CN109669457B - Robot recharging method and chip based on visual identification - Google Patents
Robot recharging method and chip based on visual identification Download PDFInfo
- Publication number
- CN109669457B CN109669457B CN201811603402.5A CN201811603402A CN109669457B CN 109669457 B CN109669457 B CN 109669457B CN 201811603402 A CN201811603402 A CN 201811603402A CN 109669457 B CN109669457 B CN 109669457B
- Authority
- CN
- China
- Prior art keywords
- robot
- preset
- recharging
- infrared
- charging seat
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000000007 visual effect Effects 0.000 title claims abstract description 29
- 230000005855 radiation Effects 0.000 claims abstract description 35
- 238000011065 in-situ storage Methods 0.000 claims description 3
- 210000001503 joint Anatomy 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 5
- 238000013459 approach Methods 0.000 abstract description 3
- 238000003032 molecular docking Methods 0.000 description 10
- 241001417527 Pempheridae Species 0.000 description 5
- 230000033001 locomotion Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010408 sweeping Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012545 processing Methods 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
- G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0225—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving docking at a fixed facility, e.g. base station or loading bay
-
- 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
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- H02J7/0027—
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a robot recharging method and a chip based on visual identification. The robot recharging method comprises the steps that firstly, a first preset recharging position is determined by collecting a guide identification image, so that a short-distance recharging butt joint area is provided for infrared signal guide, and the success rate of robot butt joint is improved; on the other hand, after the robot completes the matching of the environment image shot in real time and the pre-stored guide identification image of the charging seat, in the process of moving along the preset path, aiming at the situation that the charging seat moves, an initial recharging position of infrared vision combined with repeated guide is provided for the robot by deploying the second preset recharging position. According to the invention, the visual identification is used for recharging guidance in a remote infrared radiation area, and when the infrared guidance signal is combined after the infrared identification approaches the charging seat, the visual guidance is assisted to realize the final butt joint and charging of the robot and the charging seat, so that the success rate of the butt joint of the robot is greatly improved, and the efficiency is also greatly improved.
Description
Technical Field
The invention relates to the field of robot recharging, in particular to a robot recharging method and a chip based on visual identification.
Background
At present, the main idea for solving the power supply problem of the sweeper is to return to charge autonomously, and the most common technical means is to guide the sweeper to return to a charging seat for butt joint charging based on an infrared signal. Although the method and the system can realize the autonomous recharging of the sweeper, the distance for transmitting the coded signal is short and slightly shielded under the condition that the transmitting angle of the infrared sensor is small, the infrared signal cannot be completely penetrated, at the moment, if the space of the sweeping environment using the sweeper is large, the robot needs to search the infrared signal in a carpet mode, and particularly under the condition that a charging seat is moved, the robot needs to consume a large amount of residual electric quantity, the sweeper cannot return to a base, and the situation that the electric quantity is exhausted and stranded on a half road possibly occurs.
Disclosure of Invention
In order to overcome the technical defects, the following technical scheme is proposed:
a robot recharging method based on visual identification comprises the following steps: step S1, after the robot enters the charging mode, sending a charging signal to the charging seat; step S2, when the robot receives the infrared guide signal radiated from the charging seat in each direction of the current position, the robot starts the camera to collect the guide mark set on the charging seat in real time; step S3, according to the similarity between the environment image shot in real time and the pre-stored guide identification image of the charging seat, determining the position corresponding to the environment image matched with the similarity of the guide identification image as a first preset recharging position; step S4, planning a preset path according to the intensity of the infrared guide signal received by the robot at the current position and the environment image information matched with the similarity, and controlling the robot to move to a first preset recharging position along the preset path; step S5, judging whether the first preset recharging position shoots the guide identification of the charging seat, if so, controlling the robot to move from the first preset recharging position to align with the electrode of the charging seat to complete charging, otherwise, entering step S6; and S6, adjusting the pose of the robot from the first preset recharging position to a second preset recharging position according to the intensity of the infrared guide signal received by the first preset recharging position, and repeating the steps S3 to S5 until the robot is aligned with the electrode of the charging seat to finish charging. According to the technical scheme, a first preset recharging position is determined by collecting a guide identification image, so that a short-distance recharging docking area is provided for infrared signal guide, and the success rate of robot docking is improved; on the other hand, when the robot finishes the matching of the environment image shot in real time and the pre-stored guide identifier image of the charging seat, in the process of moving along the preset path, aiming at the situation that the charging seat moves, the first preset recharging position provided by the technical scheme provides a position for reconfirming the guide identifier of the charging seat for the robot, then an initial recharging position combining infrared vision and repeated guidance is provided for the robot by deploying the second preset recharging position, the technical scheme uses the visual identifier to carry out recharging guidance in a remote infrared radiation area, when the robot approaches the charging seat, whether the charging seat is kept at the original position is judged firstly, then under the action of an infrared guide signal, the visual guidance is assisted to realize the final butt joint charging of the robot and the charging seat, so that the robot is simpler and more convenient to use, the success rate of robot butt joint improves greatly to efficiency also can promote greatly.
