WO2019174005A1

WO2019174005A1 - Collision processing method, apparatus, robot and computer readable storage medium

Info

Publication number: WO2019174005A1
Application number: PCT/CN2018/079162
Authority: WO
Inventors: 骆磊
Original assignee: 深圳前海达闼云端智能科技有限公司
Priority date: 2018-03-15
Filing date: 2018-03-15
Publication date: 2019-09-19
Also published as: CN108778635A; CN108778635B

Abstract

A collision processing method, apparatus, robot, and computer readable storage medium. The collision processing method is applied to a robot which has at least one buffer device, comprising: determining motion information of an identified object (101), wherein the motion information at least comprises relative motion direction and absolute motion velocity; determining collision prediction information corresponding to the object according to the motion information of the object (102); and determining whether to control the robot to eject at least one buffer device according to the collision prediction information corresponding to the object (103). The described collision processing method may enable the robot to protect itself in advance when determining the possible danger of a collision by means of ejecting the buffer device, thus significantly reducing damage to the robot and surrounding objects caused by a collision accident.

Description

Collision processing method, device, robot and computer readable storage medium

Technical field

The present application relates to the field of robot technology, and in particular, to a collision processing method, apparatus, robot, and computer readable storage medium.

Background technique

With the rapid development of sensor technology and artificial intelligence algorithms, intelligent robots have also developed rapidly, and are gradually changing various traditional industries, so that human beings are gradually liberated from manufacturing and hard physical labor. For example, robots with sensation (including visual, tactile, etc.) can find and avoid obstacles by visual or tactile means, and in order to protect the internal components of the robot, due to various considerations such as technology and cost, the robot The body (outer casing) is mostly made of a hard material such as aluminum alloy, steel, PC (Polycarbonate) plastic.

technical problem

However, the inventors have found that at least the following problems exist in the prior art: although the use of a hard material to prepare the body of the robot can make the robot durable, if the robot is subjected to a collision or imbalance of higher strength, the robot body is easily exposed. Damage, this will undoubtedly increase maintenance costs. Also, when the robot falls, its hard shell can cause serious damage to people if it hits the people around it.

Technical solution

Some embodiments of the present application provide a collision processing method, apparatus, robot, and computer readable storage medium to solve the above technical problems.

An embodiment of the present application provides a collision processing method applied to a robot having at least one buffer device, comprising: determining motion information of the recognized object; wherein the motion information includes at least a relative motion direction and an absolute The motion speed is determined according to the motion information of the object, and the collision prediction information corresponding to the object is determined; and according to the collision prediction information corresponding to the object, it is determined whether the control robot pops up at least one buffer device.

An embodiment of the present application provides another collision processing method, the collision processing method being applied to a robot having at least one buffer device, comprising: acquiring state information of the robot; determining, according to state information of the robot, whether to control the robot to pop up at least one Buffer device.

An embodiment of the present application provides a collision processing apparatus applied to a robot having at least one buffering device, including: a motion information determining module, a collision prediction information determining module, and a buffering device pop-up determining module; a module, configured to determine motion information of the identified object; wherein the motion information includes at least a relative motion direction and an absolute motion speed; the collision prediction information determining module is configured to determine the object according to the motion information of the object acquired by the motion information acquiring module Corresponding collision prediction information; a buffering device pop-up judging module, configured to determine collision prediction information corresponding to the object determined by the module according to the collision prediction information, and determine whether to control the robot to eject at least one buffer device.

An embodiment of the present application provides another collision processing apparatus applied to a robot having at least one buffering apparatus, including: a state information acquiring module, a state judging module, and a control module; and a state information acquiring module, configured to: Obtaining state information of the robot; the state determining module is configured to determine, according to the state information, the state information of the robot acquired by the module, to determine whether the robot is in an unbalanced state; and the control module, configured to start protection when the state determining module determines that the robot is in an unbalanced state Mode, the control robot pops up at least one buffer device.

