CN114442625A - Environment map construction method and device based on multi-strategy joint control agent - Google Patents
Environment map construction method and device based on multi-strategy joint control agent Download PDFInfo
- Publication number
- CN114442625A CN114442625A CN202210076715.XA CN202210076715A CN114442625A CN 114442625 A CN114442625 A CN 114442625A CN 202210076715 A CN202210076715 A CN 202210076715A CN 114442625 A CN114442625 A CN 114442625A
- Authority
- CN
- China
- Prior art keywords
- environment
- boundary
- map
- strategy
- intelligent
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 56
- 230000033001 locomotion Effects 0.000 claims abstract description 46
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 239000003795 chemical substances by application Substances 0.000 claims description 89
- 238000000034 method Methods 0.000 claims description 64
- 238000005259 measurement Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 14
- 239000003344 environmental pollutant Substances 0.000 claims description 11
- 231100000719 pollutant Toxicity 0.000 claims description 11
- 230000004888 barrier function Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 239000003550 marker Substances 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 238000011109 contamination Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Optics & Photonics (AREA)
- Acoustics & Sound (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to an environment map construction method and device based on a multi-strategy joint control agent, which mainly comprises three stages of boundary detection, global detection and map construction. Firstly, detecting the boundary of an unknown environment by adopting an improved wall-following strategy; secondly, dividing the area surrounded by the boundary into grids, sequentially taking a randomly selected target point in each grid as an end point of the movement of the intelligent body by using a simplified spiral traversal strategy, and controlling the movement of the intelligent body by combining a D × Lite algorithm, so as to reduce the time for completing the global detection of the unknown environment; and finally, generating obstacle distribution and concentration field distribution of the unknown environment through a space occupying grid map algorithm and an RBF neural network respectively. The invention realizes the detection of the whole unknown environment by combining a plurality of strategy control agents, improves the calculation efficiency and can completely and accurately construct an environment map.
Description
Technical Field
The invention belongs to the field of intersection of information science and environmental science, and particularly relates to an environmental map construction method and device based on a multi-strategy joint control agent.
Background
Environmental monitoring is of great importance to public safety and the sustainability of ecosystems. Pollution source localization is one of the most critical issues in environmental monitoring applications. By locating the pollution source, effective measures can be taken in time to prevent further expansion of pollution and reduce the risk of leakage of harmful substances. In recent years, the implementation of automatic search and localization of pollution sources based on agents has become a new direction of research. Problems such as obstacle avoidance and path planning are involved in the positioning process of the pollution source of the intelligent agent, and specific information of the monitored environment needs to be known in advance. In the practical application process, the monitoring environment is mostly unknown, so that the intelligent body needs to be controlled to move through an intelligent algorithm, and an environment map is quickly and accurately constructed.
The environment map construction is a process that an intelligent agent detects environment information by utilizing a sensor carried by the intelligent agent and establishes a recognizable model. At present, the environment map construction method can be roughly divided into three categories: a geometric map based method, a topological map based method and a grid map based method. The first two methods are difficult to meet the actual application requirements in the aspects of precision and real-time performance, and the method based on the grid map has no limitation, can be used for positioning and navigation of an intelligent agent, and is the most widely applied method at present. The grid map-based method mainly includes a rapid SLAM (Simultaneous Localization And Mapping), a micro SLAM, a Cartographer algorithm, And the like. However, the three methods all involve motion estimation and update matching, which cannot guarantee robustness and computational efficiency at the same time, and thus are difficult to meet the requirements of practical applications. In addition, the D × Lite algorithm is often used for dynamic path planning in an unknown environment, but the method can only detect a grid region near a path planned in advance, cannot completely detect the whole environment, and cannot solve the problem that a target point is unknown. In order to detect the environment as much as possible, multiple applications are often needed, so that part of the environment is repeatedly detected, and the calculation efficiency of the algorithm is reduced.
Disclosure of Invention
The invention aims to solve the technical problems that the existing method is low in calculation efficiency, incomplete in map construction and the like, and provides a new method capable of effectively considering both accuracy and timeliness. In order to achieve the technical purpose, the invention provides an environment map construction method and device based on a multi-strategy joint control agent.
According to one aspect of the invention, the invention provides an environment map construction method based on a multi-strategy joint control agent, which comprises the following steps:
step S1: based on an intelligent agent sensing model, an improved wall-following strategy is adopted to control the intelligent agent to move for a circle along the boundary of an unknown environment for boundary detection, and the boundary of the unknown environment is obtained according to the pose of the intelligent agent and the measurement data analysis of the laser radar in the boundary detection process;
step S2: dividing a region surrounded by a boundary into a plurality of grids, randomly selecting a target point in each grid, and sequentially taking each target point as an end point of the motion of the intelligent agent by adopting a simplified spiral traversal strategy;
step S3: dynamically planning a path from the intelligent agent to each terminal by adopting a D-Lite algorithm, and sequentially reaching target points by the intelligent agent according to the planned trajectory to carry out global detection;
step S4: generating an obstacle distribution map of an unknown environment by adopting an occupancy grid map algorithm based on the pose of the intelligent agent and the measurement data of the laser radar in the global detection process;
step S5: training the RBF neural network based on the self position information recorded in the intelligent body movement process and the collected pollutant concentration, and after the training is finished, fitting the trained RBF neural network to generate a concentration distribution map of an unknown environment;
step S6: and combining the barrier distribution map and the concentration distribution map to generate an environment map, and completing the map construction of the unknown environment.
