Robot control method and device and storage medium

Abstract

The invention provides a robot control method and device and a storage medium, and the method comprises the steps: determining a meeting reference route of any target robot in a meeting state according to the current position of the target robot and an initial planning route; performing path planning processing in a temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route; wherein the target boundary is an original boundary corresponding to the preset offset direction side; evaluating each candidate meeting route according to a predetermined evaluation index, and screening out an optimal meeting route meeting the meeting requirements; and controlling the target robot to run along the optimal meeting route. Therefore, based on dynamic path planning, flexible temporary vehicle meeting channels and a multi-path evaluation screening mechanism, the problems of low vehicle meeting efficiency, unstable path planning, difficulty in vehicle meeting planning and the like on narrow roads are effectively solved, and efficient vehicle meeting of the robot in a complex dynamic environment is realized.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a robot control method, device and storage medium. Background Art

[0002] In complex and dynamic indoor environments, robots need to share road resources with other robots and pedestrians in a limited space to ensure efficient and safe completion of tasks. However, as the number of robots increases and the complexity of the scene increases, the problem of encounters and passing between robots becomes particularly prominent. If multiple robots cannot meet in a timely and smooth manner when they meet on a narrow road, it may cause road congestion, delay delivery time, and even affect pedestrian safety.

[0003] In order to solve these problems, the prior art has proposed some solutions. One is to draw a virtual wall in the middle of the road on the map to divide the road into different movement areas, so as to avoid robots meeting on the same road. However, this method requires complex map planning when the system is deployed, which increases the difficulty and time cost of deployment. The second is to set avoidance points beside the road during the deployment stage. When two robots meet, the system decides to let one robot go to the avoidance point and continue the original task after the other robot passes. However, this method not only complicates the overall operation of the robot system, but also reduces the efficiency of multiple robots working in parallel. The third is to control the two robots to move along the slow-moving path when determining the meeting, but this solution does not take into account the current position of the robot, and mechanically generates the central axis according to the static map. The meeting route determined by the penalty value of the central axis may require the robot to repeatedly deviate, resulting in unstable robot movement and low meeting efficiency. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a robot control method, device and storage medium, which, based on dynamic path planning, flexible temporary meeting channels and multi-route evaluation and screening mechanism, effectively solves the problems of low meeting efficiency on narrow roads, unstable path planning, difficult meeting planning, etc., and realizes the robot's efficient meeting in a complex dynamic environment.

[0005] The present application provides a robot control method, the control method comprising:

[0006] For any target robot in the oncoming state, determine the oncoming reference route of the target robot according to the current position of the target robot and the initial planned route;

[0007] Performing path planning processing in a temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route; wherein the target boundary is an original boundary corresponding to a preset offset direction side;

[0008] Evaluate each candidate meeting route according to the predetermined evaluation index, and select the optimal meeting route that meets the meeting requirements;

[0009] The target robot is controlled to travel along the optimal meeting route.

[0010] Optionally, determining a reference route for meeting the target robot according to the current position of the target robot and the initial planned route includes:

[0011] Determine a target path point on the initial planned route that is closest to the current position of the target robot;

[0012] According to at least one of the scene of the meeting area, the driving speed of at least one target robot, and the device size of at least one target robot, a first length of the required interception route is set;

[0013] Taking the target path point as a starting point, along the current driving direction of the target robot, a route of a first length is intercepted from the initial planned route as a meeting reference route for the target robot.

[0014] Optionally, performing path planning processing in a temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route includes:

[0015] Determine a point on the meeting reference route that is a second length away from the starting point of the meeting reference route as a leading reference point; wherein the second length is determined according to the current speed of the target robot and the target offset distance;

[0016] Sampling is performed at intervals of a third length on the meeting reference route starting from the preceding reference point until the designated end point on the meeting reference route ends, and at least one longitudinal sampling point is determined; wherein the third length is determined according to the length from the preceding reference point to the designated end point on the meeting reference route and a preset number of longitudinal samplings;

[0017] For each longitudinal sampling point, a fourth length is used as a sampling step length, and the corresponding target offset distance is used as a full length, and transverse sampling is performed to determine at least one transverse sampling point located on the same straight line as the longitudinal sampling point; wherein the fourth length is determined according to the target offset distance and a preset transverse sampling quantity;

[0018] According to the current position of the target robot, the front reference point, all longitudinal sampling points and all transverse sampling points, each column of longitudinal arrangement points is fitted respectively to determine at least one candidate meeting route.

[0019] Optionally, the step of evaluating each candidate meeting route according to a predetermined evaluation index to select an optimal meeting route that meets the meeting requirements includes:

[0020] For each candidate meeting route, determining an index evaluation value of the candidate meeting route under each predetermined evaluation index;

[0021] Performing weighted processing on all index evaluation values ​​corresponding to the candidate meeting route to determine the route evaluation value of the candidate meeting route;

[0022] Identify whether the candidate meeting route with the highest route evaluation value and the candidate meeting route with the highest route evaluation value of another target robot corresponding to the meeting state meet the meeting route interval requirement;

[0023] If the conditions are met, the candidate meeting route with the highest route evaluation value is determined as the optimal meeting route for the target robot.

[0024] Optionally, the predetermined evaluation index includes at least one of the following: curvature, distance from a reference route for meeting other vehicles, and distance from a preset obstacle boundary.

[0025] Optionally, determine the target offset distance by following these steps:

[0026] Determine the width of the temporary passage at any position based on the reference route and the preset obstacle boundary;

[0027] For any position in the temporary channel, a candidate offset distance at the position is determined according to the channel width at the position and a preset length setting strategy;

[0028] If the candidate offset distance does not exceed the preset threshold length, the candidate offset distance is determined as the target offset distance at the position;

[0029] If exceeded, the preset threshold length is determined as the target offset distance at the position.

[0030] Optionally, controlling the target robot to travel along the optimal meeting route includes:

[0031] Real-time identification of the position of the target robot traveling along the optimal meeting route;

[0032] updating the optimal meeting route according to the identified real-time position and the meeting reference route;

[0033] And control the target robot to travel along the updated optimal meeting route.

[0034] Optionally, after controlling the target robot to travel along the optimal meeting route, the control method further includes:

[0035] The positions of the two target robots traveling along the optimal meeting route are identified in real time to determine whether the two target robots pass through the same area;

[0036] If so, send a meeting end instruction and control the robot to drive along the initial planned route.

[0037] The present application also provides a robot control device, the control device comprising:

[0038] A first determination module is used to determine, for any target robot in a meeting state, a meeting reference route of the target robot according to the current position of the target robot and an initial planned route;

[0039] A generation module, used for performing path planning processing in a temporary meeting channel formed by the meeting reference route and a target boundary, and generating at least one candidate meeting route; wherein the target boundary is an original boundary corresponding to a preset offset direction side;

[0040] A screening module is used to evaluate each candidate meeting route according to a predetermined evaluation index and screen out the optimal meeting route that meets the meeting requirements;

[0041] The control module is used to control the target robot to travel along the optimal meeting route.