An embodiment of the present application provides a robot including at least one processor, a memory communicatively coupled to at least one processor; and at least one buffer device communicatively coupled to the at least one processor; wherein the memory is stored The instructions are executable by at least one processor, the instructions being executed by at least one processor to enable the at least one processor to perform the collision processing method involved in any of the method embodiments of the present application.

One embodiment of the present application provides a computer readable storage medium storing computer instructions for causing a computer to perform the collision processing method involved in any of the method embodiments of the present application.

Beneficial effect

According to the prior art, the robot determines the collision prediction information corresponding to the object according to the motion information of the acquired object, and determines whether to control the robot to pop out at least one buffer device according to the collision prediction information corresponding to the determined object. Or, the robot judges whether to control the robot to eject at least one buffer device according to its own state information, thereby enabling the robot to pop up at least one buffer device to protect itself before determining that a collision risk may occur, thereby greatly reducing the collision accident causing the robot and surrounding objects. s damage.

DRAWINGS

The one or more embodiments are exemplified by the accompanying drawings in the accompanying drawings, and FIG. The figures in the drawings do not constitute a scale limitation unless otherwise stated.

1 is a flowchart of a collision processing method in a first embodiment of the present application;

2 is a schematic diagram of a robot that pops up two buffer devices in the first embodiment of the present application;

3 is a flow chart of a collision processing method in a second embodiment of the present application;

4 is a flowchart of a collision processing method in a third embodiment of the present application;

FIG. 5 is a flowchart of a collision processing method in a fourth embodiment of the present application; FIG.

6 is a flowchart of a collision processing method in a fifth embodiment of the present application;

7 is a flowchart of a collision processing method in a sixth embodiment of the present application;

Figure 8 is a block diagram showing a collision processing apparatus in a seventh embodiment of the present application;

Figure 9 is a block diagram showing a collision processing apparatus in an eighth embodiment of the present application;

Figure 10 is a block diagram showing the robot in the ninth embodiment of the present application.

BEST MODE FOR CARRYING OUT THE INVENTION

In order to make the objects, the technical solutions and the advantages of the present application more clear, some embodiments of the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

The first embodiment of the present application relates to a collision processing method applied to a robot having at least one buffer device, and the specific flow is as shown in FIG.

In step 101, motion information of the identified object is determined.

Specifically, in the embodiment, before determining the motion information of the recognized object, the robot needs to identify and track at least one object appearing in the monitoring area, and then determine each according to the relevant data obtained by the identification and tracking. The motion information of the object.

It is worth mentioning that the motion information of the recognized object acquired by the robot in this embodiment includes at least the relative motion direction and the absolute running speed of the object.

In addition, the monitoring area referred to in the present embodiment specifically refers to a region in which the maximum detection distance of the sensor detecting device, the imaging device, and the like provided inside the robot is a radius, centering on the position where the robot is located.

In addition, in practical applications, the robot can not only detect the surrounding objects by using the omnidirectional detecting device or the imaging device provided therein, but also expand the viewing angle by means of the detecting device or the camera device of other devices with which the communication is established, thereby The surrounding objects can be better monitored, and the specific implementation manners can be reasonably set by a person skilled in the art, and no limitation is imposed here.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. Those skilled in the art can set the specific content that the motion information needs to acquire and the size of the monitoring area as needed. No restrictions.

For ease of understanding, the following describes the operation of identifying and tracking at least one object appearing in the monitoring area, and determining the motion information of the identified object. The specific implementation process is as follows:

First of all, the robot according to the preset frequency (such as 50Hz, that is, 50 times in 1 second, meaning the period of data acquisition T = 1 / 50 = 0.02 seconds), the point of occurrence in the center of its own position, with the maximum detection distance (eg 5 meters) Identify and track at least one object in the monitoring area composed of radii, and obtain the real-time position, real-time motion speed and real-time motion direction of each object.

After obtaining the above data, the robot performs the following processing for each object's real-time position, real-time motion speed, and real-time motion direction:

The motion information of the recognized object is determined according to any one or any combination of the real-time position of the object, the real-time motion speed, and the real-time motion direction.