Further, in step S2, the infrared guiding signal radiated outward is an infrared encoding signal emitted from the infrared light source of the charging seat toward the ceiling, and the coverage area of the infrared encoding signal is a spherical area range centered on the charging seat, and for the scene condition of the movement of the charging seat, in the case that the camera does not acquire the guiding identification image of the charging seat, the technical scheme assists the robot in visual guiding recharging by receiving the infrared guiding signal with a large radiation range emitted by the charging seat, so as to solve the visual acquisition blind area caused by the movement of the charging seat.
Further, the sphere area range is divided into a long-range infrared radiation area and a short-range infrared radiation area, and the first preset recharging position is used as a boundary position of the long-range infrared radiation area and the short-range infrared radiation area. Aiming at the situation that the charging seat moves, the first preset recharging position provided by the technical scheme provides a position for the robot to reconfirm the guide identifier of the charging seat, provides an operation space for the robot to play a role in cooperation of infrared vision recharging guide in different infrared radiation areas, and improves the recharging and docking precision of the robot.
Further, the step S3 specifically includes: step S31, matching the feature points of the real-time shot environment image with the feature points of the pre-stored charging seat guide identification image by using a feature matching method; step S32, calculating and determining the similarity between the real-time shot environment image and the guide identification image according to the Euclidean distance or the Hamming distance of each pair of feature points matched in the step S31; step S33, setting the position corresponding to the environment image with the highest similarity of the guidance identification image as the first preset refill position; the first preset recharging position is set to be a position away from the charging seat by a preset distance. In this embodiment, the euclidean distance or the hamming distance is calculated by extracting the feature points of the environmental image, so that the memory of the image can be reduced, the space can be saved during storage, and the comparison of the feature points during comparison can reduce the comparison workload.
Further, in step S4, the method for planning a preset path according to the intensity of the infrared guidance signal received at the current position and the environment image information with the similarity matching includes: step S41, in the remote infrared radiation area, selecting the direction of increasing the intensity of the infrared guiding signal as the path trend of the preset path from the current position of the robot to the first preset recharging position; step S42, marking the current position of the robot according to the internal reference of the camera, expanding nodes at positions near the current position of the robot without marks along the path direction, and marking newly expanded nodes; step S43, when the node expands to the first preset refilling position, marking the first preset refilling position as a target node, and then connecting all marked nodes to generate the preset path. According to the technical scheme, the first preset recharging position is used as the target node, so that the shortest path can be generated, and the working efficiency of robot recharging and butt joint is improved.
Further, in step S5, when the guiding identifier of the charging dock is captured at the first preset recharging position, the distance between the first preset recharging position and the charging dock is calculated according to an environment image obtained by a camera in real time; and then adjusting the posture of the robot per se, further walking to the charging seat from the first preset recharging position in a straight line, and moving to align the electrode of the charging seat in the short-range infrared radiation area so as to finish the autonomous recharging. According to the technical scheme, the charging seat can be found only through the collected guiding identification image of the charging seat without the guiding of an infrared signal, and the recharging speed is improved.
Further, in step S6, the method for adjusting the pose of the robot from the first preset recharging position to the second preset recharging position specifically includes: and controlling the robot to rotate or displace in situ towards the gradually-increased direction of the infrared guide signal, so that the pose of the robot is adjusted from the first preset recharging position to the second preset recharging position, wherein the second preset recharging position is not limited to exist in the remote infrared radiation area or the short-range infrared radiation area. According to the technical scheme, the second preset recharging position is deployed in an infrared guiding mode to provide an initial recharging position combining infrared vision and repeated guiding for the robot, and the robot is finally docked and recharged with a charging seat in an auxiliary vision guiding mode, so that the docking and recharging success rate of the robot is greatly improved.
