser radar data at 50Hz through the serial port, divides the area according to the angle, processes the data of the distance measuring sensors polled for one circle in real time through a Kalman filtering algorithm, eliminates periodic saw tooth disturbance of the distance measuring sensors on the surfaces of the hollowed-out surfaces of the cage nets or the uneven surfaces under the feeding grooves on the two sides, solves the problem of larger fluctuation of the distance measuring data through the Kalman filtering algorithm, and improves the distance measuring accuracy and stability of the distance measuring sensors.
Specifically, the Kalman filtering algorithm is utilized to process the data of the ranging sensor in one round of polling in real time: determining fixed positions and angles of a laser radar sensor and an ultrasonic ranging sensor on a mobile robot platform; polling and reading distance values of six paths of ultrasonic sensors, and acquiring data of one circle of laser radar sensors to form a rolling detection window; and fusion processing is carried out on the data in the rolling detection window by using a Kalman filtering algorithm.
The rolling detection window of the embodiment takes the geometric center of the robot platform as a center point, and a hexagon formed by connecting lines between the end points of the preset ranging range of each ultrasonic sensor and a circle of data acquired by the laser radar are fused to be used as the rolling detection window so as to detect the obstacle.
Specifically, the Kalman filtering algorithm is an algorithm for optimally estimating the system state by using a linear system state equation and through system input and output observation data, and the specific algorithm steps are as follows:
(1) Predicting a state equation, and calculating a system estimated value at the time k from an optimal value at the time k-1 of a system state variable and a system input:
X(k|k-1)＝F(k)*X(k-1|k-1)+B(k)*u(k)
(2) Predicting covariance equation, predicting the system covariance at k moment according to the system covariance at k-1 moment:
P(k|k-1)＝F(k)*P(k-1|k-1)*F(k) T +Q(k)
(3) Updating a Kalman gain equation, and calculating Kalman gain according to the predicted value of the covariance matrix at the moment k:
X(k|k)＝X(k|k-1)+K(k)*(Z(k)-H(k)*X(k|k-1))
(4) Updating a covariance equation, and solving a covariance matrix at the k moment, wherein the covariance matrix is used for calculating Kalman output at the next moment:
P(k|k)＝(I-K(k)*H(k))*P(k|k-1)
wherein X (k|k-1) represents the current state result predicted at time k-1, X (k-1|k-1) represents the optimal value at time k-1, X (k|k) represents the optimal estimated value of the state variable at time k, F (k) is the transformation matrix acting in the state of X (k-1|k-1), and B (k) is the transformation matrix acting on the control quantity. And u (k) represents the current control gain. P (k|k-1) represents the covariance matrix value at time K, P (K-1|k-1) represents the covariance matrix at time K-1, Q (K) represents the covariance of the system process noise, K (K) is the Kalman gain, H (K) represents the prediction matrix of the object, R (K) is the covariance matrix of the object measurement noise, and Z (K) is the measurement value of the object. P (k|k) represents the covariance matrix at time k, and I is the identity matrix.
The following steps of the embodiment are path tracking and obstacle avoidance algorithm, which ensures that the mobile robot stably tracks path points in the actual running process, as shown in fig. 4 to 6, and specifically described as follows:
s202, according to pose information of a series of action data key points recorded in the teaching process, position and angle information of a current point and a next target point are obtained.
Specifically, in the henhouse inspection process, because the passageway between the hencoops at two sides in the henhouse is narrower, the inspection route is fixed, and most of the inspection route is a straight line segment; turning is needed when entering the next aisle, and the specific steps are as follows according to the characteristics of the henhouse inspection route: and determining a target point to be moved at the next stage of the mobile robot and a gesture after reaching the target point, and a patrol linear speed entering the aisle as a tracked object according to the key waypoint information provided under the teaching learning method.
And S203, executing a corner action according to the difference value between the deflection angle of the current point and the deflection angle of the target point, so that the mobile robot rotates to a yaw angle consistent with the deflection angle between the two points.
S204, correcting the angle of the connecting line of the target point and the starting point in the process of advancing to the target point by adopting a PID algorithm according to the distance between the two points, and tracking the straight line segment between the two points.