That is, after acquiring the real-time position of the object, the real-time motion speed, and the real-time motion direction, the motion speed and the motion direction of the robot are deducted based on the mathematical model, and the absolute motion speed and the relative motion direction of the object, that is, the operation information of the object are obtained.

In addition, it is worth mentioning that in order to improve the accuracy of subsequent judgments and avoid interference due to acquired motion information, which affects the judgment of the robot, the robot needs to appear from before appearing at least one object in the monitoring area. An object that appears in the monitoring area at least twice in the at least one object in the monitoring area is selected.

That is, through the above filtering, a part of the interference object can be excluded, so that when acquiring the motion information of the object, the robot only acquires the motion information of the object that may collide with the robot, which not only ensures the accuracy of the subsequent judgment but also reduces the accuracy. The occupation of the resources of the processor that processes the data.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected, and those skilled in the art may set the collection conditions as needed, and are not limited herein.

In step 102, collision prediction information corresponding to the object is determined according to the motion information of the object.

Specifically, in the embodiment, when determining the collision prediction information corresponding to the object according to the motion information of the object, it is necessary to first determine the real-time distance of the robot from the object, such as by acquiring the coordinate information of the current location of the robot and the object. The coordinate information of the position is used to determine the real-time distance between the two, or the moving distance of the object is obtained by using the absolute motion speed, the relative motion direction and the motion time of the object, and the robot is acquired at the same exercise time based on the same manner. The distance of the motion is then determined based on the distance determined when an object is detected to be approaching, to determine the direct real-time distance between the two.

After determining the real-time distance of the robot from the object, the robot can determine the collision prediction information corresponding to the object according to the motion information of the object and the real-time distance between the two.

That is, under the preset acquisition frequency (time), after determining the real-time distance between the two and the absolute motion speed and relative motion direction of the object, the mathematical formula based on the speed and the distance (the time when the collision may occur T=real time) The distance S/actual speed V) determines the time at which the object may collide.

In addition, it is worth mentioning that, in practical applications, the determined collision prediction information may be a time when the robot may collide with the object, in addition to the time when the object may collide with the object.

Further, in order to ensure that the robot can perform subsequent judgments more accurately (determining whether to control the robot to pop up at least one buffer device according to the collision prediction information corresponding to the object), the determined collision prediction information may simultaneously add the time when the robot and the object may collide. And the location, the specific setting manner, the person skilled in the art can set as needed, and no limitation is made here.

In step 103, it is determined whether the robot will collide with the object.

Specifically, when it is determined whether the robot collides with the object according to the collision prediction information corresponding to the object, if it is determined that the robot is about to collide with the object, the process proceeds to step 104; if it is determined that the robot does not collide with the object, the process returns to step 101. Continue to get the motion information of the identified object.

In step 104, the protection mode is activated and the control robot pops up at least one buffer device.

Specifically, in the embodiment, the number of buffer devices that control the pop-up of the robot may be specifically determined according to the identity information of the object to be collided with the collision prediction information corresponding to the object.

That is, for different kinds of objects, such as people, vehicles, and stationary objects, the impact force generated in the event of a collision will be different, so the measures taken may be different, such as when a collision with a stationary object is possible. Immediately control the robot to stop the movement, so that collision can be avoided without the need of a pop-up buffer. If both are in motion and the unilateral stop motion cannot avoid the collision, the impact force generated during the collision is determined according to the motion information of the object, if the impact force is compared Large, the control robot pops up a plurality of buffer devices, and if the impact force is small, the control robot pops up a buffer device. In addition, while the buffer device is ejected, the robot can also be controlled to lower the center of gravity and avoid falling. By making countermeasures against the object according to the identity information of the object, the collision processing method can be more in line with actual needs.

In addition, in practical applications, the number of buffer devices that control the pop-up of the robot can also be determined according to the angle (ie, the area) that each buffer device can cover and the area that may collide when a collision occurs.