[0042] Optionally, when the first determining module is used to determine the oncoming reference route of the target robot according to the current position of the target robot and the initial planned route, the first determining module is used to:

[0043] Determine a target path point on the initial planned route that is closest to the current position of the target robot;

[0044] According to at least one of the scene of the meeting area, the driving speed of at least one target robot, and the device size of at least one target robot, a first length of the required interception route is set;

[0045] Taking the target path point as a starting point, along the current driving direction of the target robot, a route of a first length is intercepted from the initial planned route as a meeting reference route for the target robot.

[0046] Optionally, when the generating module is used to perform path planning processing in a temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route, the generating module is used to:

[0047] Determine a point on the meeting reference route that is a second length away from the starting point of the meeting reference route as a leading reference point; wherein the second length is determined according to the current speed of the target robot and the target offset distance;

[0048] Sampling is performed at intervals of a third length on the meeting reference route starting from the preceding reference point until the designated end point on the meeting reference route ends, and at least one longitudinal sampling point is determined; wherein the third length is determined according to the length from the preceding reference point to the designated end point on the meeting reference route and a preset number of longitudinal samplings;

[0049] For each longitudinal sampling point, a fourth length is used as a sampling step length, and the corresponding target offset distance is used as a full length, and transverse sampling is performed to determine at least one transverse sampling point located on the same straight line as the longitudinal sampling point; wherein the fourth length is determined according to the target offset distance and a preset transverse sampling quantity;

[0050] According to the current position of the target robot, the front reference point, all longitudinal sampling points and all transverse sampling points, each column of longitudinal arrangement points is fitted respectively to determine at least one candidate meeting route.

[0051] Optionally, when the screening module is used to evaluate each candidate meeting route according to a predetermined evaluation index and screen out an optimal meeting route that meets the meeting requirements, the screening module is used to:

[0052] For each candidate meeting route, determining an index evaluation value of the candidate meeting route under each predetermined evaluation index;

[0053] Performing weighted processing on all index evaluation values ​​corresponding to the candidate meeting route to determine the route evaluation value of the candidate meeting route;

[0054] Identify whether the candidate meeting route with the highest route evaluation value and the candidate meeting route with the highest route evaluation value of another target robot corresponding to the meeting state meet the meeting route interval requirement;

[0055] If the conditions are met, the candidate meeting route with the highest route evaluation value is determined as the optimal meeting route for the target robot.

[0056] Optionally, the predetermined evaluation index includes at least one of the following: curvature, distance from a reference route for meeting other vehicles, and distance from a preset obstacle boundary.

[0057] Optionally, the control device further includes a second determining module, and the second determining module is used to determine the target offset distance through the following steps:

[0058] Determine the width of the temporary passage at any position based on the reference route and the preset obstacle boundary;

[0059] For any position in the temporary channel, a candidate offset distance at the position is determined according to the channel width at the position and a preset length setting strategy;

[0060] If the candidate offset distance does not exceed the preset threshold length, the candidate offset distance is determined as the target offset distance at the position;

[0061] If exceeded, the preset threshold length is determined as the target offset distance at the position.

[0062] Optionally, when the control module is used to control the target robot to travel along the optimal meeting route, the control module is used to:

[0063] Real-time identification of the position of the target robot traveling along the optimal meeting route;

[0064] updating the optimal meeting route according to the identified real-time position and the meeting reference route;

[0065] And control the target robot to travel along the updated optimal meeting route.

[0066] Optionally, the control device further includes an ending module, and the ending module is used to:

[0067] After controlling the target robot to travel along the optimal meeting route, real-time identification is performed on the positions of the two target robots traveling along the optimal meeting route to determine whether the two target robots pass through the same area;

[0068] If so, send a meeting end instruction and control the robot to drive along the initial planned route.

[0069] An embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method described above are performed.

[0070] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the control method described above are executed.

[0071] The embodiments of the present application provide a robot control method, device and storage medium, the control method comprising: for any target robot in a meeting state, determining a meeting reference route of the target robot according to the current position of the target robot and an initially planned route; performing path planning processing in a temporary meeting channel formed by the meeting reference route and a target boundary, and generating at least one candidate meeting route; wherein the target boundary is an original boundary corresponding to a preset offset direction side; evaluating each candidate meeting route according to a predetermined evaluation index, and screening out an optimal meeting route that meets the meeting requirements; and controlling the target robot to travel along the optimal meeting route.

[0072] In this way, the present application generates a "reference route for meeting vehicles" based on the current position of the target robot and the initial planned route, so that the route planning is more in line with the actual scene conditions, reducing the problem of repeated offsets of the robot and improving the stability of meeting vehicles. In addition, the channel range is adjusted in real time according to the dynamic changes in the current environment, reducing the dependence on complex map planning and fixed avoidance points, and reducing the difficulty and time cost of deployment. In addition, multiple candidate meeting routes are generated, and these routes are screened based on predetermined evaluation indicators to select the optimal route. This method not only improves the efficiency of meeting vehicles, but also ensures the smooth operation of the robot during the meeting process.

[0073] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0075] Figure 1 A schematic diagram of the structure of a delivery robot provided in an embodiment of the present application;

[0076] Figure 2 A flowchart of a robot control method provided in an embodiment of the present application;

[0077] Figure 3 A schematic diagram of the initial planned route provided for this application;

[0078] Figure 4 A schematic diagram of a candidate route provided for this application;

[0079] Figure 5A schematic diagram of a meeting along an optimal meeting route provided by the present application;

[0080] Figure 6 A schematic diagram of movement after a vehicle meeting is provided in this application;

[0081] Figure 7 A schematic diagram of the structure of a robot control device provided in an embodiment of the present application;

[0082] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0084] First, the application scenarios to which this application is applicable are introduced. This application is applied to the field of robots. Specifically, delivery robots are intelligent devices that replace manual delivery services. While bringing customers a novel experience, they can also reduce manual labor intensity and improve work efficiency. They have been increasingly used in canteens, restaurants, hotels and other places.

[0085] For example, see Figure 1 , Figure 1 This is a schematic diagram of the structure of a delivery robot provided in an embodiment of the present application. Figure 1 As shown, the delivery robot includes: a shell 20 for carrying items, a mobile chassis 10, a function controller that provides user operations (not shown in the figure), an underlying controller for map generation and path planning (not shown in the figure), and an element controller that controls the mobile unit and the environment detection unit (not shown in the figure).

[0086] The shell 20 for carrying items includes a storage rack, which is fixed on the mobile chassis 10 of the delivery robot, and the storage rack has multiple storage layers 201, and each storage layer 201 can be used to place items to be delivered. By providing a storage rack with multiple storage layers 201, the delivery robot can have the ability to store multiple items, so that the delivery robot can deliver multiple items in one operation, thereby improving the delivery efficiency of the delivery robot.

[0087] The mobile chassis 10 is provided with at least two sets of driving wheels 120, each set of driving wheels 120 is respectively located on one side of the mobile chassis 10; the component controller controls the travel speed of the driving wheels 120. At least one turn signal unit is provided at the bottom of the mobile chassis 10, and each turn signal unit includes at least one turn signal 111; the mobile unit is provided with at least two sets of driving wheels 120, each set of driving wheels 120 is respectively located on one side of the chassis 10; the component controller controls the travel speed of the driving wheels 120; and controls the turn signal 111 in the turn signal unit to light up in a preset manner when the delivery robot turns.