Specifically, the process of the mobile robot reaching the target position and posture is divided into three action phases, action one: rotating to the same straight line of the starting position (starting point) and the target position (target point) of the mobile robot at a certain angular speed around the vertical longitudinal axis of the vehicle body; action two: obtaining Euclidean distance and drift angle information between a current point and a target point of the mobile robot, obtaining a difference delta e between the current drift angle and the target drift angle, inputting the difference delta e as a controlled quantity into a PID controller, outputting the controlled quantity u (t) by the PID controller, and outputting the controlled quantity u (t) as an angular velocity change quantity of the mobile robot, wherein the PID controller is a closed-loop control algorithm integrating three links of Proportion (process), integration (integrate) and differentiation (Differential), and the core formula is shown as follows:
and obtaining the wheel speeds of the left wheel and the right wheel according to a double-wheel differential kinematics formula:
V r ＝V in +W*d
V l ＝V in -W*d
wherein V is in The linear velocity input during inspection is represented, and d represents half of the symmetry axis from the left or right wheel to the mobile robot.
S205, in the process of advancing to the target point, when the obstacle enters the detection area range of the mobile robot, obstacle avoidance is achieved.
The obstacle avoidance algorithm of the embodiment adopts a method for improving a vector histogram, and specifically comprises the following steps: measuring the angle and the position of an obstacle in a detection range by using a ranging sensor, establishing a polar coordinate system, and ensuring that the movement is stopped under an emergency by using a safety touch edge sensor around the mobile robot; wherein, utilize the safety around the mobile robot to touch limit sensor to guarantee under the emergency and stop the motion and be: dividing the 360-degree detection range into 12 area ranges according to 30 degrees, performing secondary processing on the interval value, discarding the interval which does not meet the motion constraint, calculating the interval with the minimum cost from the rest intervals, and outputting the intermediate angle of the interval as the speed direction.
Specifically, a polar coordinate system is established by the center of a mobile robot platform, and obstacle data are updated; performing expansion processing on the obstacle data, and dividing the area in the detection range according to angles; the distance data are converted into obstacle feasibility data, a reliability interval diagram is obtained, and the feasibility calculation method comprises the following steps: dividing the difference of the distance value of the obstacle subtracted by the maximum detection distance value, namely, the higher the reliability is, the greater the probability of having the obstacle is; converting the feasibility interval diagram into a binary diagram by using a double-threshold mode, wherein in the binary diagram, a 1 is used for indicating an obstacle area, and a 0 is used for indicating an obstacle-free area; adding an obstacle-free region into a motion constraint equation of the mobile robot, wherein the motion constraint mainly comprises brake constraint of the mobile robot, and calculating whether a required distance value from maximum acceleration to zero speed is collided with an obstacle according to the current speed, so as to remove an unreachable interval and obtain an effective interval; and carrying out cost calculation on each effective interval to obtain optimal angle information as a speed vector to be output, wherein a cost calculation formula is as follows:
h＝k1*(θ-θ goal )+k2*(θ-θ v )+k3*(θ-θ last )
the cost function consists of three parts, wherein the first part is the deflection angle of the predicted direction and the target direction, the second part is the deviation of the predicted direction and the current speed direction, and the third part is the deviation of the predicted direction and the last speed direction. And adjusting the proportionality coefficients k1, k2 and k3 according to actual conditions to ensure that the robot is safe to avoid the obstacle.
S206, after reaching the target point, adjusting to a yaw angle consistent with the key point of the action data, completing track tracking of the current patrol area, and starting tracking of the target point of the next patrol area.
Specifically, the left wheel speed and the right wheel speed are output to a motor, and the angle and the position after the deltat moment are deduced; when the mobile robot does not reach the vicinity of the target point, correcting the angle through the PID controller in unit time to enable the mobile robot to travel towards the target point; defining a calm range of the target point near the target point, and setting the calm range to be a radius range of 5cm at present, wherein when the mobile robot is about to enter the limited range of the target point (namely near the target point), a linear decreasing strategy is adopted to reduce the rotating speed of the motor, so that the mobile robot can calm at the target point; action point three: after reaching the target point, determining a deflection angle according to the comparison of the current pose of the mobile robot and the target pose, rotating around the center of the mobile robot at a certain angular speed to the target point, namely, adjusting to the yaw angle consistent with the key point of the action data, then completing track tracking of the current inspection area, and starting tracking of the target point of the next inspection area.
It should be noted that although the above-described method operations are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in that particular order or that all of the illustrated operations be performed to achieve desirable results. Rather, the depicted steps may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.