A chip is used for storing a program, the program is used for controlling a robot to execute the robot recharging method, the robot recharging is guided by an auxiliary visual identification through large-range infrared guiding recharging, the working efficiency of the visual guiding recharging and the success rate of the guiding identification of a visual identification charging seat are improved, the robot is prevented from carrying out carpet type infrared signal searching in the butt-joint recharging process, and the electric quantity loss of the robot in the low-efficiency recharging is further avoided.
Drawings
Fig. 1 is a flowchart of a robot recharging method based on visual identification according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for determining the first preset recharge location according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for planning the preset path according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a robot recharging method based on visual identification, including the steps of:
step S101, after the robot enters a charging mode, sending a charging signal to a charging seat, and then entering step S102; under this embodiment, the robot carries out the instruction interaction through wireless connection mode with the charging seat, and the robot sends the charging instruction to the charging seat through wireless mode, and then the charging seat starts infrared light source and sends infrared signal, and the robot passes through infrared receiver tube search, discovery, the infrared signal that the discernment charging seat sent.
Step S102, when the robot receives infrared guide signals radiated by the charging seat outwards in all directions of the current position, the robot starts a camera to collect a guide identifier arranged on the charging seat in real time, and then the step S103 is carried out. In this embodiment, the charging base starts the infrared light source, and emits an infrared guiding signal toward the ceiling, and particularly, the infrared guiding signal is scattered by the convex lens installed on the upper portion of the infrared light source, and then reflected by the reflector, and then radiates an infrared light signal outward in a four-point divergent manner. Because infrared guide signal transmission spherical wave to with 360 omnidirectional emission infrared guide signal, thereby ensure that charging seat any position all around can have infrared light signal, make the robot all receive the infrared guide signal of charging seat external radiation in each position of current position, do not have the dead angle of infrared radiation in the region that the camera was gathered in real time at least.
Optionally, in step S102, the infrared guiding signal radiated outward is an infrared encoding signal emitted from an infrared light source of the charging seat to a ceiling, and a coverage area of the infrared encoding signal is a spherical area range centered on the charging seat, and for a scene condition of movement of the charging seat, in the case that the camera does not acquire a guiding identification image of the charging seat, the technical scheme assists the robot in visual guiding recharging by receiving the infrared guiding signal with a large radiation range emitted by the charging seat, so as to solve a visual acquisition blind area caused by movement of the charging seat.
Step S103, according to the similarity between the environment image shot in real time and the pre-stored guide identification image of the charging seat, determining that the position corresponding to the environment image matched with the similarity of the guide identification image is the first preset recharging position, and then entering step S104. According to the technical scheme, the first preset recharging position is determined by collecting the guide identification image, so that a short-distance recharging docking area is provided for infrared signal guide, and the docking success rate of the robot is improved.
In the embodiment of the present invention, an active visual guidance device may be installed on the charging base, the active visual guidance device is installed with a light source capable of emitting visible light or infrared light, and the light source has obvious shape or texture features, constituting an image mark that can be distinguished obviously, and the size of the mark must be ensured to be visible and distinguishable within a certain range. The active visual guidance device must be powered to operate before automatic charging begins. In which a visible or infrared band camera is installed above the charging electrode of the robot, it should be noted that the camera type must match the lighting type of the active visual guidance device on the charging stand. Due to the active visual guide markers, the exposure time of the camera does not need to be set too large. In addition, a processor which can be used for image processing and alignment control calculation is installed on the robot, and the signal wire of the camera is connected to the data interface of the image processor. Meanwhile, an output signal wire of the processor is connected with a motor drive control module interface of the mobile robot.
Step S104, planning a preset path according to the intensity of the infrared guide signal received by the robot at the current position and the environment image information matched with the similarity, controlling the robot to move to the first preset recharging position along the preset path, and then entering step S105. And S105, judging whether the first preset recharging position shoots a guide identifier of the charging seat, if so, controlling the robot to move from the first preset recharging position to align with an electrode of the charging seat to finish charging, otherwise, entering the step S106. After the robot completes the matching of the environment image shot in real time and the pre-stored guide identifier image of the charging seat, in the process of moving along the preset path, aiming at the situation that the charging seat moves, the first preset recharging position provided by the technical scheme provides a position for reconfirming the guide identifier of the charging seat for the robot.