[0088] Specifically, among the driving wheels 120 provided in the mobile unit, at least one group of driving wheels 120 is used as the left driving wheel, and at the same time, at least one group of driving wheels 120 is used as the right driving wheel, and the left driving wheel and the right driving wheel are located on opposite sides of the chassis 10. Optionally, the mobile unit may further include at least two groups of driven wheels, one group of driving wheels corresponding to one group of driven wheels, wherein at least one group of driven wheels is used as the left driven wheel, and at the same time, at least one group of driven wheels is used as the right driven wheel, and the left driven wheel and the right driven wheel are used to assist the left driving wheel and the right driving wheel in driving the housing 20 and the chassis 10 of the delivery robot to move, thereby reducing the load pressure of the driving wheel 120.

[0089] The delivery robot provided in the embodiment of the present application has a component controller controlling the turn signal lights to light up when the delivery robot turns, so as to alert pedestrians.

[0090] On the basis of the above technical solution, optionally, when the speed difference of the driving wheels 120 on both sides of the chassis 10 is greater than a preset value, the component controller controls the turn signal 111 in the turn signal unit to light up in a preset manner. Optionally, the delivery robot further includes a voice module, which is electrically connected to the component controller; when the delivery robot turns, the component controller controls the voice module to issue a voice prompt message.

[0091] Furthermore, the delivery robot also includes a laser radar system, which can be set in the equipment of the delivery robot. The laser radar system can rotate along a set plane so that the photoelectric receiving array of the laser radar system forms a scanning cylinder. The laser radar system can also be set at the slit of the robot shell, so that it is easy to send out laser signals to detect surrounding objects. The above-mentioned laser radar system includes a photoelectric receiving array and a laser emitting unit array, so that when the laser radar system rotates along the set plane, the photoelectric receiving array can form a scanning cylinder, thereby increasing the scanning area, facilitating the acquisition of the details of the object shape, and avoiding the robot equipment from colliding with obstacles. If the laser radar system only includes a single photoelectric receiving unit and a single laser emitting unit, the laser radar system can only measure the object shape of a circle after rotating along the set plane, and cannot obtain the shape of complex objects in time, which is easy to cause collisions and endanger personal and property safety. Optionally, the above-mentioned set plane can be a horizontal plane, which is convenient for the robot equipment to detect objects during the movement. In addition, other set planes, such as vertical planes, can be selected according to user needs, and this embodiment does not limit this.

[0092] In one embodiment, the delivery robot performs the following steps during the delivery process:

[0093] Step 101: The delivery robot moves to a target delivery area.

[0094] Among them, the delivery robot refers to a robot that can perform delivery tasks and deliver items to users, such as room delivery services in hotel scenarios and meal delivery services in restaurant scenarios. A delivery task can be a task that provides users with services for delivering goods. Delivery scenarios include communities, warehouses, airports, hotels, restaurants, etc. The delivery area refers to a pre-designated area in the delivery scenario. The delivery robot can move to the delivery area and notify the user and wait for the user to pick up the item. Exemplarily, the delivery area can be a specific location in the delivery scenario, such as a building in a community or the door of a room in a hotel, or next to a table in a restaurant. The target delivery area is the specific address that the target delivery task requires delivery to. For example, if the target delivery task is to provide express delivery service to Room B in Area A, the robot can move to the target delivery area, that is, the door of Room B in Area A, and call the landline phone in the room to notify the user to pick up the item at the door; for another example, if the target delivery task is to provide meal delivery service to Gate D of Hotel C, the robot can move to the target delivery area, that is, Gate D of Hotel C, and call the phone inside the door to notify the user to pick up the meal at the door; or if the target delivery task is to provide meal delivery service to Table F in Restaurant E, the robot can move to the target delivery area, that is, Table F in Restaurant E, and control the ringing of Table F to notify the user to pick up the meal.

[0095] In a specific example, the distribution scenario is a hotel, and the distribution robot can be a hotel distribution robot. Each distribution robot has an identification information, for example, ID (Identity document, identity identification number), which is used to identify the identity of the distribution robot. The distribution area of ​​the distribution robot of the hotel includes the room door area inside the hotel. After checking in to the hotel, the user can use the hotel's ordering system to order food or daily necessities, wherein the ordering system can be a telephone order or a mobile phone APP (Application) service system. For example, when ordering food, the user can reserve food and beverage in the ordering system and enter the room number of the user. The ordering system sends the reserved food and beverage information entered by the user to the platform system of the hotel. The platform system can generate a target delivery task and send it to the distribution robot in the hotel with the room number of the user staying and the food and beverage information reserved by the user. After the robot obtains the user's reserved food and beverage from the hotel staff, it moves to the target delivery area, and the target delivery area can be the area in front of the room where the user stays.

[0096] In another specific example, the delivery scenario is a restaurant, and the delivery robot can be a restaurant delivery robot. The delivery area of ​​the restaurant's delivery robot includes the dining location inside the restaurant, such as the dining table area where the user is located. After the user selects the dining table, he can use the ordering system corresponding to the dining table to order, such as scanning the QR code on the dining table to place an order. When ordering, the user can manually enter the table number of the table or automatically enter the table number of the table. The ordering system sends the reserved dining information entered by the user to the restaurant's platform system. The platform system can generate a target delivery task based on the user's table number and the user's reserved dining information and send it to the delivery robot in the restaurant. After the robot obtains the user's reserved dining from the restaurant staff, it moves to the target delivery area, which can be the dining table area where the user is located. Here, the autonomous delivery of food by the delivery robot greatly reduces the labor cost and improves the service quality.

[0097] Step 102: The robot triggers key generation, and the key is used to confirm the pickup, such as a pickup code.

[0098] Step 103: The robot prompts the user corresponding to the target delivery area to pick up the item through the communication connection.

[0099] The robot can transmit voice information to the user through the communication connection, prompting the user to move to the target delivery area to pick up the item. The user obtains the robot's pick-up prompt information. The robot can inform the user of the delivered item information and the location of the target delivery area in the form of voice. After the user confirms that the item delivered by the robot is the item he or she has reserved, he or she arrives at the location of the target delivery area to obtain the item delivered by the robot.

[0100] For example, when the robot arrives at the dining location of the user, it can call the ringing phone on the dining table to remind the user to pick up the food. After the user confirms that the food delivered by the robot is the food he ordered, he can take the food delivered by the robot.

[0101] Furthermore, when using a delivery robot to deliver items, you need to first place the items to be delivered on the storage layer, and then select the delivery location corresponding to the storage layer. Here, each storage layer needs to select its corresponding delivery location. After selecting the delivery location corresponding to each storage layer, click the "Go Now" button on the delivery robot, and the delivery robot can directly enter the delivery page and perform the delivery task.

[0102] However, research has found that during the delivery process, if a complex and dynamic indoor environment is encountered, the delivery robot needs to share road resources with other robots and pedestrians in a limited space to ensure that the task is completed efficiently and safely. However, as the number of robots increases and the complexity of the scene increases, the problem of encounters and passing between robots becomes particularly prominent. If multiple robots cannot meet in a timely and smooth manner when they meet on a narrow road, it may cause road congestion, delay delivery time, and even affect pedestrian safety.