Example 2:
as shown in fig. 7, the embodiment provides an in-cage chicken house inspection navigation system, which comprises a path planning module 701, an acquisition module 702, an execution module 703, a tracking module 704, an obstacle avoidance module 705 and an adjustment module 706, wherein the specific descriptions of the modules are as follows:
a path planning module 701, configured to perform path planning based on teaching learning;
the acquisition module 702 is configured to obtain position and angle information of a current point and a next target point according to pose information of a series of motion data key points recorded in a teaching process;
the execution module 703 is configured to execute a corner action according to a difference between the current point offset angle and the target point offset angle, so that the mobile robot turns to a yaw angle consistent with the offset angle between the two points;
the tracking module 704 is configured to correct an angle of a connection line between the target point and the starting point in a process of traveling to the target point by using a PID algorithm according to a distance between the two points, and track a straight line segment between the two points;
the obstacle avoidance module 705 is configured to implement obstacle avoidance when an obstacle enters a range of a detection area of the mobile robot during traveling to the target point;
and the adjusting module 706 is configured to complete tracking the track of the current patrol area after reaching the target point and adjusting to a yaw angle consistent with the key point of the action data, and start tracking the target point of the next patrol area.
Specific implementation of each module in this embodiment may be referred to embodiment 1 above, and will not be described in detail herein; it should be noted that, in the system provided in this embodiment, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be performed by different functional units according to needs, that is, the internal structure is divided into different functional units, so as to perform all or part of the functions described above.
Example 3:
the present embodiment provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the method for navigating patrol inside a cage chicken house according to embodiment 1, and the method specifically includes:
path planning is conducted based on teaching learning;
obtaining the position and angle information of the current point and the next target point according to the pose information of a series of action data key points recorded in the teaching process;
executing a corner action according to the difference value between the deflection angle of the current point and the deflection angle of the target point, so that the mobile robot turns to a yaw angle consistent with the deflection angle between the two points;
correcting the angle of the connecting line of the target point and the starting point in the process of advancing to the target point by adopting a PID algorithm according to the distance between the two points, and tracking the straight line segment between the two points;
In the process of advancing to the target point, when an obstacle enters the range of the detection area of the mobile robot, obstacle avoidance is realized;
after reaching the target point, the yaw angle consistent with the key point of the action data is adjusted, the track tracking of the current patrol area is completed, and the target point of the next patrol area is tracked.
The computer readable storage medium of the present embodiment may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In this embodiment, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this embodiment, however, the computer-readable signal medium may include a data signal that propagates in baseband or as part of a carrier wave, in which a computer-readable program is carried. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable storage medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable storage medium may be written in one or more programming languages, including an object oriented programming language such as Java, python, C ++ and conventional procedural programming languages, such as the C-language or similar programming languages, or combinations thereof for performing the present embodiments. The program may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
In conclusion, the stable inspection path tracking and obstacle avoidance functions in the cage chicken house with higher environmental complexity are realized; meanwhile, the sensor device of the mobile robot is utilized to compensate the problem of initial pose correction, so that the problem that the mobile robot deviates from an original driving path possibly occurring after multiple rounds of inspection is solved, and the inspection navigation task of the mobile robot when facing multiple types of obstacles in a house is realized.
The above-mentioned embodiments are only preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can make equivalent substitutions or modifications according to the technical solution and the inventive concept of the present invention within the scope of the present invention disclosed in the present invention patent, and all those skilled in the art belong to the protection scope of the present invention.
Claims (10)
1. The method for navigating patrol in the cage chicken house is characterized by comprising the following steps:
path planning is conducted based on teaching learning;
obtaining the position and angle information of the current point and the next target point according to the pose information of a series of action data key points recorded in the teaching process;
executing a corner action according to the difference value between the deflection angle of the current point and the deflection angle of the target point, so that the mobile robot turns to a yaw angle consistent with the deflection angle between the two points;
correcting the angle of the connecting line of the target point and the starting point in the process of advancing to the target point by adopting a PID algorithm according to the distance between the two points, and tracking the straight line segment between the two points;
in the process of advancing to the target point, when an obstacle enters the range of the detection area of the mobile robot, obstacle avoidance is realized;
after reaching the target point, the yaw angle consistent with the key point of the action data is adjusted, the track tracking of the current patrol area is completed, and the target point of the next patrol area is tracked.