And S106, adjusting the pose of the robot from the first preset recharging position to a second preset recharging position according to the intensity of the infrared guide signal received by the first preset recharging position, and then repeating the steps S103 to S105 until the robot is aligned with the electrode of the charging seat to finish charging. According to the technical scheme, the second preset recharging position is arranged to provide an initial recharging position combining infrared vision with repeated guidance for the robot, the robot recharges in a remote infrared radiation area by using the visual identification, whether the charging seat is kept at the original position or not is judged firstly when the charging seat is close to the charging seat, and then the robot is finally docked and charged with the charging seat under the action of the infrared guidance signal by assisting the visual guidance, so that the robot is simpler and more convenient to use, the docking success rate of the robot is greatly improved, and the efficiency is also greatly improved.
In this embodiment, the robot does not necessarily start from the charging stand when starting to operate, and may start cleaning after the user directly puts the robot in a certain room, or may start operating from a certain corner of the room. When the robot cleans according to the track specified by the preset logic algorithm, the vision sensor of the robot, such as a camera, also collects the image of the surrounding environment, in this embodiment, as long as the guidance identifier of the charging seat is collected, the position of the robot at the time of collecting the image of the environment is also calculated, the position of the robot is recorded, the starting point of the robot is taken as the reference for recording, for example, the displacement and the direction of the robot from the starting point to the point of collecting the image of the guidance identifier of the charging seat can be recorded, and the robot records the motion track of the robot in real time when in work. When the robot starts recharging, the collected environment image is compared with a guide identification image of a charging seat, which is stored in the sweeping robot in advance by a user or shot and stored when the sweeping robot is at a charging position, an environment image with the highest similarity with the guide identification image of the charging seat is found out, and then the environment image is moved to a first preset recharging position corresponding to the environment image with the highest similarity along a planned path; after the robot reaches the first preset recharging position, if the charging seat guide mark does not appear in the shot environment image, the infrared guide signal sent by the charging seat is received, the infrared guide signal is controlled to guide and adjust the robot to the second preset recharging position by recognizing the intensity change condition of the infrared guide signal, and then the robot is guided to automatically walk to the charging seat according to the searched and recognized guide mark image of the charging seat so as to charge the electrode.
The preset rule for acquiring the environment image may be to acquire the environment image once every a period of time or once every a distance. The recharging command is generated, and may be a recharging command generated after the electric quantity of the robot is lower than a preset threshold value or a command for ending work sent by a user is received. In this embodiment, the vision sensor is configured to acquire the moving position of the robot by using internal reference of the camera, and acquire the posture of the robot in real time, so that the robot recognizes the position of the robot in the environment.
Under this embodiment the guide identification is the two-dimensional code, and the two-dimensional code is the picture alternate between black and white, and the degree of discernment is high, simple manufacture. The guide mark is placed on the center position of the electrode of the charging seat, so that the robot can conveniently recognize and align.
Optionally, the infrared light source of the charging seat radiates an infrared code signal outwards, wherein the coverage area of the infrared code signal is a spherical area range centered on the charging seat, the spherical area range is divided into a remote infrared radiation area and a short infrared radiation area, and the first preset recharging position is used as a boundary position of the remote infrared radiation area and the short infrared radiation area. Aiming at the situation that the charging seat moves, the first preset recharging position provided by the technical scheme provides a position for the robot to reconfirm the guide identifier of the charging seat, provides an operation space for the robot to play a role in cooperation of infrared vision recharging guide in different infrared radiation areas, and improves the recharging and docking precision of the robot.
Optionally, as shown in fig. 2, the step S103 specifically includes: step S1031, matching the feature points of the environment image shot in real time with the feature points of the pre-stored charging seat guide identification image by using a feature matching method, and then entering step S1032; the matching of the feature points is performed for the feature descriptors of the guide identification image of the charging seat, the feature descriptors are usually a vector, the distance between the two feature descriptors can reflect the similarity degree, that is, the two feature points are not the same, so that the matching of the feature points is performed according to the distance between the feature descriptors of the environment image shot in real time and the feature descriptors of the guide identification image of the charging seat stored in advance.