[0103] In order to solve these problems, the prior art has proposed some solutions. One is to draw a virtual wall in the middle of the road on the map to divide the road into different movement areas, so as to avoid robots meeting on the same road. However, this method requires complex map planning when the system is deployed, which increases the difficulty and time cost of deployment. The second is to set avoidance points beside the road during the deployment stage. When two robots meet, the system decides to let one robot go to the avoidance point and continue the original task after the other robot passes. However, this method not only complicates the overall operation of the robot system, but also reduces the efficiency of multiple robots working in parallel. The third is to control the two robots to move along the slow-moving path when determining the meeting, but this solution does not take into account the current position of the robot, and mechanically generates the central axis according to the static map. The meeting route determined by the penalty value of the central axis may require the robot to repeatedly deviate, resulting in unstable robot movement and low meeting efficiency.

[0104] Based on this, the embodiments of the present application provide a robot control method, device and storage medium, which effectively solve the problems of low efficiency of meeting vehicles on narrow roads, unstable path planning, and difficult meeting vehicle planning, and realize the robot's efficient meeting of vehicles in a complex dynamic environment.

[0105] See also Figure 2 , Figure 2 This is a flow chart of a robot control method provided by an embodiment of the present application. Figure 2As shown in , the control method provided by the embodiment of the present application includes:

[0106] S201. For any target robot in a meeting state, determine a meeting reference route for the target robot according to the current position of the target robot and an initially planned route.

[0107] S202: Perform path planning processing in a temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route.

[0108] S203: Evaluate each candidate meeting route according to a predetermined evaluation index, and select the optimal meeting route that meets the meeting requirements.

[0109] S204: Control the target robot to travel along the optimal meeting route.

[0110] A control method for a robot provided in the present application, first, for a target robot in a meeting state, first determine a reference route for meeting the vehicle according to its current position and the initial planned route. Among them, the initial planned route can be generated by the robot according to the current position and the target position (such as the delivery target position) based on the static map. Then, the meeting route is determined according to the initial planned route, so that the meeting route is no longer fixed, but is associated with the current position of the robot, and can more flexibly respond to the real-time position information of the robot. If the current position of the robot is not considered, the meeting reference route generated according to the static map is often a strict center line of the road. When the width of the road in the environment where the robot is running changes, the center line of the road will suddenly shift laterally, and the optimal meeting route finally obtained also has this problem. Therefore, this solution reduces the planning route that does not consider the current position of the robot, which may cause the meeting reference route to be far away from the robot, so that the robot needs a large offset and repeated adjustment, thereby improving the stability and efficiency of the meeting.

[0111] Then, a temporary meeting channel is formed between the meeting reference route and the target boundary (the target boundary is the original boundary determined according to the preset offset direction), and path planning is performed in the channel to generate at least one candidate meeting route. For example, when meeting on the right, the temporary meeting channel is between the meeting reference route and the right boundary of the channel. By generating a temporary meeting channel, flexibility is increased, so that the robot can better adapt to the meeting scene in a dynamic environment, reduce the complexity of the deployment process, and effectively avoid collision and blocking problems in narrow roads or highly dynamic environments. Then, the generated candidate meeting routes are evaluated according to the predetermined evaluation indicators, and the optimal route that best meets the meeting requirements is selected. Through the evaluation and screening of multiple routes, the route that best suits the current scenario can be selected to ensure that the robot is both efficient and safe when meeting. This avoids the limitations that may be caused by a single route and improves the intelligence and flexibility of the overall operation. Finally, the target robot is controlled to move along the selected optimal meeting route to complete the meeting operation. Finally, the robot can meet based on the optimal route, reducing the blocking and waiting time on narrow roads and improving the overall task efficiency. Moreover, since the route is dynamically generated and screened and optimized, the smoothness and safety of the robot's driving are also guaranteed.

[0112] With respect to step S201, the determination of the meeting state may be determined according to at least one of the relative distance between the robots, the relative movement direction, and the expected meeting area.

[0113] For example, the position information of each robot in the multiple robots in the same working area is identified in real time. When it is determined that the distance between two robots in the same channel is d meters, the scheduling module determines that the two machines will conflict, and sends a meeting message to the navigation module to notify the navigation module that the two robots are starting to meet (that is, it is determined that the two robots are in a meeting state). The navigation module and the scheduling module can be set in the robot or in the background server. When the navigation module and the scheduling module are set in the robot, the scheduling module of the current robot and the scheduling modules of other robots can establish a connection through short-distance communication. When the distance between the current robot and other robots is less than or equal to the set threshold d, it can be triggered to enter the meeting state.

[0114] Here, d can be a dynamic value, and different distance values ​​can be used according to the different scenes of the meeting area and the sizes of the models of the vehicles. In this way, the meeting distance value that changes dynamically according to the scenes and machine sizes has better applicability and a better sports experience.

[0115] When multiple robots are in channels of different widths, the meeting distance can be set larger than the meeting distance when multiple robots are in channels of the same width. For example, when two robots are in a channel with a width of 3m, the meeting distance d can be set to 6m; when one robot is in a narrow channel, such as 2m, and the other is in a channel with a width of 3m, the meeting distance d can be set to 8m. In this way, in this scenario, entering the meeting mode earlier can control the speed of the robot, so that the machine in the wide channel can slow down in advance and wait for the machine in the narrow channel to leave the narrow channel, so that the two machines can meet in the wide channel. Otherwise, it may not be possible to meet, because the two machines in the narrow channel may not be able to move at the same time, and it is more dangerous.

[0116] Among them, when the models are different, especially the sizes of the machines are different, the longer the size of the machine, the longer the meeting distance can be set, so as to facilitate the adjustment of its own position in advance and complete the meeting more smoothly. That is, the meeting distance of each robot can be different.

[0117] In step S201, the initial planned route can be a route to the target point planned using a global path planning algorithm based on the current task, starting from the current position of the target robot, without considering dynamic obstacles, and only considering static map information. The global path planning algorithm used in the delivery task considers dynamic obstacles and is planned periodically. The initial planned route can be generated and saved once at the beginning of the task, and then obtained after receiving the meeting message.

[0118] The initial planned route may or may not be the center line of the road, and may be determined specifically according to the current position of the target robot. In addition, the initial planned routes of the two target robots in the meeting state may be the same or different.

[0119] For examples, see Figure 3 , Figure 3 A schematic diagram of the initial planned route provided for this application. Figure 3 As shown, when the starting position of the target robot is at A, the initial planned route may be L1, and if the starting position of the target robot is at B, the initial planned route may be L2. That is, the initial planned route may change according to the current position of the robot, and may be equal to or close to the center line of the current position or the next driving section. Exemplarily, the distance of the initial planned route from the center line of the driving section at the current position or the center line of the next driving section is less than or equal to a first set value, and the distance from the side boundary is greater than or equal to a second set value, and the initial planned route is a straight line or an approximate straight line, that is, there is no corner with a curvature greater than a set threshold.

[0120] Continuing with step S201, determining the meeting reference route of the target robot according to the current position of the target robot and the initial planned route may include: according to the current position of the target robot, intercepting a section of the route from the initial planned route as the meeting reference route of the target robot.

[0121] In one embodiment provided in the present application, determining a reference route for meeting a target robot according to a current position of the target robot and an initial planned route includes:

[0122] S2011. Determine the target path point on the initial planned route that is closest to the current position of the target robot.