2. The method for navigating patrol in a cage chicken house according to claim 1, wherein the path planning based on teaching learning specifically comprises:
determining starting point and end point information of the mobile robot, and acquiring a plurality of teaching tracks of the mobile robot;
learning to acquire action data and environment data of a plurality of teaching tracks, dividing key points of the action data according to the inspection area, and acquiring teaching track information of a plurality of sub-areas;
removing track points which are easy to collide with the obstacle according to the acquired environmental data, and correcting and fitting teaching tracks of a plurality of sub-areas;
and generating a patrol teaching track suitable for the henhouse environment according to the corrected tracks.
3. The method for navigating patrol in a cage chicken house according to claim 2, wherein the performing correction fitting on the teaching tracks of the plurality of sub-areas specifically comprises:
correcting the teaching tracks of the plurality of sub-areas by using a Gaussian mixture model and Gaussian mixture regression, and eliminating track noise to obtain a smooth teaching track;
and learning the modified teaching tracks of the plurality of sub-areas by using the dynamic primitive parameterized model, so that the generalization capability under the strong environmental constraint of the henhouse is enhanced, and the fitted teaching tracks are generated.
4. The method for navigating patrol in a cage chicken house according to claim 1, wherein the method for realizing obstacle avoidance comprises the following steps:
measuring the angle and the position of an obstacle in a detection range by using a ranging sensor, and establishing a polar coordinate system;
and dividing the fused rolling detection window data which surrounds the mobile robot into different area ranges according to the degrees, performing secondary treatment on the intervals, processing the intervals which do not meet the motion constraint, calculating the interval with the minimum cost from the rest intervals, and outputting the intermediate angle of the interval as the speed direction.
5. The method for navigating patrol in a cage chicken house according to claim 1, wherein after the path planning based on teaching learning, further comprises:
obtaining the included angle position between the mobile robot and the vertical wall according to the distance value obtained by the laser ranging sensor;
obtaining the distance between the mass center of the mobile robot and the walls on two sides by utilizing the geometric relationship to obtain the position information of the robot;
comparing the current position information with the target position information, establishing a moving distance, and moving from the current position to the target point position by using a pure tracking algorithm;
obtaining an included angle between the mobile robot and a vertical wall according to a distance value obtained by the laser ranging sensor, rotating the included angle to a position parallel to the left wall, updating state information of the mobile robot to the pose sensor, and completing initial pose correction;
And (3) carrying out real-time processing on the data of the ranging sensor polled for one circle by using a Kalman filtering algorithm, and eliminating periodic saw-tooth disturbance of the ranging sensor on the hollowed-out surfaces of the cage meshes on two sides or the uneven surface under the feeding trough.
6. A navigation system for patrol in a cage chicken house, the system comprising:
the path planning module is used for planning paths based on teaching learning;
the acquisition module is used for acquiring the position and angle information of the current point and the next target point according to the pose information of a series of action data key points recorded in the teaching process;
the execution module is used for executing a corner action according to the difference value between the deflection angle of the current point and the deflection angle of the target point, so that the mobile robot is turned to a yaw angle consistent with the deflection angle between the two points;
the tracking module is used for correcting the angle of the connecting line of the target point and the starting point in the process of advancing to the target point by adopting a PID algorithm according to the distance between the two points, and tracking the straight line segment between the two points;
the obstacle avoidance module is used for avoiding an obstacle when the obstacle enters the detection area range of the mobile robot in the process of travelling to the target point;
and the adjusting module is used for completing track tracking of the current patrol area after the yaw angle consistent with the key point of the action data is adjusted after the target point is reached, and starting tracking of the target point of the next patrol area.
7. The mobile robot comprises a robot platform and is characterized in that a controller, a ranging sensor, a pose sensor and a safe touch sensor are mounted on the robot platform, and the ranging sensor, the pose sensor and the safe touch sensor are respectively connected with the controller;
the distance measuring sensor is used for sensing the distance, the size and the direction of the obstacle;
the pose sensor is used for estimating the absolute position and the pose of the mobile robot at the current moment;
the safety touch edge sensor is used for stopping movement of the mobile robot in an emergency;
the controller is used for executing the method for navigating patrol in the cage chicken house according to any one of claims 1-5.
8. The mobile robot of claim 7, wherein the ranging sensors comprise one single line mechanical lidar, six ultrasonic ranging sensors, and four laser ranging sensors;
the single-line mechanical laser radar is arranged at the center of the robot platform, performs two-dimensional scanning measurement on the surrounding 360-degree environment by adopting a light time flight method, and is connected with the controller through a serial port;
six ultrasonic sensors are arranged at the determined orientation position of the robot platform in a hexagonal arrangement mode and form a fusion rolling detection window with the single-wire mechanical laser radar, and the six ultrasonic sensors are connected and communicated with the controller in an RS485 bus mode;
Four laser rangefinder sensors are arranged in the front and back position and the left and right position of the rear side of the left side of the robot platform respectively, keep parallel with the side edge of the robot platform, and communicate with the controller by adopting an RS485 bus.