Preferably, in step S1, the agent is a mobile carrier carrying two ultrasonic sensors, a lidar, a concentration sensor and a photoelectric encoder; the two ultrasonic sensors are respectively positioned in front of and on the right side of the intelligent agent and used for detecting whether obstacles exist in the front and on the right side; the concentration sensor, the laser radar and the photoelectric encoder are located at the central position of the intelligent body, the concentration sensor is used for collecting pollutant concentration, the laser radar is used for scanning the whole environment and calculating and detecting the distribution condition of the obstacles, and the photoelectric encoder is used for calculating the pose of the intelligent body and comprises coordinates and angles.
Preferably, in step S1, the improved wall-following strategy includes:
the intelligent body is placed at any boundary point, the front direction and the back direction are parallel to the boundary, the intelligent body is controlled to advance or turn according to the detection distance result of the ultrasonic sensor, and the intelligent body is guaranteed to be always on the left side of the boundary along the movement direction.
Preferably, in step S1, the improved wall-following strategy includes:
the zone bit of the ultrasonic sensor i is set as UiThe values are:
where l is the distance threshold, d is the distance between the agent and the boundary, when UiIf the value is 1, the ultrasonic sensor i faces to the boundary, otherwise, the boundary is absent;
when the intelligent object detects different boundary conditions, the zone bit U1U2There are four combinations, namely 00, 01, 10 and 11;
if the current movement direction of the intelligent agent is J, the value range is 0-3, and the current movement direction is corresponding to the lower direction, the right direction, the upper direction and the left direction respectively, then the formula for controlling the movement direction change of the intelligent agent according to the marker bit combination is as follows:
where Δ J is a motion direction change value, i.e., the difference between the new motion direction and the current motion direction.
Preferably, in step S2, the simplified spiral traversal strategy includes:
and selecting a clockwise direction, taking each target point as the end point of the movement of the intelligent agent in sequence, and ensuring that the target point in each grid can only be visited once.
Preferably, step S4 includes:
in the global detection process, the scanning angle range of the laser radar is set to be-23 degrees to 23 degrees, the stepping angle is set to be 2.86 degrees, namely the scanning range of the laser radar is divided into 16 different scanning angles;
measuring data in a laser beam coverage range are obtained through laser radar scanning, and the probability p (I | z) that each point in an unknown environment is occupied by an obstacle is calculated by adopting an occupancy grid algorithmt) The concrete formula is as follows:
where I denotes the scanned point, ztIs a set of the measurement data of the lidar and the pose of the agent at time t, rmaxIs the farthest distance, r, that the lidar can detectIIs the distance from the center of the laser radar to I, phiIIs the relative angle between the lidar and I, phikIs phiIThe closest scan angle, k is the index of the scan angle, rkIs phikDetection range of the laser radar in the direction, beta being the step angle of the scanning, pminAnd pmaxIs a constant, satisfies 0<pmin<0.5<pmax<1；
Updating the confidence coefficient of the t moment I according to the probability that each point is occupied by the obstacle, and calculating the occupancy probability based on the confidence coefficient, wherein the specific formula is as follows:
wherein, Ct,IAnd Ct-1,IConfidence levels of the t moment and the t-1 moment I, and an initial confidence level C0,I＝0，pIIs the occupation probability of I, the more the occupation probability is close to 0, the more likely I is a free area; conversely, the closer the occupancy probability is to 1, the more likely I is to be an obstacle region;
and continuously updating the occupation probability of each point detected by the laser radar by the intelligent agent according to the movement of the planned path to generate an obstacle distribution map of the unknown environment.
Preferably, in step S5, the RBF neural network is a network structure having two inputs and one output and including 5 hidden layer nodes, where the input is the position coordinates of each point in the environment area, and the output is the concentration value; and (3) learning and training the RBF neural network through the position and concentration value sample pairs recorded in the boundary detection and global detection to obtain the trained RBF neural network, and completing the fitting of the concentration field distribution of the whole unknown environment.