[0123] S2012: Setting a first length of the required interception route according to at least one of the scene of the meeting area, the driving speed of at least one target robot, and the device size of at least one target robot.

[0124] S2013: Taking the target path point as a starting point, and along the current driving direction of the target robot, intercepting a route of a first length from the initial planned route as a meeting reference route for the target robot.

[0125] For step S2011, the current position of the target robot is not necessarily located on the initial planning route. Exemplarily, when the current position of the target robot is located on the initial planning route, the current position of the target robot is determined as the target path point; when the current position of the target robot is not located on the initial planning route, a vertical line is drawn from the current position to the initial planning route, and the intersection is determined as the target path point. Exemplarily, when multiple path points are set on the initial planning route, the path point closest to the robot is selected as the target path point.

[0126] For step S2012, the first length is a dynamic value. For example, if the robot needs to meet other vehicles in a narrow area and the speed is slow, the first length can be set to 3 meters; but in a wider area or when the robot is fast, the first length can be set to 10 meters.

[0127] For step S2013, for example, assuming that the initial planned route consists of multiple path points, assuming that the determined target path point is the 9th path point, and the planned interception length (first length) is 5 meters, then starting from the 9th path point, a route that matches the length is intercepted forward along the initial planned route as a reference route for meeting the other vehicle.

[0128] In this way, the nearest target path point is determined according to the current position of the target robot, which can accurately match the current driving state, avoid deviation from the actual position, and ensure that the intercepted reference route for meeting vehicles is more accurate and in line with the actual driving situation. In the process of path interception, by comprehensively considering factors such as the meeting area scene, the robot's driving speed and the size of the equipment, the length of the intercepted route is flexibly adjusted, so that the meeting path can adapt to different scene requirements and is suitable for narrow, wide or complex meeting environments, thereby improving the versatility and adaptability of the solution. In addition, since the determined meeting reference route is only a part of the initial planned route, the computational complexity can be reduced and the efficiency of path planning can be improved. Therefore, through precise positioning, flexible adjustment, and adaptive meeting scenes, the safety, efficiency and fluency of the robot when meeting vehicles in complex environments can be effectively improved.

[0129] With respect to step S202, the target boundary is an original boundary corresponding to the preset offset direction side.

[0130] For example, if the preset offset direction is rightward, the target boundary is the right original boundary; if the preset offset direction is leftward, the target boundary is the left original boundary. The original boundary may be a wall, an obstacle, a virtual wall or other boundary lines.

[0131] In this step, the candidate route is a feasible path for the robot in the current meeting scene. The temporary meeting channel is generally a part of the overall channel. For example, the overall lane is a 6-meter-wide lane, and the temporary meeting channel of the target robot is a 3-meter lane on the right.

[0132] In an implementation manner provided in the present application, performing path planning processing in a temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route includes:

[0133] S2021: Determine a point on the meeting reference route that is a second distance from a starting point of the meeting reference route as a preceding reference point.

[0134] S2022: Starting from the preceding reference point, sampling is performed at intervals of a third length on the meeting reference route until the designated end point of the meeting reference route is reached, and at least one longitudinal sampling point is determined.

[0135] S2023. For each longitudinal sampling point, perform transverse sampling with the fourth length as the sampling step length and the corresponding target offset distance as the full length, and determine at least one transverse sampling point that is on the same straight line as the longitudinal sampling point.

[0136] S2024. According to the current position of the target robot, the front reference point, all longitudinal sampling points, and all transverse sampling points, each column of longitudinal arrangement points is fitted to determine at least one candidate meeting route.

[0137] With respect to step S2021, the second length is determined according to the current speed and offset distance of the target robot.

[0138] The front reference point is a point on the oncoming reference route that is a certain distance from the starting point of the oncoming reference route. By setting the front reference point, a reference can be provided for subsequent sampling, and the curvature of the route can be ensured to be as smooth as possible, so that the robot can switch to the oncoming route more smoothly.

[0139] Here, in an implementation manner provided in the present application, the leading distance is determined by the following formula:

[0140] d4=k*V+m

[0141] Where d4 is the lead distance, k is the proportional coefficient, V is the current speed of the robot, and m is the base number. The values ​​of k and m are related to the current speed of the robot and the offset distance d5. The greater the current speed of the robot or the greater d5, the greater k and m. It should be noted that different values ​​of k and m will affect the lead distance, and thus affect the smoothness of the robot's movement when meeting other vehicles.

[0142] In this way, the leading reference point can be determined based on the leading distance.

[0143] For example, if the target robot is currently moving faster and needs a larger offset distance, a position farther from the starting point (e.g., 1 meter) can be selected as the front reference point. If the robot is slower or the offset is smaller, the front reference point may be located near the starting point (e.g., 0.5 meters).

[0144] In step S2021, the target offset distance is the distance offset from the meeting reference route to the preset offset direction, and the offset distances at different width positions in the temporary meeting channel are not necessarily the same.

[0145] Continuing with step S2021, in one implementation provided in the present application, the target offset distance is determined by the following steps:

[0146] S301. Determine the channel width at any position in the temporary channel according to the meeting reference route and the preset obstacle boundary.

[0147] S302: For any position in the temporary channel, determine a candidate offset distance at the position according to the channel width at the position and a preset length setting strategy.

[0148] S303: If the candidate offset distance does not exceed a preset threshold length, determine the candidate offset distance as the target offset distance at the position; if it exceeds the preset threshold length, determine the preset threshold length as the target offset distance at the position.

[0149] For step S301, the channel width is the width of the available space between any point in the channel and two boundaries (the oncoming reference route and the preset obstacle boundary).

[0150] When determining the channel width, it can be determined by referring to known map data or based on other data.

[0151] With respect to step S302, the preset length setting strategy may be adjusted according to multiple factors such as channel width, robot size, driving speed, etc., so as to calculate an offset distance suitable for the current environment.

[0152] For example, if the width of the passage at a certain location is 2 meters, and the robot needs to reserve 0.5 meters of avoidance space according to the set strategy, then the candidate offset distance may be 0.5 meters. At locations where the passage is wider, the candidate offset distance may be larger, such as 1 meter.

[0153] For step S303, in this step, for each candidate offset distance, it is compared with the preset threshold length corresponding to the position. If the candidate offset distance is less than or equal to the threshold, the candidate offset distance is determined as the final target offset distance. If the candidate offset distance exceeds the threshold, the threshold length is set as the target offset distance.

[0154] For example, assuming that the preset threshold length at a certain position is 1 meter, if the candidate offset distance at a certain position is 0.5 meters, 0.5 meters will be used as the target offset distance; but if the candidate offset distance is 1.5 meters, 1 meter will be used as the target offset distance.

[0155] In this way, according to the channel width at different positions and the preset length setting strategy, the offset distance is dynamically adjusted to adapt to changes in complex environments. And by comparing the candidate offset distance with the preset threshold, the offset can be effectively controlled to avoid excessive offset or insufficient avoidance of the robot, so that the robot's movement behavior is relatively stable, ensuring driving safety and obtaining a better user experience.

[0156] With respect to step S2022, the third length is determined according to the length from the preceding reference point to the designated end point on the meeting reference route and a preset number of longitudinal samplings.