9. The mobile robot of claim 7, wherein the pose sensor comprises a pose reference system and an incremental photoelectric encoder, wherein the pose reference system is composed of a gyroscope, an accelerometer and a magnetometer based on MEMS, the pose reference system sends heading, roll and pitch angle data to the controller through a serial port DMA, the encoder is connected with an electric drive controller on a motor through a signal line, and the controller obtains mileage information of the mobile robot through operation by reading pulse feedback signals of the incremental encoder on the corresponding motor;
the safety touch edge sensor comprises a safety contact and an induction signal belt, wherein the safety contact is arranged on the surface around the robot platform, the induction signal belt wraps the surface of the robot platform provided with the safety contact through a flexible belt, the safety touch edge sensor is in contact with the safety contact through a conducting strip inside the induction signal belt, and then the current and the resistance of the safety contact are changed, and a corresponding collision signal is sent to the controller.
10. A computer-readable storage medium storing a program, wherein the program, when executed by a processor, implements the in-cage inspection navigation method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311714749.8A CN117762134A (en) | 2023-12-14 | 2023-12-14 | Inspection navigation method and system in cage chicken house, mobile robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311714749.8A CN117762134A (en) | 2023-12-14 | 2023-12-14 | Inspection navigation method and system in cage chicken house, mobile robot and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117762134A true CN117762134A (en) | 2024-03-26 |
Family
ID=90317369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311714749.8A Pending CN117762134A (en) | 2023-12-14 | 2023-12-14 | Inspection navigation method and system in cage chicken house, mobile robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117762134A (en) |
-
2023
- 2023-12-14 CN CN202311714749.8A patent/CN117762134A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262495B (en) | Control system and method capable of realizing autonomous navigation and accurate positioning of mobile robot | |
| US11892855B2 (en) | Robot with perception capability of livestock and poultry information and mapping approach based on autonomous navigation | |
| CN108536149B (en) | Unmanned vehicle obstacle avoidance control method based on Dubins path | |
| CN107966150B (en) | Substation operation robot path planning and navigation positioning method based on intersection points and road sections | |
| CN111522339A (en) | Automatic path planning and positioning method and device for inspection robot of livestock and poultry house | |
| US4821192A (en) | Node map system and method for vehicle | |
| CN112256023B (en) | Bezier curve-based airport border patrol robot local path planning method and system | |
| WO1988004081A1 (en) | Node map system and method for vehicle | |
| CN113625702B (en) | Unmanned vehicle simultaneous path tracking and obstacle avoidance method based on quadratic programming | |
| CN114200945B (en) | Safety control method of mobile robot | |
| CN116069037A (en) | Unmanned vehicle formation track planning control method, device, equipment and storage medium | |
| CN111596666A (en) | Detection method for obstacle collision threat based on AGV motion prediction | |
| CN117762134A (en) | Inspection navigation method and system in cage chicken house, mobile robot and storage medium | |
| CN112611374A (en) | Path planning and obstacle avoidance method and system based on laser radar and depth camera | |
| Che et al. | A wall-following navigation method for autonomous driving based on lidar in tunnel scenes | |
| WO2023173076A1 (en) | End-to-end systems and methods for streaming 3d detection and forecasting from lidar point clouds | |
| Tebueva et al. | A method for planning the trajectory of a mobile robot in an unknown environment with obstacles | |
| US20230202470A1 (en) | Integrated trajectory forecasting, error estimation, and vehicle handling when detecting an observed scenario | |
| US11887317B2 (en) | Object trajectory forecasting | |
| Suzuki et al. | Smooth path planning with pedestrian avoidance for wheeled robots: Implementation and evaluation | |
| CN115657664A (en) | Path planning method, system, equipment and medium based on human teaching learning | |
| CN111026163B (en) | Indoor-oriented uncontrolled radioactive source autonomous searching robot and searching method thereof | |
| Jung et al. | Vision guidance system for AGV using ANFIS | |
| Zhan et al. | Application of image process and distance computation to WMR obstacle avoidance and parking control | |
| Nejad et al. | Real time localization, path planning and motion control for autonomous parking in cluttered environment with narrow passages |
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 |