According to a second aspect of the present invention, the present invention further provides an environment map building apparatus based on a multi-policy joint control agent, including the following modules:
the boundary detection module is used for controlling the intelligent body to move for a circle along the boundary of the unknown environment by adopting an improved wall-following strategy based on the intelligent body sensing model so as to carry out boundary detection, and analyzing the pose of the intelligent body and the measurement data of the laser radar in the boundary detection process so as to obtain the boundary of the unknown environment;
the spiral traversal module is used for dividing the area surrounded by the boundary into a plurality of grids, randomly selecting a target point in each grid, and sequentially taking each target point as an end point of the motion of the intelligent agent by adopting a simplified spiral traversal strategy;
the global detection module is used for dynamically planning a path from the intelligent agent to each terminal by adopting a D-Lite algorithm, and the intelligent agent sequentially reaches target points according to the planned path to perform global detection;
the obstacle distribution map generating module is used for generating an obstacle distribution map of an unknown environment by adopting an occupancy grid map algorithm based on the pose of the intelligent agent and the measurement data of the laser radar in the global detection process;
the concentration distribution map generation module is used for training the RBF neural network based on the self position information recorded in the intelligent agent movement process and the collected pollutant concentration, and after the training is finished, the trained RBF neural network is adopted to generate a concentration distribution map of an unknown environment in a fitting mode;
and the environment map generation module is used for generating an environment map by combining the barrier distribution map and the concentration distribution map to complete the map construction of the unknown environment.
The technical scheme provided by the invention has the following technical effects:
the method and the device for constructing the environment map of the multi-strategy combined control agent are mainly divided into three stages of boundary detection, global detection and map construction. Firstly, detecting the boundary of an unknown environment through an improved wall-following strategy; secondly, dividing the area surrounded by the boundary into grids, sequentially taking a randomly selected target point in each grid as an end point of the movement of the intelligent body by using a simplified spiral traversal strategy, and controlling the movement of the intelligent body by combining a D × Lite algorithm, so as to reduce the time for completing the global detection of the unknown environment; and finally, generating obstacle distribution and concentration field distribution of the unknown environment through a space occupying grid map algorithm and an RBF neural network respectively. The invention controls the movement of the intelligent body through multiple strategies, scans and monitors the environment to generate the obstacle area, and fits the concentration field distribution of the pollution source according to the concentration information acquired by the sensor and the position information of the intelligent body. The intelligent agent is controlled to move in the unknown monitoring environment through multi-strategy combination, the environment map can be constructed quickly and accurately, and the problems that the existing method is low in calculation efficiency and incomplete in map construction are effectively solved.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a schematic diagram of an environment mapping method based on a multi-strategy joint control agent according to the present invention;
FIG. 2 is a diagram of six unknown environments and their map construction, wherein FIG. 2(a) is a real environment map, and FIG. 2(b) is a constructed environment map;
FIG. 3 is a diagram of the movement trajectory of an agent in six environments in accordance with the present invention;
FIG. 4 is a comparison of the map construction results of three different methods of the present invention, wherein FIG. 4(a) is a real environment map, and FIGS. 4(B) to 4(d) are a method A and a method B, respectively, and an environment map constructed by the present invention;
fig. 5 is a concentration distribution graph fitted by the RBF neural network of the present invention, in which fig. 5(a) is a real concentration map and fig. 5(b) is a fitted concentration map.
Fig. 6 is a block diagram of an environment mapping apparatus for jointly controlling agents based on multiple policies according to the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
In this embodiment, a Python is used to compile corresponding codes, and a Pygame module is used to perform a simulation experiment. In the present embodiment, six different environments (each having a length and a width of 150cm × 105cm) are designed, and different numbers and shapes of obstacles are distributed in each environment, so as to simulate a complex actual environment. A single Gaussian concentration distribution model is adopted to simulate the point pollution source in the environment, and the function of the point pollution source is defined as:
wherein (x)0,y0) Is the position of the pollution source, (x, y) is the coordinate of any point in the environment, c (x, y) is the concentration of the point, and the value range is (0, 1)]。
Referring to fig. 1, fig. 1 is a schematic diagram of an environment map construction method based on a multi-policy joint control agent according to the present invention, and the specific implementation steps are as follows:
step S1: based on the intelligent sensing model, an improved wall-following strategy is adopted to control the intelligent body to move for a circle along the boundary of the unknown environment for boundary detection, and the boundary of the unknown environment is obtained according to the pose of the intelligent body and the measurement data of the laser radar in the boundary detection process.
The intelligent agent is a mobile carrier carrying two ultrasonic sensors, a laser radar, a concentration sensor and a photoelectric encoder, and has the functions of detecting distance, scanning environment and detecting pollutant concentration. The two ultrasonic sensors are respectively positioned in front of and on the right side of the intelligent body and used for detecting whether obstacles exist in the front and on the right side; the concentration sensor, the laser radar and the photoelectric encoder are located in the center of the intelligent body, the concentration sensor is used for collecting pollutant concentration, the laser radar is used for scanning the whole environment and calculating and detecting the distribution situation of the obstacles, and the photoelectric encoder is used for calculating the pose of the intelligent body and comprises coordinates and angles.
The system for sensing the unknown environment around the intelligent agent by using the functions of detecting the distance, scanning the environment and detecting the concentration of pollutants is called an intelligent agent sensing model.
And in the process of boundary detection, the intelligent agent perception model obtains the boundary of the unknown environment according to the pose of the intelligent agent and the measurement data of the laser radar.