[0157] The length from the front reference point to the designated end point on the oncoming reference route is called the pull-over route length, which is determined based on factors such as the current speed of the target robot and the oncoming road conditions. The pull-over route lengths in different scenarios are not necessarily the same, so the designated end point on the oncoming reference route is a dynamic change point.

[0158] Therefore, the third length is determined according to the length of the side route and the preset longitudinal sampling quantity.

[0159] For example, assuming that the length of the side route is 10 meters, the system presets 5 sampling points, and the interval between each sampling point is 2 meters (that is, the third length is 2 meters). The system will collect a longitudinal sampling point every 2 meters within this 10-meter range until the specified end point.

[0160] For step S2023, the fourth length is determined according to the target offset distance at the longitudinal sampling point position and the preset transverse sampling number. In this way, by setting the transverse sampling points, it is ensured that there are also enough sampling points in the transverse direction (i.e., the direction perpendicular to the oncoming reference route), so as to generate a more refined route.

[0161] For example, for each longitudinal sampling point, assuming that the target offset distance at that position is 1.5 meters, and the preset number of horizontal sampling is 3, the fourth length is 0.5 meters, and the preset offset direction is the right side, then a point is sampled every 0.5 meters on the right side of the longitudinal sampling point, and 3 horizontal sampling points are obtained, forming a horizontal sampling distribution.

[0162] The preset number of lateral sampling is related to the number of pull-over routes expected to be generated. When the offset distance is constant, the smaller the fourth length d2 is, the more pull-over routes are generated, the more pull-over routes can be selected, and the higher the success rate of meeting the vehicle.

[0163] With respect to step S2024, the fitting process may be performed using a spline function. For example, a spline function is used to fit each column of sampling points arranged in the longitudinal direction, thereby generating a plurality of smooth candidate meeting routes.

[0164] In this way, the front reference point is determined according to the current speed of the robot and the target offset distance, which can flexibly adapt to the robot's needs for meeting vehicles at different speeds. By setting the front reference point, the curvature of the route can be ensured to be as smooth as possible, and the robot can switch to the side route for meeting vehicles more smoothly. The third length is set according to the side route length and the preset longitudinal sampling number to determine the longitudinal sampling point, and reasonable longitudinal sampling points are dynamically generated, ensuring that sufficient sampling points can be generated on a shorter road section, thereby ensuring the accuracy of path planning. For each longitudinal sampling point, transverse sampling is performed, and through the fourth length (sampling step) and the preset transverse sampling number, it can be adjusted according to actual needs to generate transverse sampling points suitable for the current scene. In this way, through transverse sampling, it can dynamically adapt to different obstacles or boundary conditions, generate multiple potential meeting routes (candidate meeting routes), provide more options, and avoid spatial conflicts when meeting. Finally, fitting is performed to generate at least one smooth candidate meeting route. This fitting method ensures the continuity and smoothness of the path, and avoids problems such as sudden direction changes or curve incoherence.

[0165] For examples, see Figure 4 , Figure 4 A schematic diagram of a candidate route provided for this application. Figure 4 As shown, robot 1 and robot 2 are in a meeting state, d is the meeting distance set when determining the meeting state, d1 is the third length, d2 is the fourth length, d3 is the length of the side route, d4 is the front distance, and d5 is the offset distance. Points other than the front sampling point are longitudinal sampling points and transverse sampling points. In this way, for robot 1, fitting processing is performed based on the current position of the robot, the front reference point, all longitudinal sampling points, and all transverse sampling points to generate a total of 4 candidate meeting routes, namely F1, F2, F3, and F4.

[0166] With respect to step S203, in this step, each candidate meeting route is evaluated according to a predetermined evaluation index to determine an evaluation value of each candidate meeting route; then, according to the evaluation value of each candidate meeting route, an optimal meeting route that meets the meeting requirements is screened out according to a preset screening rule.

[0167] In an implementation manner provided in the present application, the step of evaluating each candidate meeting route according to a predetermined evaluation index and selecting the optimal meeting route that meets the meeting requirements includes:

[0168] S2031. For each candidate meeting route, determine an index evaluation value of the candidate meeting route under each predetermined evaluation index.

[0169] S2032: Perform weighted processing on all index evaluation values ​​corresponding to the candidate meeting route to determine a route evaluation value of the candidate meeting route.

[0170] S2033, identifying whether the candidate meeting route with the highest route evaluation value and the candidate meeting route with the highest route evaluation value of another target robot corresponding to the meeting state meet the meeting route interval requirement.

[0171] S2034: If satisfied, determine the candidate meeting route with the highest route evaluation value as the optimal meeting route for the target robot.

[0172] For step S2031, illustratively, the predetermined evaluation index includes at least one of the following: curvature, distance from a reference oncoming route, and distance from a preset obstacle boundary.

[0173] In this way, by setting multiple different evaluation indicators, a multi-dimensional evaluation can be performed, so that a more comprehensive and reasonable route selection can be made, avoiding the deviation caused by a single indicator, improving decision-making accuracy and enhancing robustness.

[0174] In this step, for each candidate meeting route, an index evaluation value of the candidate meeting route under each predetermined evaluation index is determined, including: for each candidate meeting route, a curvature index evaluation value of the candidate meeting route, a curvature index evaluation value of the distance from the meeting reference route, and a curvature index evaluation value of the distance from the preset obstacle boundary are determined.

[0175] For step S2032, different evaluation indicators may be set with different weight values, and the weight values ​​of the same evaluation indicator in different scenarios may also be different.

[0176] Exemplarily, the optimal side route is selected according to the following evaluation function:

[0177] f(x)=α*f(dist)+β*f(safe)+γ*f(curture)

[0178] Among them: f(dist) represents the Euclidean distance from a point on the candidate meeting route to the meeting reference route. The larger the Euclidean distance is set, the larger f(dist) is, which means that the side route far from the meeting reference center line is preferred; f(safe) represents whether the candidate meeting route is safe, that is, the cost value of each point on the candidate side route in the cost map. The larger the sum of the cost values ​​is set, the smaller f(safe) is, which means that the safe side route is preferred. f(curture) represents the curvature of each candidate side route. The smaller the curvature is set, the larger f(curture) is, which means that the side route with small curvature is preferred. Then, by adjusting the weight coefficient, the selected optimal meeting route meets the requirements of safe and collision-free passage, few corners and small curvature.

[0179] For example, the weight value of the curvature is set to 0.3, the weight value of the distance from the oncoming vehicle reference route is set to 0.6, and the weight value of the distance from the preset obstacle boundary is set to 0.2.

[0180] In this way, for each candidate meeting route, all the indicator evaluation values ​​corresponding to the candidate meeting route and the weight value of each evaluation indicator are known, and the route evaluation value of the candidate meeting route can be determined.

[0181] For step S2033, for example, assuming that robot 1 and robot 2 need to meet each other, if the highest evaluation value of the candidate meeting route selected by robot 1 is 8.0, and the highest evaluation value of the candidate meeting route selected by robot 2 is 7.8, their relative positions and distances are evaluated to determine whether the two routes meet the interval requirements. For example, determine whether the minimum distance between the two routes is greater than a set safety threshold (such as 1 meter).

[0182] For step S2034, continuing with the above example, assuming that the route of robot 1 meets the interval requirement, the system will determine the candidate meeting route with the highest evaluation value as the optimal meeting route for robot 1, and the same applies to robot 2.