Step S1032, calculating and determining the similarity between the real-time shot environment image and the guide identification image according to the Euclidean distance or the Hamming distance of each pair of feature points matched in the step S1031; it should be noted that different distance measures can be selected according to different descriptors. If the descriptor is a floating point type descriptor, the Euclidean distance of the descriptor can be used; for binary descriptors (BRIEF), their hamming distance (hamming distance between two different binary strings refers to the number of different bits of two binary strings) can be used. With the method of calculating the similarity of descriptors, finding the most similar feature point in the set of feature points is the matching of the feature points. The specific method comprises the following steps: firstly, the distances between a certain feature point descriptor and all other feature point descriptors are calculated, then the obtained distances are sorted, and the closest one is taken as a matching point. The result of this approach is also obvious, as it is simple and crude, and although there are a large number of false matches, some mechanism can be used to filter out false matches. For example, the hamming distance of the matched point pair is selected to be less than twice of the minimum distance as a judgment basis, if the hamming distance is less than the minimum distance, an error match is considered, and filtering is performed; a match greater than this value is considered a correct match.
Step S1033, where the position corresponding to the environment image with the highest similarity to the guidance identification image is the first preset refill position; the first preset recharging position is set to be a position away from the charging seat by a preset distance. In this embodiment, the euclidean distance or the hamming distance is calculated by extracting the feature points of the environmental image, so that the memory of the image can be reduced, the space can be saved during storage, and the comparison of the feature points during comparison can reduce the comparison workload.
Optionally, as shown in fig. 3, in step S104, the method for planning a preset path according to the intensity of the infrared guidance signal received at the current position of the user and the environment image information with the similarity matching includes:
step S1041, in the remote infrared radiation area, selecting, from the direction of the path from the current position of the robot to the first preset recharging position, a direction in which the intensity of the infrared guidance signal increases as a path direction of the preset path; because infrared guide signal transmission spherical wave to with 360 omnidirectional emission infrared guide signal, thereby ensure that charging seat any position all around can have infrared light signal, make the robot all receive the infrared guide signal of charging seat external radiation in each position of current position, and can sense infrared light intensity after the charging seat removes and change.
Step S1042, marking the current position of the robot according to the internal parameters of the camera, expanding nodes at positions near the current position of the robot without marks along the path direction, and marking newly expanded nodes; the marking the current position of the robot according to the internal reference of the camera comprises: and calculating the relative position relationship between the robot and the guide identifier according to the internal parameters of the vision sensor of the robot, so as to mark the current position coordinate of the robot in a global coordinate system.
Step S1043, when the node is expanded to the first preset recharge position, marking the first preset recharge position as a target node, then setting a path weight between every two marked nodes according to the relative position relationship, and generating the preset path by combining all marked node path connections, which is beneficial to generating a shortest path, and after the shortest path is obtained, controlling the robot to move to the first preset recharge position along the shortest path, thereby improving the working efficiency of robot recharge docking.
Optionally, in step S105, when the guidance identifier of the charging dock is captured at the first preset recharging position, calculating a distance between the first preset recharging position and the charging dock according to an environment image obtained by a camera in real time; and then adjusting the posture of the robot per se, further walking to the charging seat from the first preset recharging position in a straight line, and moving to align the electrode of the charging seat in the short-range infrared radiation area so as to finish the autonomous recharging. According to the technical scheme, the charging seat can be found only through the collected guiding identification image of the charging seat without the guiding of an infrared signal, and the recharging speed is improved. In this embodiment, after the charging seat is recognized, if the distance between the robot and the charging seat is smaller than the preset distance, it may be considered that the robot crosses the first preset recharging position, if the charging seat remains in the original position without displacement, the robot enters the short-range infrared radiation area, otherwise, a further determination is made according to the intensity of the received infrared guiding signal, where the determination may be based on a distance value measured by photographing with a camera or based on a distance between the directional measurement of the distance sensor and the charging seat, and the guiding identifier is used as a reference to determine the specific position of the charging seat.