In step S1, the improved wall-following strategy specifically includes:
setting the mark bit of the ultrasonic sensor i as UiThe values are:
where l is the distance threshold, d is the distance between the agent and the boundary, when UiIf the value is 1, the ultrasonic sensor i faces to the boundary, otherwise, the boundary is absent;
when the intelligent object detects different boundary conditions, the zone bit U1U2There are four combinations, namely 00, 01, 10 and 11;
if the current movement direction of the intelligent agent is J, the value range is 0-3, and the current movement direction is corresponding to the lower direction, the right direction, the upper direction and the left direction respectively, then the formula for controlling the movement direction change of the intelligent agent according to the marker bit combination is as follows:
where Δ J is a motion direction change value, i.e., the difference between the new motion direction and the current motion direction.
In this embodiment, the distance threshold l of the ultrasonic sensor is set to 1cm, the moving direction of the agent is adjusted according to equation (3), and the agent is ensured to be always on the left side of the boundary along the moving direction, so that the boundary detection of the unknown environment is completed.
Step S2: and dividing the area surrounded by the boundary into a plurality of grids, randomly selecting a target point in each grid, and sequentially taking each target point as an end point of the motion of the intelligent agent by adopting a simplified spiral traversal strategy.
In this embodiment, the unknown area surrounded by the boundary is divided into a plurality of 9 grids, a target point is randomly selected from each large grid, and the target points are sequentially used as the end points of the movement of the agent in the clockwise direction.
Step S3: dynamically planning a path from the intelligent agent to each terminal by adopting a D-Lite algorithm, and sequentially reaching target points by the intelligent agent according to the planned trajectory to carry out global detection;
in the global detection process, the intelligent agent only needs to sequentially reach the target point according to the planned path, and the whole environment area does not need to be fully covered.
Step S4: and generating an obstacle distribution map of an unknown environment by adopting an occupancy grid map algorithm based on the pose of the intelligent agent and the measurement data of the laser radar in the global detection process.
In this embodiment, step S4 specifically includes:
in the global detection process, the scanning angle range of the laser radar is set to be-23 degrees to 23 degrees, the stepping angle is set to be 2.86 degrees, namely the scanning range of the laser radar is divided into 16 different scanning angles;
measuring data in a laser beam coverage range are obtained through laser radar scanning, and the probability p (I | z) that each point in an unknown environment is occupied by an obstacle is calculated by adopting an occupancy grid algorithmt) The concrete formula is as follows:
where I denotes the scanned point, ztIs a set of the measurement data of the lidar and the pose of the agent at time t, rmaxIs the farthest distance, r, that the lidar can detectIIs the distance from the center of the laser radar to I, phiIIs the relative angle between the lidar and I, phikIs phiIThe closest scan angle, k is the index of the scan angle, rkIs phikDetection range of the laser radar in the direction, beta being the step angle of the scanning, pminAnd pmaxIs constant and satisfies 0<pmin<0.5<pmax<1, empirical value pmin＝0.3、pmax0.7. The first condition in the formula (4) corresponds to that the detected point is an undetected area, the probability value is 0.5, and the undetermined area is represented as whether the detected point is occupied or not; the second case represents that the point is likely to be occupied, and a larger probability needs to be assigned; the third case indicates that the point is less likely to be occupied, giving a lower probability.
Updating the confidence coefficient of the t moment I according to the probability that each point is occupied by the obstacle, and calculating the occupancy probability based on the confidence coefficient, wherein the specific formula is as follows:
wherein, Ct,IAnd Ct-1,IConfidence levels of the t moment and the t-1 moment I, and an initial confidence level C0,I＝0，pIIs the occupation probability of I, the more the occupation probability is close to 0, the more likely I is a free area; conversely, the closer the occupancy probability is to 1, the more likely I is to be an obstacle region;
in this embodiment, a probability of being occupied by an obstacle is given to each point in the environment map according to equation (4), the confidence of the point is updated according to equation (5), the occupancy probability of the point is calculated based on the confidence, the occupancy probability of each point detected by the laser radar is continuously updated by the intelligent agent according to the movement of the planned path, and finally, an obstacle distribution map of the unknown environment is generated.
Step S5: training the RBF neural network based on the self position information recorded in the intelligent body motion process (including the boundary detection process and the global detection process) and the collected pollutant concentration, and after the training is finished, fitting the trained RBF neural network to generate a concentration distribution map of an unknown environment.
Step S6: and combining the barrier distribution map and the concentration distribution map to generate an environment map, and completing the map construction of the unknown environment.
In this embodiment, the multi-policy joint control agent algorithm provided by the present invention is applied to map reconstruction in an unknown environment. In order to verify the effectiveness of the invention, six different environments are tested, and a constructed environment map and a motion track of the intelligent agent are drawn, specifically referring to fig. 2 and fig. 3. Comparing fig. 2(a) and fig. 2(b), the constructed maps of six unknown environments are accurate, and only a few edge regions are missing (the missing part is less than 1% of the full map). This is because the scanning range of the laser radar is a sector, and when the occupancy probability is calculated by dividing the sector area with the grid, a situation that a part of the grid area is overlapped or a part of the sector area is not divided by the grid occasionally occurs, so that the occupancy probability of the area is calculated incorrectly, and the finally generated obstacle map is missing. As can be seen from fig. 3, the agent moves around the boundary for one circle to detect the boundary of the environment, then moves to each target point in a spiral traversal manner, and finally stops at the last target point, thereby basically completing coverage detection of all unknown environments.