[0183] In addition, if it is not satisfied, the navigation module will notify the scheduling module that there is a collision risk and the robot cannot meet the other vehicle. And by adjusting the coefficient of the evaluation function, the robot can maintain a corresponding distance when meeting the other vehicle and avoid collision.

[0184] In this way, through the comprehensive consideration of multiple evaluation indicators, the rationality and accuracy of route selection are guaranteed. And through the interval inspection of the meeting route, it can effectively avoid the routes of the two robots being too close, reduce mutual interference during the meeting process, and improve the overall safety of the meeting. Therefore, through this candidate meeting route evaluation and screening technology, the robot can perform more efficient and safe meeting path planning in a complex and changeable environment, meeting the needs of multi-robot collaborative work scenarios.

[0185] Regarding step S204, in this step, the target robot is controlled to move forward along the selected optimal meeting route to complete the meeting operation.

[0186] In one embodiment provided in the present application, controlling the target robot to travel along the optimal meeting route includes:

[0187] S2041. Real-time identification of the position of the target robot traveling along the optimal meeting route.

[0188] S2042: Update the optimal meeting route according to the identified real-time position and the meeting reference route.

[0189] S2043, and controlling the target robot to travel along the updated optimal meeting route.

[0190] With respect to step S2041, in this step, when the robot is driving along the optimal meeting route, the current position of the robot is continuously monitored and identified, for example, by using laser radar, vslam or other positioning technologies to ensure that the robot is accurately positioned during driving.

[0191] For example, when the robot 1 starts to travel along the optimal meeting route, its current position is obtained at regular intervals (eg, every second).

[0192] With respect to step S2042, when the optimal meeting route driving is updated according to the identified real-time position and the meeting reference route, the updating process may be repeatedly executed according to steps S201-S203.

[0193] For step S2043, when controlling the target robot to drive along the updated optimal oncoming route, the navigation module can control the machine to move along the selected oncoming route according to the local path planning algorithm. The selectable local path planning algorithms include dynamic window method (DWA), time elastic band algorithm (TEB), model predictive control algorithm (MPC), pure tracking algorithm, etc. The final output is the speed and angular velocity control amount of the robot moving along the oncoming route.

[0194] In this way, by monitoring the real-time position of the robot and continuously updating the route according to the oncoming reference route, dynamic adjustment of the driving path can be achieved, thereby improving the stability and safety of the oncoming process, enhancing the flexibility and accuracy of path planning, improving the oncoming efficiency and reducing the oncoming risk.

[0195] For examples, see Figure 5 , Figure 5 A schematic diagram of a meeting along the optimal meeting route provided by this application. Figure 5 As shown, the optimal meeting route for robot 1 is candidate meeting route F4, and the optimal meeting route for robot 2 is candidate meeting route B4. Thus, robot 1 is controlled to travel along F4, and robot 2 is controlled to travel along B4, and the F4 and B4 routes are corrected and updated in real time.

[0196] In addition, in another embodiment provided by the present application, after controlling the target robot to travel along the optimal meeting route, the control method further includes:

[0197] S401. Perform real-time identification of the positions of two target robots traveling along the optimal meeting route to determine whether the two target robots pass through the same area.

[0198] S402: If yes, send a meeting end instruction and control the robot to drive along the initial planned route.

[0199] In step S401, the two target robots traveling along the optimal meeting route are tracked in real time to ensure that their current position information is known. According to the identified current position information, it is determined whether the two robots have passed through the same area, such as near the same path point, that is, whether they have completed the meeting process.

[0200] For example, when the same path point on the map, or two adjacent points between the meeting routes of two robots, both belong to the area that the two robots have already traveled through, it can be confirmed that the meeting is completed.

[0201] With respect to step S402, when robots 1 and 2 pass through the meeting area, an end instruction is sent to them to inform them to end the meeting state. Next, the robots are controlled to return to their original global planning routes and continue to complete their scheduled tasks (e.g., continue the delivery task).

[0202] In this way, by identifying the positions of the two target robots in real time, it is possible to ensure that they successfully pass through the meeting area, and send the end command in time after the meeting, avoiding the possibility of the two robots continuing to interfere with each other in narrow passages or complex environments. As a result, the robots can be guided to leave the meeting area in time, quickly return to the initial planned route, resume normal driving status, and perform tasks normally. This greatly improves the safety, efficiency, and adaptability of the multi-robot meeting process.

[0203] For examples, see Figure 6 , Figure 6 A schematic diagram of movement after the vehicle meeting is provided in this application, such as Figure 6 As shown, after determining that the meeting is over, the two robots drive along their respective corresponding global planning routes to perform the original delivery task.

[0204] Based on the same inventive concept, a control device corresponding to the control method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned control method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0205] See also Figure 7 , Figure 7 This is a schematic diagram of the structure of a robot control device provided in an embodiment of the present application. Figure 7 As shown in , the control device 700 includes:

[0206] A first determination module 710 is used to determine, for any target robot in a meeting state, a meeting reference route of the target robot according to the current position of the target robot and the initial planned route;

[0207] A generating module 720 is used to perform path planning processing in a temporary meeting channel formed by the meeting reference route and a target boundary to generate at least one candidate meeting route; wherein the target boundary is an original boundary corresponding to a preset offset direction side;

[0208] A screening module 730 is used to evaluate each candidate meeting route according to a predetermined evaluation index, and screen out the optimal meeting route that meets the meeting requirements;

[0209] The control module 740 is used to control the target robot to travel along the optimal meeting route.

[0210] Optionally, when the first determining module 710 is used to determine the meeting reference route of the target robot according to the current position of the target robot and the initial planned route, the first determining module 710 is used to:

[0211] Determine a target path point on the initial planned route that is closest to the current position of the target robot;

[0212] According to at least one of the scene of the meeting area, the driving speed of at least one target robot, and the device size of at least one target robot, a first length of the required interception route is set;

[0213] Taking the target path point as a starting point, along the current driving direction of the target robot, a route of a first length is intercepted from the initial planned route as a meeting reference route for the target robot.

[0214] Optionally, when the generating module 720 is used to perform path planning processing in the temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route, the generating module 720 is used to:

[0215] Determine a point on the meeting reference route that is a second length away from the starting point of the meeting reference route as a leading reference point; wherein the second length is determined according to the current speed of the target robot and the target offset distance;

[0216] Sampling is performed at intervals of a third length on the meeting reference route starting from the preceding reference point until the designated end point on the meeting reference route ends, and at least one longitudinal sampling point is determined; wherein the third length is determined according to the length from the preceding reference point to the designated end point on the meeting reference route and a preset number of longitudinal samplings;

[0217] For each longitudinal sampling point, a fourth length is used as a sampling step length, and the corresponding target offset distance is used as a full length, and transverse sampling is performed to determine at least one transverse sampling point located on the same straight line as the longitudinal sampling point; wherein the fourth length is determined according to the target offset distance and a preset transverse sampling quantity;

[0218] According to the current position of the target robot, the front reference point, all longitudinal sampling points and all transverse sampling points, each column of longitudinal arrangement points is fitted respectively to determine at least one candidate meeting route.