For example, the arrangement of the "head" of the robot and the body is set by six buffer devices, each of which can cover an area of 60 degrees. When it is determined that a collision will occur, the obtained contact data is obtained as a portion of the range of 60 degrees directly in front of the "head" of the robot, and then it is only necessary to control the robot to pop up a buffer device in the area. Alternatively, if the portion in contact with the collision is between the two buffer devices, the robot can be controlled to eject two buffer devices adjacent to the attachment of the contact area.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. In practical applications, those skilled in the art can appropriately set according to actual needs, and no limitation is made herein.

In addition, it should be noted that, in practical applications, when it is determined that the robot is about to collide with the object, the protection mode is activated, and the control robot pops up at least one buffer device, and can also control the robot to make an alarm prompt to inform the surrounding people to avoid in time. , further reduce the damage to people around.

In addition, it is worth mentioning that, in this embodiment, the buffer device needs to at least partially cover the robot after the pop-up, that is, the buffer device at least needs to cover the contact portion of the collision when the robot collides.

In addition, in order to further protect the robot, the part covered by the buffer device may further include a portion where the robot is relatively fragile, which is easily damaged after the collision, and a portion where the robot is sharp, and when the collision is easy, damage to the surrounding objects is not repeated. For example.

In addition, in the present embodiment, the buffer device provided in the robot may specifically be a buffer airbag.

Since the use of the cushioning airbag has been relatively mature, how to inflate the cushioning airbag and control its ejection will not be repeated here. The main protection of this embodiment is: how to determine whether the robot will encounter danger, and control the robot to eject at least one buffer airbag before the collision occurs, so that the pop-up buffer airbag can at least partially cover the robot, thereby reducing the collision on the robot and the surrounding of the robot. The damage caused by the object.

Figure 2 shows a schematic diagram of the robot ejecting two buffer devices (specifically two buffer airbags) before determining that it is about to collide with the object. Each buffer airbag covers part of the "head" area of the robot and collides. At the same time, the weaker part of the robot can be protected.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. Those skilled in the art can set the robot to pop up different numbers or pop up when receiving different collision prediction information as needed. Buffers of different angles (different positions), and buffers prepared by suitable materials are selected as needed, and are not limited herein.

It is not difficult to find through the above description that the collision processing method provided in the present embodiment can enable the robot to eject at least one buffer device to protect itself before determining that a collision risk may occur, thereby greatly reducing the damage caused by the collision accident to the robot and surrounding objects.

It should be noted that the robot mentioned in this embodiment may be a navigation robot, a catering robot, a cleaning robot, etc., which provides services in public or on a vehicle, or may be a robot that performs pipeline work in a factory, and is no longer here. For one example, no specific restrictions are imposed.

In addition, it is worth mentioning that, in actual applications, the above collision processing method can also be directly applied to a movable object such as a motor vehicle (such as a car), or to an object that does not have the ability to move, such as Postbox on the road, advertising screen, etc.

That is, any object that can be networked can utilize the collision processing method provided in this embodiment, regardless of whether there is a processor inside (if there is no processor, it can be transmitted to the cloud through the network, and after the processing, control information is generated, and the control is performed. The object can be responded to).

It should be noted that the above is only an example, and the technical solutions of the present application and the scope of the present invention are not limited. Those skilled in the art may combine or reduce any steps as needed, and are not limited herein.

Embodiments of the invention

A second embodiment of the present application relates to a collision processing method. The embodiment is further improved on the basis of the first embodiment. The specific improvement is: after the control robot pops up at least one buffer device, it is determined whether the danger of the robot is released, and according to the determination result, it is determined whether to withdraw the pop-up buffer device. The specific process is shown in Figure 3.

Specifically, in this embodiment, the steps 301 to 306 are included, and the steps 301 to 304 are respectively the same as the steps 101 to 104 in the first embodiment, and are not described herein again. For details of the technical details that are not described in detail in this embodiment, refer to the collision processing method provided in the first embodiment, and details are not described herein again.