Optionally, in step S106, the method for adjusting the pose of the robot from the first preset recharging position to the second preset recharging position specifically includes: controlling the robot to rotate or displace in situ towards the gradually-increased direction of the infrared guide signal, so that the pose of the robot is adjusted from the first preset recharging position to the second preset recharging position, and the robot does not remain at the original position due to the fact that the charging seat is moved; and when the charging seat moves to an accessory area of the home position, determining that the second preset recharging position exists in the short-range infrared radiation area, otherwise, setting the second preset recharging position in the long-range infrared radiation area. According to the technical scheme, the second preset recharging position is deployed in an infrared guiding mode to provide an initial recharging position combining infrared vision and repeated guiding for the robot, and the robot is finally docked and recharged with a charging seat in an auxiliary vision guiding mode, so that the docking and recharging success rate of the robot is greatly improved.
It should be noted that the present invention uses a square mark as the guide mark, and those skilled in the art can easily conceive of the improvement method using a plurality of geometric figures (a plurality of squares, one or more triangles, a plurality of circles, or black and white grids).
A chip is used for storing a program, the program is used for controlling a robot to execute the robot recharging method, the robot recharging is guided by an auxiliary visual identification through large-range infrared guiding recharging, the working efficiency of the visual guiding recharging and the success rate of the guiding identification of a visual identification charging seat are improved, the robot is prevented from carrying out carpet type infrared signal searching in the butt-joint recharging process, and the electric quantity loss of the robot in the low-efficiency recharging is further avoided.
In the embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Claims (6)
1. A robot recharging method based on visual identification comprises the following steps: step S1, after the robot enters the charging mode, sending a charging signal to the charging seat; it is characterized by also comprising:
step S2, when the robot receives the infrared guide signal radiated from the charging seat in each direction of the current position, the robot starts the camera to collect the guide mark set on the charging seat in real time;
step S3, according to the similarity between the environment image shot in real time and the pre-stored guide identification image of the charging seat, determining the position corresponding to the environment image matched with the similarity of the guide identification image as a first preset recharging position;
step S4, planning a preset path according to the intensity of the infrared guide signal received by the robot at the current position and the environment image information matched with the similarity, and controlling the robot to move to a first preset recharging position along the preset path;
step S5, judging whether the first preset recharging position shoots the guide identification of the charging seat, if so, controlling the robot to move from the first preset recharging position to align with the electrode of the charging seat to complete charging, otherwise, entering step S6;
step S6, adjusting the pose of the robot from the first preset recharging position to a second preset recharging position according to the intensity of the infrared guide signal received by the first preset recharging position, and then repeating the steps S3 to S5 until the robot is aligned with the electrode of the charging seat to finish charging;
the infrared guide signal radiated outwards is an infrared coding signal emitted from an infrared light source of the charging seat to a ceiling, and the coverage range of the infrared coding signal is a spherical area range taking the charging seat as a center;
the sphere area range is divided into a long-range infrared radiation area and a short-range infrared radiation area, and the first preset recharging position is used as a boundary position of the long-range infrared radiation area and the short-range infrared radiation area.
2. The robot recharging method of claim 1, wherein the step S3 specifically includes:
step S31, matching the feature points of the real-time shot environment image with the feature points of the pre-stored charging seat guide identification image by using a feature matching method;
step S32, calculating and determining the similarity between the real-time shot environment image and the guide identification image according to the Euclidean distance or the Hamming distance of each pair of feature points matched in the step S31;
step S33, setting the position corresponding to the environment image with the highest similarity of the guidance identification image as the first preset refill position;
the first preset recharging position is set to be a position away from the charging seat by a preset distance.
3. The robot recharging method of claim 2, wherein in step S4, the method for planning a preset path according to the intensity of the infrared guiding signal received at the current position and the environment image information with the matching similarity includes:
step S41, in the remote infrared radiation area, selecting the direction of increasing the intensity of the infrared guiding signal as the path trend of the preset path from the current position of the robot to the first preset recharging position;
step S42, marking the current position of the robot according to the internal reference of the camera, expanding nodes at positions near the current position of the robot without marks along the path direction, and marking newly expanded nodes;
step S43, when the node expands to the first preset refilling position, marking the first preset refilling position as a target node, and then connecting all marked nodes to generate the preset path.
4. The robot recharging method of claim 1, wherein in step S5, when the guiding id of the charging dock is captured at the first preset recharging location, the distance between the first preset recharging location and the charging dock is calculated according to an environment image obtained by a camera in real time; and then adjusting the posture of the robot per se, further walking to the charging seat from the first preset recharging position in a straight line, and moving to align the electrode of the charging seat in the short-range infrared radiation area so as to finish the autonomous recharging.