To further illustrate the advancement of the present invention, environment 2 and environment 3 are taken as examples to compare the present invention with two other methods: the method A does not adopt a wall-following strategy and a spiral traversal strategy, and randomly selected points are used as target points when the intelligent agent moves; the method B does not adopt a wall-following strategy to control the intelligent agent to move. The environment map constructed by the three methods is shown in fig. 4. As can be seen from fig. 4, the method a has the worst effect, many parts in the environment are not detected, and the generated map is far from the real environment; the method B finishes the detection of most environmental regions, and a small number of boundary regions are not detected; the invention completely explores the whole environment, and the result is closest to the real map.
Figure 5 shows the concentration profile fitted to the RBF neural network. Although the predicted concentration near the contamination source is slightly lower than the true value, the predicted concentration distribution trend and the position of the concentration peak are substantially consistent with the true condition.
In some embodiments, referring to fig. 6, there is further provided an environment mapping apparatus based on multi-policy joint control agent, including the following modules:
the boundary detection module 1 is used for controlling the intelligent body to move for a circle along the boundary of the unknown environment by adopting an improved wall-following strategy based on the intelligent body sensing model so as to carry out boundary detection, and analyzing the pose of the intelligent body and the measurement data of the laser radar in the boundary detection process so as to obtain the boundary of the unknown environment;
the spiral traversal module 2 is used for dividing the area surrounded by the boundary into a plurality of grids, randomly selecting a target point in each grid, and sequentially taking each target point as an end point of the motion of the intelligent agent by adopting a simplified spiral traversal strategy;
the global detection module 3 is used for dynamically planning a path from the intelligent agent to each terminal by adopting a D × Lite algorithm, and the intelligent agent sequentially reaches target points according to a planned track to perform global detection;
the obstacle distribution map generating module 4 is used for generating an obstacle distribution map of an unknown environment by adopting an occupancy grid map algorithm based on the pose of the intelligent agent and the measurement data of the laser radar in the global detection process;
the concentration distribution map generation module 5 is used for training the RBF neural network based on the self position information recorded in the intelligent agent movement process and the collected pollutant concentration, and generating a concentration distribution map of an unknown environment by adopting the trained RBF neural network in a fitting manner after the training is finished;
and the environment map generation module 6 is used for generating an environment map by combining the barrier distribution map and the concentration distribution map to complete the map construction of the unknown environment.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third and the like do not denote any order, but rather the words first, second and the like may be interpreted as indicating any order.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (8)
1. An environment map construction method based on a multi-strategy joint control agent is characterized by comprising the following steps:
step S1: based on the intelligent body sensing model, an improved wall-following strategy is adopted to control the intelligent body to move for a circle along the boundary of the unknown environment for boundary detection, and the boundary of the unknown environment is obtained according to the pose of the intelligent body and the measurement data analysis of the laser radar in the boundary detection process;
step S2: dividing a region surrounded by a boundary into a plurality of grids, randomly selecting a target point in each grid, and sequentially taking each target point as an end point of the movement of the intelligent body by adopting a simplified spiral traversal strategy;
step S3: dynamically planning a path from the intelligent agent to each terminal by adopting a D-Lite algorithm, and sequentially reaching target points by the intelligent agent according to the planned trajectory to carry out global detection;
step S4: generating an obstacle distribution map of an unknown environment by adopting an occupancy grid map algorithm based on the pose of the intelligent agent and the measurement data of the laser radar in the global detection process;
step S5: training the RBF neural network based on the self position information recorded in the intelligent body movement process and the collected pollutant concentration, and after the training is finished, fitting the trained RBF neural network to generate a concentration distribution map of an unknown environment;
step S6: and combining the barrier distribution map and the concentration distribution map to generate an environment map, and completing the map construction of the unknown environment.
2. The method for building an environment map based on multi-strategy joint control agent of claim 1, wherein in step S1, the agent is a mobile carrier carrying two ultrasonic sensors, a laser radar, a concentration sensor and a photoelectric encoder; the two ultrasonic sensors are respectively positioned in front of and on the right side of the intelligent agent and used for detecting whether obstacles exist in the front and on the right side; the concentration sensor, the laser radar and the photoelectric encoder are located at the central position of the intelligent body, the concentration sensor is used for collecting pollutant concentration, the laser radar is used for scanning the whole environment and calculating and detecting the distribution condition of the obstacles, and the photoelectric encoder is used for calculating the pose of the intelligent body and comprises coordinates and angles.
3. The method for building an environment map based on multi-strategy joint control agent according to claim 1, wherein in step S1, the improved wall-following strategy comprises:
the intelligent body is placed at any boundary point, the front direction and the back direction are parallel to the boundary, the intelligent body is controlled to advance or turn according to the detection distance result of the ultrasonic sensor, and the intelligent body is guaranteed to be always on the left side of the boundary along the movement direction.