In step 305, it is determined whether the danger is released.

Specifically, if it is determined that the danger is released, the process proceeds to step 306; otherwise, the step is continued to determine whether the danger is released until the danger is released, and the process proceeds to step 306.

It should be noted that determining the danger release in the embodiment specifically means that the robot has collided with an object, or has fallen, and no secondary collision has occurred for a period of time.

In step 306, the protection mode is exited and at least one buffer device is retracted.

Compared with the prior art, the collision processing method provided in this embodiment controls the robot to exit the protection mode after determining the danger release, and retracts all the buffering devices that are popped up, so that the robot can be promptly popped up before the next collision occurs. Buffer device.

A third embodiment of the present application relates to a collision processing method. The embodiment is further improved on the basis of the second embodiment. The specific improvement is: after recovering at least one buffer device, detecting whether the robot is injured, and if the injury cannot continue to work, an alarm prompt is given, the specific process As shown in Figure 4.

Specifically, in this embodiment, the steps 401 to 408 are included, wherein the steps 401 to 406 are substantially the same as the steps 301 to 306 in the second embodiment, and details are not described herein. For details of the technical details that are not described in detail in this embodiment, refer to the collision processing method provided in the second embodiment, and details are not described herein again.

In step 407, it is determined whether the robot is injured.

Specifically, when judging whether the robot is injured, it is necessary to first acquire the current state information of the robot, such as the running state of the internal device, and compare the current state information with the normal state information of the robot before the collision to determine whether the robot is If you are injured (if it can run normally), if it is determined that the robot is hurt, go to step 408; otherwise, exit the collision process directly.

In step 408, an alert is made.

Specifically, in this embodiment, when it is determined that the robot is damaged and cannot operate normally, the operation of making an alarm prompt may specifically notify the owner of the robot through a wireless signal (such as sending a message to the owner's mobile phone), or to the relevant management department. Send an alarm message and send the current location of the robot and the specific parts damaged so that the relevant personnel can quickly rush to the site for maintenance.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. Those skilled in the art can set the alarm mode of the robot as needed, which is not limited herein.

Compared with the prior art, the collision processing method provided in this embodiment can promptly make an alarm prompt when determining that the robot is injured, so that relevant personnel can quickly rush to the site for maintenance processing.

A fourth embodiment of the present application relates to a collision processing method applied to a robot having at least one buffer device, and the specific flow is as shown in FIG.

In step 501, status information of the robot is acquired.

Specifically, the state information of the robot acquired in the present embodiment specifically refers to whether or not the portion of the robot that is in contact with the ground is suspended (eg, the object that suddenly appears knocks down or is falling into an undetected pit).

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the technical scope to be protected. In practical applications, those skilled in the art can appropriately set according to requirements, and are not limited herein.

In step 502, it is determined whether the robot is in an unbalanced state.

Specifically, when it is determined whether the robot is in an unbalanced state according to the state information of the robot, if it is determined that the robot is in an unbalanced state (the robot is falling and the own mechanical mechanism cannot cope), the process proceeds to step 503; otherwise, the step 501 is continued to acquire the robot. Status information.

In step 503, the protection mode is activated, and the control robot pops up at least one buffer device.

It should be noted that, in practical applications, when it is determined that the robot is about to collide with the object, the protection mode is activated, and the control robot pops up at least one buffer device, and can also control the robot to make an alarm prompt to inform the surrounding people to avoid in time, further Reduce damage to people around you.

In addition, it is worth mentioning that, in this embodiment, the buffer device at least partially covers the robot after being popped up, and the covered portion is usually a part that the robot is relatively fragile, easily damaged after the collision, and the robot is sharp, and the collision is easy. The part that causes damage to surrounding objects, etc., is not mentioned here.