5. The robot recharging method according to claim 4, wherein in step S6, the method for adjusting the pose of the robot from the first preset recharging position to the second preset recharging position is specifically:
and controlling the robot to rotate or displace in situ towards the gradually-increased direction of the infrared guide signal, so that the pose of the robot is adjusted from the first preset recharging position to the second preset recharging position, wherein the second preset recharging position is not limited to exist in the remote infrared radiation area or the short-range infrared radiation area.
6. A chip for storing a program for controlling a robot to perform the robot refilling method according to claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603402.5A CN109669457B (en) | 2018-12-26 | 2018-12-26 | Robot recharging method and chip based on visual identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603402.5A CN109669457B (en) | 2018-12-26 | 2018-12-26 | Robot recharging method and chip based on visual identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109669457A CN109669457A (en) | 2019-04-23 |
| CN109669457B true CN109669457B (en) | 2021-08-24 |
Family
ID=66146247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811603402.5A Active CN109669457B (en) | 2018-12-26 | 2018-12-26 | Robot recharging method and chip based on visual identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109669457B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378285A (en) * | 2019-07-18 | 2019-10-25 | 北京小狗智能机器人技术有限公司 | A kind of recognition methods of cradle, device, robot and storage medium |
| CN112405518B (en) * | 2019-08-23 | 2022-08-23 | 深圳拓邦股份有限公司 | Robot control method, robot and automatic backtracking system of robot |
| CN110597255B (en) * | 2019-09-11 | 2022-08-09 | 珠海一微半导体股份有限公司 | Method for establishing safety zone by using seat avoidance signal |
| CN110597265A (en) * | 2019-09-25 | 2019-12-20 | 深圳巴诺机器人有限公司 | Recharging method and device for sweeping robot |
| CN111103879A (en) * | 2019-12-12 | 2020-05-05 | 南京苏美达智能技术有限公司 | Guiding method of self-walking equipment and self-walking equipment |
| CN111753695B (en) * | 2020-06-17 | 2023-10-13 | 上海宜硕网络科技有限公司 | Method and device for simulating robot charging return route and electronic equipment |
| CN114077246A (en) * | 2020-08-21 | 2022-02-22 | 苏州三六零机器人科技有限公司 | Recharging method and device for sweeping robot, sweeping robot and readable medium |
| CN114601373B (en) * | 2021-10-18 | 2023-07-04 | 北京石头世纪科技股份有限公司 | Control method and device of cleaning robot, cleaning robot and storage medium |
| CN114397886B (en) * | 2021-12-20 | 2024-01-23 | 烟台杰瑞石油服务集团股份有限公司 | Charging method and charging system |
| CN115173890B (en) * | 2022-06-30 | 2024-02-20 | 珠海一微半导体股份有限公司 | Recharging control method, recharging control system and recharging control chip for multiple robots |
| CN115191887A (en) * | 2022-07-14 | 2022-10-18 | 杭州萤石软件有限公司 | Control method and control device for cleaning robot and cleaning robot system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060099684A (en) * | 2005-03-14 | 2006-09-20 | 삼성광주전자 주식회사 | Gyro-scope calibration apparatus and calibration method having the same |
| US7227327B2 (en) * | 2005-06-07 | 2007-06-05 | Lg Electronics Inc. | System and method for automatically returning self-moving robot to charger |
| CN102773862A (en) * | 2012-07-31 | 2012-11-14 | 山东大学 | Quick and accurate locating system used for indoor mobile robot and working method thereof |
| CN103066645A (en) * | 2012-12-14 | 2013-04-24 | 安科智慧城市技术（中国）有限公司 | Robot and system and method of automatic charging thereof |
| CN106125724A (en) * | 2016-06-13 | 2016-11-16 | 华讯方舟科技有限公司 | A kind of method and system of robot autonomous charging |
| CN107092264A (en) * | 2017-06-21 | 2017-08-25 | 北京理工大学 | Towards the service robot autonomous navigation and automatic recharging method of bank's hall environment |
| CN107392962A (en) * | 2017-08-14 | 2017-11-24 | 深圳市思维树科技有限公司 | A kind of robot charging docking system and method based on pattern identification |
| CN107945233A (en) * | 2017-12-04 | 2018-04-20 | 深圳市沃特沃德股份有限公司 | Vision sweeping robot and its recharging method |