[0219] Optionally, when the screening module 730 is used to evaluate each candidate meeting route according to a predetermined evaluation index and screen out an optimal meeting route that meets the meeting requirements, the screening module 730 is used to:

[0220] For each candidate meeting route, determining an index evaluation value of the candidate meeting route under each predetermined evaluation index;

[0221] Performing weighted processing on all index evaluation values ​​corresponding to the candidate meeting route to determine the route evaluation value of the candidate meeting route;

[0222] Identify whether the candidate meeting route with the highest route evaluation value and the candidate meeting route with the highest route evaluation value of another target robot corresponding to the meeting state meet the meeting route interval requirement;

[0223] If the conditions are met, the candidate meeting route with the highest route evaluation value is determined as the optimal meeting route for the target robot.

[0224] Optionally, the predetermined evaluation index includes at least one of the following: curvature, distance from a reference route for meeting other vehicles, and distance from a preset obstacle boundary.

[0225] Optionally, the control device 700 further includes a second determination module 750 (not shown in the figure), and the second determination module 750 is used to determine the target offset distance through the following steps:

[0226] Determine the width of the temporary passage at any position based on the reference route and the preset obstacle boundary;

[0227] For any position in the temporary channel, a candidate offset distance at the position is determined according to the channel width at the position and a preset length setting strategy;

[0228] If the candidate offset distance does not exceed the preset threshold length, the candidate offset distance is determined as the target offset distance at the position;

[0229] If exceeded, the preset threshold length is determined as the target offset distance at the position.

[0230] Optionally, when the control module 740 is used to control the target robot to travel along the optimal meeting route, the control module 740 is used to:

[0231] Real-time identification of the position of the target robot traveling along the optimal meeting route;

[0232] updating the optimal meeting route according to the identified real-time position and the meeting reference route;

[0233] And control the target robot to travel along the updated optimal meeting route.

[0234] Optionally, the control device 700 further includes an ending module 760 (not shown in the figure), and the ending module 760 is used to:

[0235] After controlling the target robot to travel along the optimal meeting route, real-time identification is performed on the positions of the two target robots traveling along the optimal meeting route to determine whether the two target robots pass through the same area;

[0236] If so, send a meeting end instruction and control the robot to drive along the initial planned route.

[0237] See also Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown in , the electronic device 800 includes a processor 810 , a memory 820 and a bus 830 .

[0238] The memory 820 stores machine-readable instructions executable by the processor 810. When the electronic device 800 is running, the processor 810 communicates with the memory 820 via the bus 830. When the machine-readable instructions are executed by the processor 810, the above-mentioned Figures 2 to 6 The specific implementation of the steps in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0239] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figures 2 to 6 The specific implementation of the steps in the method embodiment shown can be found in the method embodiment, and will not be repeated here.

[0240] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0241] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0242] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0243] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0244] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0245] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A robot control method, characterized in that: The control method comprises: For any target robot in the oncoming state, determine the oncoming reference route of the target robot according to the current position of the target robot and the initial planned route; Performing path planning processing in a temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route; wherein the target boundary is an original boundary corresponding to a preset offset direction side; Evaluate each candidate meeting route according to the predetermined evaluation index, and select the optimal meeting route that meets the meeting requirements; The target robot is controlled to travel along the optimal meeting route.

2. The control method according to claim 1, characterized in that: Determining a reference route for meeting a target robot according to the current position of the target robot and the initial planned route includes: Determine a target path point on the initial planned route that is closest to the current position of the target robot; According to at least one of the scene of the meeting area, the driving speed of at least one target robot, and the device size of at least one target robot, a first length of the required interception route is set; Taking the target path point as a starting point, along the current driving direction of the target robot, a route of a first length is intercepted from the initial planned route as a meeting reference route for the target robot.

3. The control method according to claim 1, characterized in that: The performing path planning processing in the temporary meeting channel formed by the meeting reference route and the target boundary to generate at least one candidate meeting route includes: Determine a point on the meeting reference route that is a second length away from the starting point of the meeting reference route as a leading reference point; wherein the second length is determined according to the current speed of the target robot and the target offset distance; Sampling is performed at intervals of a third length on the meeting reference route starting from the preceding reference point until the designated end point on the meeting reference route ends, and at least one longitudinal sampling point is determined; wherein the third length is determined according to the length from the preceding reference point to the designated end point on the meeting reference route and a preset number of longitudinal samplings; For each longitudinal sampling point, a fourth length is used as a sampling step length, and the corresponding target offset distance is used as a full length, and transverse sampling is performed to determine at least one transverse sampling point located on the same straight line as the longitudinal sampling point; wherein the fourth length is determined according to the target offset distance and a preset transverse sampling quantity; According to the current position of the target robot, the front reference point, all longitudinal sampling points and all transverse sampling points, each column of longitudinal arrangement points is fitted respectively to determine at least one candidate meeting route.

4. The control method according to claim 1, characterized in that: The step of evaluating each candidate meeting route according to a predetermined evaluation index and selecting the optimal meeting route that meets the meeting requirements includes: For each candidate meeting route, determining an index evaluation value of the candidate meeting route under each predetermined evaluation index; Performing weighted processing on all index evaluation values ​​corresponding to the candidate meeting route to determine the route evaluation value of the candidate meeting route; Identify whether the candidate meeting route with the highest route evaluation value and the candidate meeting route with the highest route evaluation value of another target robot corresponding to the meeting state meet the meeting route interval requirement; If the conditions are met, the candidate meeting route with the highest route evaluation value is determined as the optimal meeting route for the target robot.

5. The control method according to claim 1, characterized in that: The predetermined evaluation index includes at least one of the following: curvature, distance from a reference route for meeting other vehicles, and distance from a preset obstacle boundary.

6. The control method according to claim 3, characterized in that: Determine the target offset distance using the following steps: Determine the width of the temporary passage at any position based on the reference route and the preset obstacle boundary; For any position in the temporary channel, a candidate offset distance at the position is determined according to the channel width at the position and a preset length setting strategy; If the candidate offset distance does not exceed the preset threshold length, the candidate offset distance is determined as the target offset distance at the position; If exceeded, the preset threshold length is determined as the target offset distance at the position.

7. The control method according to claim 1, characterized in that: The controlling the target robot to travel along the optimal meeting route comprises: Real-time identification of the position of the target robot traveling along the optimal meeting route; updating the optimal meeting route according to the identified real-time position and the meeting reference route; And control the target robot to travel along the updated optimal meeting route.

8. The control method according to claim 1, characterized in that: After controlling the target robot to travel along the optimal meeting route, the control method further includes: The positions of the two target robots traveling along the optimal meeting route are identified in real time to determine whether the two target robots pass through the same area; If so, send a meeting end instruction and control the robot to drive along the initial planned route.

9. A robot control device, characterized in that: The control device comprises: A first determination module is used to determine, for any target robot in a meeting state, a meeting reference route of the target robot according to the current position of the target robot and an initial planned route; A generation module, used for performing path planning processing in a temporary meeting channel formed by the meeting reference route and a target boundary to generate at least one candidate meeting route; wherein the target boundary is an original boundary corresponding to a preset offset direction side; A screening module is used to evaluate each candidate meeting route according to a predetermined evaluation index and screen out the optimal meeting route that meets the meeting requirements; The control module is used to control the target robot to travel along the optimal meeting route.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the control method according to any one of claims 1 to 8 are executed.

Images