Since the use of the cushioning airbag has been relatively mature, how to inflate the cushioning airbag and control its ejection will not be repeated here. The main protection of this embodiment is how to determine whether the robot encounters danger, and controls the robot to eject at least one buffer airbag before the collision occurs, so that the pop-up buffer airbag can at least partially cover the robot, thereby reducing the collision on the robot and the objects around the robot. The damage caused.

It should be noted that the above is only an example, and does not limit the technical solution of the present application and the scope to be protected. Those skilled in the art can set the robot to pop up a different number of buffers when receiving different collision prediction information as needed. The device, and a buffer device prepared from a suitable material, is selected as needed, and is not limited herein.

It is not difficult to find out by the above description that the collision processing method provided in the present embodiment can cause the robot to be in an unbalanced state and eject at least one buffer device to protect itself before falling, thereby greatly reducing the damage caused by the collision accident to the robot and surrounding objects.

In addition, it is worth mentioning that in practical applications, the robot may encounter various unexpected situations, such as the cases listed in the above first to third embodiments, and the above various situations and the present implementation The situations that exist in the examples may exist interactively, so in order to enable the robot to better apply the external environment. The collision processing method provided in this embodiment may be used in combination with the collision processing methods provided in the foregoing first to third embodiments, and the specific interactions in the steps are implemented, and details are not described herein again, and those skilled in the art may Set its processing logic according to the actual situation, there is no limit here.

A fifth embodiment of the present application relates to a collision processing method. The embodiment is further improved on the basis of the fourth embodiment. The specific improvement is: after the control robot pops up at least one buffer device, it is determined whether the danger of the robot is released, and according to the determination result, it is determined whether to withdraw the pop-up buffer device. The specific process is shown in Figure 6.

Specifically, in this embodiment, the steps 601 to 605 are included, and the steps 601 to 603 are substantially the same as the steps 501 to 503 in the fourth embodiment, and details are not described herein again. For details of the technical details that are not described in detail in this embodiment, refer to the collision processing method provided in the fourth embodiment, and details are not described herein again.

In step 604, it is determined whether the danger is released.

Specifically, if it is determined that the danger is released, the process proceeds to step 605; otherwise, the step is continued to determine whether the danger is released until the danger is released, and the process proceeds to step 605.

It should be noted that determining the danger release in the embodiment specifically means that the robot has already fallen, and will not fall again by an external impact for a certain period of time.

In step 605, the protection mode is exited and at least one buffer device is retracted.

A sixth embodiment of the present application relates to a collision processing method. The embodiment is further improved on the basis of the fifth embodiment. The specific improvement is: after recovering at least one buffer device, detecting whether the robot is injured, and if the injury cannot continue to work, an alarm prompt is given, the specific process As shown in Figure 7.

Specifically, in this embodiment, the steps 701 to 707 are included, and the steps 701 to 705 are substantially the same as the steps 601 to 605 in the fifth embodiment, and details are not described herein. For details of the technical details that are not described in detail in this embodiment, refer to the collision processing method provided in the fifth embodiment, and details are not described herein again.

In step 706, it is determined whether the robot is injured.

Specifically, when judging whether the robot is injured, it is necessary to first acquire the current state information of the robot, such as the running state of the internal device, and compare the current state information with the normal state information of the robot before the collision to determine whether the robot is If you are hurt (if it can run normally), if it is determined that the robot is hurt, go to step 707; otherwise, directly exit the collision process.

In step 707, an alert is made.

Compared with the prior art, the collision processing method provided in the embodiment can timely make an alarm message when determining that the robot is injured, so that the relevant personnel can quickly rush to the site for maintenance processing.

A seventh embodiment of the present application relates to a collision processing apparatus mainly applied to a robot having at least one buffering device, the block structure of which is as shown in FIG.

As shown in FIG. 8, the collision processing apparatus includes a motion information determining module 801, a collision prediction information determining module 802, and a buffering apparatus pop-up determining module 803.

The motion information determining module 801 is configured to determine motion information of the identified object.