4. The method for building an environment map based on multi-strategy joint control agent according to claim 1, wherein in step S1, the improved wall-following strategy comprises:
the zone bit of the ultrasonic sensor i is set as UiThe values are:
where l is the distance threshold and d isDistance between agent and boundary, when UiIf the value is 1, the ultrasonic sensor i faces to the boundary, otherwise, the boundary is absent;
when the intelligent object detects different boundary conditions, the zone bit U1U2There are four combinations, namely 00, 01, 10 and 11;
if the current movement direction of the intelligent agent is J, the value range is 0-3, and the current movement direction is corresponding to the lower direction, the right direction, the upper direction and the left direction respectively, then the formula for controlling the movement direction change of the intelligent agent according to the marker bit combination is as follows:
where Δ J is a motion direction change value, i.e., the difference between the new motion direction and the current motion direction.
5. The method for environment mapping based on multi-strategy joint control agent as claimed in claim 1, wherein in step S2, the simplified spiral traversal strategy comprises:
and selecting the clockwise direction, sequentially taking the target points as the end points of the movement of the intelligent agent, and ensuring that the target points in each grid can be accessed only once.
6. The multi-policy joint control agent-based environment mapping method according to claim 1, wherein step S4 includes:
in the global detection process, the scanning angle range of the laser radar is set to be-23 degrees to 23 degrees, the stepping angle is set to be 2.86 degrees, namely the scanning range of the laser radar is divided into 16 different scanning angles;
measuring data in a laser beam coverage range are obtained through laser radar scanning, and the probability p (I | z) that each point in an unknown environment is occupied by an obstacle is calculated by adopting an occupancy grid algorithmt) The concrete formula is as follows:
where I denotes the scanned point, ztIs a set of the measurement data of the lidar and the pose of the agent at time t, rmaxIs the farthest distance, r, that the lidar can detectIIs the distance from the center of the laser radar to I, phiIIs the relative angle between the lidar and I, phikIs phiIClosest scan angle, k is the index number of the scan angle, rkIs phikDetection range of the laser radar in the direction, beta being the step angle of the scanning, pminAnd pmaxIs constant and satisfies 0<pmin<0.5<pmax<1；
Updating the confidence coefficient of the t moment I according to the probability that each point is occupied by the obstacle, and calculating the occupancy probability based on the confidence coefficient, wherein the specific formula is as follows:
wherein, Ct,IAnd Ct-1,IConfidence levels of the t moment and the t-1 moment I, and an initial confidence level C0,I＝0，pIIs the occupation probability of I, the more the occupation probability is close to 0, the more likely I is a free area; conversely, the closer the occupancy probability is to 1, the more likely I is to be an obstacle region;
and continuously updating the occupation probability of each point detected by the laser radar by the intelligent agent according to the movement of the planned path to generate an obstacle distribution map of the unknown environment.
7. The method for building an environment map based on multi-strategy cooperative control agent of claim 1, wherein in step S5, the RBF neural network is a network structure with two inputs and one output and comprises 5 hidden layer nodes, the input is the position coordinates of each point in the environment area, and the output is the concentration value; and (3) learning and training the RBF neural network through the position and concentration value sample pairs recorded in the boundary detection and global detection to obtain the trained RBF neural network, and completing the fitting of the concentration field distribution of the whole unknown environment.
8. An environment map construction device based on multi-strategy joint control agent is characterized by comprising the following modules:
the boundary detection module is used for controlling the intelligent body to move for a circle along the boundary of the unknown environment by adopting an improved wall-following strategy based on the intelligent body sensing model so as to carry out boundary detection, and analyzing the pose of the intelligent body and the measurement data of the laser radar in the boundary detection process so as to obtain the boundary of the unknown environment;
the spiral traversal module is used for dividing the area surrounded by the boundary into a plurality of grids, randomly selecting a target point in each grid, and sequentially taking each target point as an end point of the motion of the intelligent agent by adopting a simplified spiral traversal strategy;
the global detection module is used for dynamically planning a path from the intelligent agent to each terminal by adopting a D-Lite algorithm, and the intelligent agent sequentially reaches target points according to the planned path to perform global detection;
the obstacle distribution map generating module is used for generating an obstacle distribution map of an unknown environment by adopting an occupancy grid map algorithm based on the pose of the intelligent agent and the measurement data of the laser radar in the global detection process;