| CN207319066U (en) * | 2017-09-30 | 2018-05-04 | 天津智汇时代科技有限公司 | A kind of automatic charging system based on monocular vision and infrared sensor |
-
2018
- 2018-12-26 CN CN201811603402.5A patent/CN109669457B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060099684A (en) * | 2005-03-14 | 2006-09-20 | 삼성광주전자 주식회사 | Gyro-scope calibration apparatus and calibration method having the same |
| US7227327B2 (en) * | 2005-06-07 | 2007-06-05 | Lg Electronics Inc. | System and method for automatically returning self-moving robot to charger |
| CN102773862A (en) * | 2012-07-31 | 2012-11-14 | 山东大学 | Quick and accurate locating system used for indoor mobile robot and working method thereof |
| CN103066645A (en) * | 2012-12-14 | 2013-04-24 | 安科智慧城市技术（中国）有限公司 | Robot and system and method of automatic charging thereof |
| CN106125724A (en) * | 2016-06-13 | 2016-11-16 | 华讯方舟科技有限公司 | A kind of method and system of robot autonomous charging |
| CN107092264A (en) * | 2017-06-21 | 2017-08-25 | 北京理工大学 | Towards the service robot autonomous navigation and automatic recharging method of bank's hall environment |
| CN107392962A (en) * | 2017-08-14 | 2017-11-24 | 深圳市思维树科技有限公司 | A kind of robot charging docking system and method based on pattern identification |
| CN207319066U (en) * | 2017-09-30 | 2018-05-04 | 天津智汇时代科技有限公司 | A kind of automatic charging system based on monocular vision and infrared sensor |
| CN107945233A (en) * | 2017-12-04 | 2018-04-20 | 深圳市沃特沃德股份有限公司 | Vision sweeping robot and its recharging method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109669457A (en) | 2019-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109669457B (en) | Robot recharging method and chip based on visual identification | |
| CN109890573B (en) | Control method and device for mobile robot, mobile robot and storage medium | |
| WO2019144541A1 (en) | Cleaning robot | |
| CN109683605B (en) | Robot and automatic recharging method and system thereof, electronic equipment and storage medium | |
| KR102403504B1 (en) | Mobile Robot And Method Thereof | |
| CN107945233B (en) | Visual floor sweeping robot and refilling method thereof | |
| WO2020199589A1 (en) | Recharging control method for desktop robot | |
| US10482619B2 (en) | Method and apparatus for combining data to construct a floor plan | |
| CN105242670B (en) | Robot, system and corresponding method with auto-returned charge function | |
| US20190254490A1 (en) | Vacuum cleaner and travel control method thereof | |
| CN108062098B (en) | Map construction method and system for intelligent robot | |
| CN109508014A (en) | A kind of the laser aiming recharging method and chip of mobile robot | |
| CN109199240B (en) | Gesture control-based sweeping robot control method and system | |
| KR20160146379A (en) | Moving robot and controlling method thereof | |
| US20210276441A1 (en) | A computerized system for guiding a mobile robot to a docking station and a method of using same | |
| WO2023025028A1 (en) | Charging method, charging apparatus, and robot | |
| US10983528B2 (en) | Systems and methods for orienting a robot in a space | |
| EP2776216A1 (en) | Scaling vector field slam to large environments | |
| WO2017092565A1 (en) | Charging system and charging method, computer storage medium | |
| JP7127303B2 (en) | AUTONOMOUS MOBILE DEVICE, AUTONOMOUS MOVEMENT METHOD AND PROGRAM | |
| CN112819943B (en) | Active vision SLAM system based on panoramic camera | |
| CN113467451A (en) | Robot recharging method and device, electronic equipment and readable storage medium | |
| CN113014658B (en) | Device control, device, electronic device, and storage medium | |
| JP2002268746A (en) | Mobile robot device and self-charging method for mobile robot device and medium for providing its control program | |
| CN110133681B (en) | Recharge guiding system based on laser radar and recharge guiding method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 519000 2706, No. 3000, Huandao East Road, Hengqin new area, Zhuhai, Guangdong Patentee after: Zhuhai Yiwei Semiconductor Co.,Ltd. Country or region after: China Address before: Room 105-514, No.6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Patentee before: AMICRO SEMICONDUCTOR Co.,Ltd. Country or region before: China |