Specifically, before the motion information acquiring module 801 in the robot determines the motion information of the recognized object, each sensing device in the robot needs to identify and track at least one object appearing in the monitoring area, and then according to the identification. And the relevant data obtained by the tracking determines the motion information of each object.

It is worth mentioning that the motion information of the recognized object acquired in this embodiment includes at least the relative motion direction and the absolute running speed of the object.

The collision prediction information determining module 802 is configured to determine collision prediction information corresponding to the object according to the motion information of the object acquired by the motion information acquiring module 801.

The buffering device pop-up judging module 803 is configured to determine, according to the collision prediction information, the collision prediction information corresponding to the object determined by the module 802, and determine whether to control the robot to eject at least one buffer device. If it is determined that the control robot needs to eject at least one buffer device, the control command is sent by the processor in the robot or the cloud processor connected through the network, and the control robot pops up at least one buffer device.

It is not difficult to find through the above description that the collision processing device provided in the present embodiment can enable the robot to eject at least one buffer device to protect itself before determining that a collision risk may occur, thereby greatly reducing the damage caused by the collision accident to the robot and surrounding objects.

It should be noted that, as this embodiment is a virtual device embodiment corresponding to the first method embodiment, and thus the technical details not described in detail in this embodiment, refer to the collision processing method provided by the first embodiment of the present application. , will not repeat them here.

In addition, it should be noted that the device embodiments described above are merely illustrative and do not limit the scope of protection of the present application. In practical applications, those skilled in the art may select some of them according to actual needs or All modules are used to achieve the purpose of the solution of the embodiment, and no limitation is imposed here.

An eighth embodiment of the present application relates to a collision processing apparatus, and the specific structure is as shown in FIG.

As shown in FIG. 9, the collision processing apparatus includes a state information acquisition module 901, a state determination module 902, and a control module 903.

The status information obtaining module 901 is configured to acquire status information of the robot.

The state determining module 902 is configured to determine whether the robot is in an unbalanced state according to the state information of the robot acquired by the state information acquiring module 901.

The control module 903 is configured to start the protection mode when the state determination module 902 determines that the robot is in an unbalanced state, and control the robot to eject at least one buffer device.

It should be noted that, as this embodiment is a virtual device embodiment corresponding to the fourth method embodiment, and thus the technical details that are not described in detail in this embodiment, refer to the collision processing method provided by the fourth embodiment of the present application. , will not repeat them here.

It is not difficult to find out from the above description that the collision processing device provided in the embodiment can make the robot be in an unbalanced state and pop out at least one buffer device to protect itself before falling, thereby greatly reducing the damage caused by the collision accident to the robot and surrounding objects.

A ninth embodiment of the present application relates to a robot whose block structure is as shown in FIG.

The robot in the embodiment may be a navigation robot, a catering robot, a cleaning robot, or the like that provides services in public or on a vehicle, or may be a robot that performs pipeline operations in a factory. No specific restrictions are imposed.

Specifically, the inside of the robot may specifically include one or more processors 1001, a memory 1002, and one or more buffer devices 1003. One processor 1001 and one buffer device 1003 are exemplified in FIG.

It should be noted that, in practical applications, the robot may encounter various unexpected situations, such as those listed in the first embodiment to the sixth embodiment, so that the robot can better apply the external environment. . In this embodiment, each functional module in the collision processing device involved in each of the above embodiments is deployed on the processor 1001, and the processor 1001 is connected to the memory 1002 and the buffer device 1003 through a bus or other connection. In 10, the bus connection is taken as an example.

The memory 1002 is a computer readable storage medium, and can be used to store a software program, a computer executable program, and a module, such as a program instruction/module corresponding to the collision processing method involved in any method embodiment of the present application. The processor 1001 executes various functional applications and data processing of the server by executing software programs, instructions, and modules stored in the memory 1002, that is, implementing the collision processing method involved in any method embodiment of the present application.