the concentration distribution map generation module is used for training the RBF neural network based on the self position information recorded in the intelligent agent movement process and the collected pollutant concentration, and after the training is finished, the concentration distribution map of the unknown environment is generated by adopting the trained RBF neural network in a fitting manner;
and the environment map generation module is used for generating an environment map by combining the barrier distribution map and the concentration distribution map to complete the map construction of the unknown environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210076715.XA CN114442625B (en) | 2022-01-24 | 2022-01-24 | Environment map construction method and device based on multi-strategy combined control agent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210076715.XA CN114442625B (en) | 2022-01-24 | 2022-01-24 | Environment map construction method and device based on multi-strategy combined control agent |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114442625A true CN114442625A (en) | 2022-05-06 |
| CN114442625B CN114442625B (en) | 2023-06-06 |
Family
ID=81370603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210076715.XA Active CN114442625B (en) | 2022-01-24 | 2022-01-24 | Environment map construction method and device based on multi-strategy combined control agent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114442625B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115316887A (en) * | 2022-10-17 | 2022-11-11 | 杭州华橙软件技术有限公司 | Robot control method, robot, and computer-readable storage medium |
| US11829154B1 (en) | 2022-07-18 | 2023-11-28 | Intelligent Cleaning Equipment Holdings Co. Ltd. | Systems and methods for robotic navigation, teaching and mapping |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013071190A1 (en) * | 2011-11-11 | 2013-05-16 | Evolution Robotics, Inc. | Scaling vector field slam to large environments |
| CN106840168A (en) * | 2017-03-16 | 2017-06-13 | 苏州大学 | Complete coverage path planning method under clean robot and its dynamic environment |
| CN108983781A (en) * | 2018-07-25 | 2018-12-11 | 北京理工大学 | A kind of environment detection method in unmanned vehicle target acquisition system |
| CN109059931A (en) * | 2018-09-05 | 2018-12-21 | 北京航空航天大学 | A kind of paths planning method based on multiple agent intensified learning |
| CN109213169A (en) * | 2018-09-20 | 2019-01-15 | 湖南万为智能机器人技术有限公司 | The paths planning method of mobile robot |
| WO2019190395A1 (en) * | 2018-03-28 | 2019-10-03 | Agency For Science, Technology And Research | Method and system for returning a displaced autonomous mobile robot to its navigational path |
| CN111220999A (en) * | 2019-11-29 | 2020-06-02 | 大连海事大学 | Restricted space detection system and method based on instant positioning and mapping technology |
| CN111598916A (en) * | 2020-05-19 | 2020-08-28 | 金华航大北斗应用技术有限公司 | Preparation method of indoor occupancy grid map based on RGB-D information |
| CN112558599A (en) * | 2020-11-06 | 2021-03-26 | 深圳拓邦股份有限公司 | Robot work control method and device and robot |
| WO2022007350A1 (en) * | 2020-07-08 | 2022-01-13 | 格力电器（武汉）有限公司 | Global path planning method and apparatus, terminal, and readable storage medium |
-
2022
- 2022-01-24 CN CN202210076715.XA patent/CN114442625B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013071190A1 (en) * | 2011-11-11 | 2013-05-16 | Evolution Robotics, Inc. | Scaling vector field slam to large environments |
| CN106840168A (en) * | 2017-03-16 | 2017-06-13 | 苏州大学 | Complete coverage path planning method under clean robot and its dynamic environment |
| WO2019190395A1 (en) * | 2018-03-28 | 2019-10-03 | Agency For Science, Technology And Research | Method and system for returning a displaced autonomous mobile robot to its navigational path |
| CN108983781A (en) * | 2018-07-25 | 2018-12-11 | 北京理工大学 | A kind of environment detection method in unmanned vehicle target acquisition system |
| CN109059931A (en) * | 2018-09-05 | 2018-12-21 | 北京航空航天大学 | A kind of paths planning method based on multiple agent intensified learning |
| CN109213169A (en) * | 2018-09-20 | 2019-01-15 | 湖南万为智能机器人技术有限公司 | The paths planning method of mobile robot |
| CN111220999A (en) * | 2019-11-29 | 2020-06-02 | 大连海事大学 | Restricted space detection system and method based on instant positioning and mapping technology |
| CN111598916A (en) * | 2020-05-19 | 2020-08-28 | 金华航大北斗应用技术有限公司 | Preparation method of indoor occupancy grid map based on RGB-D information |
| WO2022007350A1 (en) * | 2020-07-08 | 2022-01-13 | 格力电器（武汉）有限公司 | Global path planning method and apparatus, terminal, and readable storage medium |
| CN112558599A (en) * | 2020-11-06 | 2021-03-26 | 深圳拓邦股份有限公司 | Robot work control method and device and robot |
Non-Patent Citations (6)
| Title |
|---|
| BERND-HELGE SCHAFER; CHRISTOPHER ARMBRUST; TOBIAS FOHST; KARSTEN BERNS: "The Application of Design Schemata in Off-Road Robotics", 《 IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE 》 * |
| STEPHEN COSSELL , JOSÉ GUIVANT: "Concurrent dynamic programming for grid-based problems and its application for real-time path planning", 《ROBOTICS AND AUTONOMOUS SYSTEMS》 * |
| YARU KANG; DIANXI SHI: "A Research on Area Coverage Algorithm for Robotics", 《2018 IEEE INTERNATIONAL CONFERENCE OF INTELLIGENT ROBOTIC AND CONTROL ENGINEERING (IRCE)》 * |
| 任泉林;臧铁钢;崔海程: "粮仓库区移动机器人导航***设计", 《电子技术与软件工程》 * |
| 王艺博: "障碍物场景下基于信息熵的气体源定位搜索", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 范云生;***;石林龙;张月;: "基于电子海图栅格化的无人水面艇全局路径规划", 中国航海 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11829154B1 (en) | 2022-07-18 | 2023-11-28 | Intelligent Cleaning Equipment Holdings Co. Ltd. | Systems and methods for robotic navigation, teaching and mapping |
| WO2024016101A1 (en) * | 2022-07-18 | 2024-01-25 | Intelligent Cleaning Equipment Holdings Co., Ltd. | Systems and methods for robotic navigation, teaching and mapping |
| CN115316887A (en) * | 2022-10-17 | 2022-11-11 | 杭州华橙软件技术有限公司 | Robot control method, robot, and computer-readable storage medium |
| CN115316887B (en) * | 2022-10-17 | 2023-02-28 | 杭州华橙软件技术有限公司 | Robot control method, robot, and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114442625B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105043396B (en) | The method and system of self-built map in a kind of mobile robot room | |
| CN112000754B (en) | Map construction method, device, storage medium and computer equipment | |
| Fox | Markov localization-a probabilistic framework for mobile robot localization and navigation. | |
| Wijk et al. | Localization and navigation of a mobile robot using natural point landmarks extracted from sonar data | |
| Wolf et al. | Online simultaneous localization and mapping in dynamic environments | |
| Marjovi et al. | Multi-robot olfactory search in structured environments | |
| Chatterjee et al. | A neuro-fuzzy assisted extended Kalman filter-based approach for simultaneous localization and mapping (SLAM) problems | |
| CN114442625B (en) | Environment map construction method and device based on multi-strategy combined control agent | |
| Di Marco et al. | A set theoretic approach to dynamic robot localization and mapping | |
| Teleweck et al. | Path planning algorithms and their use in robotic navigation systems | |
| CN114879660B (en) | Robot environment sensing method based on target drive | |
| Ordonez et al. | The virtual wall approach to limit cycle avoidance for unmanned ground vehicles | |
| Carinena et al. | Landmark detection in mobile robotics using fuzzy temporal rules | |
| Duckett et al. | Experiments in evidence based localisation for a mobile robot | |
| Li et al. | Robot map building from sonar sensors and DSmT | |
| Jiménez Serrata et al. | An intelligible implementation of FastSLAM2. 0 on a low-power embedded architecture | |
| Zelinsky | Environment mapping with a mobile robot using sonar | |
| Li et al. | Robot navigation method based on intelligent evolution | |
| Korthals et al. | Occupancy Grid Mapping with Highly Uncertain Range Sensors based on Inverse Particle Filters. | |
| Lee et al. | Probabilistic localization of the service robot by map matching algorithm | |
| Zelinsky | Environment exploration and path planning algorithms for mobile robot navigation using sonar | |
| ElKaissi et al. | SEDLRF: A new door detection system for topological maps | |
| Mohamad Yatim et al. | Comparison of Sampling Methods for Rao-blackwellized Particle Filter with Neural Network | |
| Ryu et al. | Local map-based exploration for mobile robots | |
| Qian et al. | Probabilistic deployment for multiple sensor systems |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220506 Assignee: Hubei Hongrui Membrane Technology Co.,Ltd. Assignor: CHINA University OF GEOSCIENCES (WUHAN CITY) Contract record no.: X2024980001471 Denomination of invention: A method and device for constructing environmental maps based on multi strategy joint control intelligent agents Granted publication date: 20230606 License type: Common License Record date: 20240129 Application publication date: 20220506 Assignee: Wuhan Xingqi Technology Co.,Ltd. Assignor: CHINA University OF GEOSCIENCES (WUHAN CITY) Contract record no.: X2024980001469 Denomination of invention: A method and device for constructing environmental maps based on multi strategy joint control intelligent agents Granted publication date: 20230606 License type: Common License Record date: 20240129 Application publication date: 20220506 Assignee: Wuhan Xintiande Energy Technology Co.,Ltd. Assignor: CHINA University OF GEOSCIENCES (WUHAN CITY) Contract record no.: X2024980001464 Denomination of invention: A method and device for constructing environmental maps based on multi strategy joint control intelligent agents Granted publication date: 20230606 License type: Common License Record date: 20240129 Application publication date: 20220506 Assignee: Wuhan Shitu Technology Co.,Ltd. Assignor: CHINA University OF GEOSCIENCES (WUHAN CITY) Contract record no.: X2024980001462 Denomination of invention: A method and device for constructing environmental maps based on multi strategy joint control intelligent agents Granted publication date: 20230606 License type: Common License Record date: 20240129 Application publication date: 20220506 Assignee: Wuhan Rongguo Biotechnology Co.,Ltd. Assignor: CHINA University OF GEOSCIENCES (WUHAN CITY) Contract record no.: X2024980001461 Denomination of invention: A method and device for constructing environmental maps based on multi strategy joint control intelligent agents Granted publication date: 20230606 License type: Common License Record date: 20240129 |
|
| EE01 | Entry into force of recordation of patent licensing contract |