The memory 1002 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required by at least one function; the storage data area may establish a history database for storing a frequency for identifying surrounding moving objects, and collecting Radius and various countermeasures. In addition, the memory 1002 may include a high speed random access memory, and may also include a read/write memory (Random Access Memory, RAM) or the like. In some embodiments, the memory 1002 can optionally include memory remotely located relative to the processor 1001, which can be connected to the terminal device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

In an actual application, the memory 1002 may store at least one instruction executed by the processor 1001, and the instruction is executed by the at least one processor 1001, so that the at least one processor 1001 can perform the collision processing method according to any method embodiment of the present application, and control Each of the functional modules in the collision processing device completes the respective operations in the collision processing method. For the technical details not described in detail in this embodiment, reference may be made to the collision processing method provided by any embodiment of the present application.

In addition, it is worth mentioning that with the development of cloud computing technology, in order to further improve the processing capability of the robot, the robot mentioned in this embodiment may also be a cloud intelligent robot, that is, a robot "brain" for performing processing operations. It’s in the cloud.

Specifically, the cloud intelligent robot connects the robot body and the cloud “brain” with a safe and fast mobile network, making the intelligent computing capability of the cloud a convenient service, thereby greatly reducing the research and development costs and operating costs of the intelligent robot. And with the powerful computing power of the cloud, it is more convenient and fast to perform autonomous navigation and achieve rapid positioning.

It should be noted that the above-mentioned two types of robots are only specific examples in the embodiment, and do not limit the technical solutions and the scope to be protected of the present application. In practical applications, those skilled in the art It can be implemented based on the development process of the existing machine equipment based on the implementation process of the above collision processing method, and is not limited herein.

A tenth embodiment of the present application is directed to a computer readable storage medium, which is a computer readable storage medium having stored therein computer instructions that enable a computer to perform any of the present application The collision processing method involved in the method embodiment.

Those skilled in the art can understand that all or part of the steps of implementing the above embodiments may be completed by a program instructing related hardware, and the program is stored in a storage medium, and includes a plurality of instructions for making a device (which may be a single chip microcomputer). , a chip, etc. or a processor performs all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

A person skilled in the art can understand that the above embodiments are specific embodiments of the present application, and various changes can be made in the form and details without departing from the spirit and scope of the application. range.

Claims

A collision processing method is applied to a robot having at least one buffer device, the collision processing method comprising:

Determining motion information of the recognized object; wherein the motion information includes at least a relative motion direction and an absolute motion speed;

Determining collision prediction information corresponding to the object according to the motion information of the object;

Determining whether to control the robot to eject at least one of the buffer devices according to the collision prediction information corresponding to the object.
The collision processing method according to claim 1, wherein the collision processing method further comprises: before the determining the motion information of the recognized object, the collision processing method further comprises:

Identify and track at least one object that appears in the monitored area.
The collision processing method according to claim 2, wherein the identifying and tracking the at least one object that is present in the monitoring area, and determining the motion information of the identified object, specifically includes:

Identifying and tracking the at least one object appearing in the monitoring area to obtain a real-time position, a real-time moving speed, and a real-time moving direction of each of the objects;

The following processing is performed for each of the real-time position, the real-time motion speed, and the real-time motion direction of each of the objects:

The recognized motion information of the object is determined according to any one or any combination of the real-time position of the object, the real-time motion speed, and the real-time motion direction.
The collision processing method according to claim 2 or 3, wherein the collision processing method further comprises: before the identifying and tracking the at least one object appearing in the monitoring area, the collision processing method further comprises:

It is determined that the object appears in the monitoring area at least twice in succession.
The collision processing method according to any one of claims 1 to 4, wherein the determining the collision prediction information corresponding to the object according to the motion information of the object includes:

Determining a real-time distance of the robot from the object;

Determining the collision prediction information according to the motion information of the object and the real-time distance; wherein the collision prediction information includes a time and/or a location where a collision may occur with the object.
The collision processing method according to any one of claims 1 to 5, wherein the determining, according to the collision prediction information corresponding to the object, determining whether to control the robot to eject at least one of the buffering devices comprises:

Determining, according to the collision prediction information corresponding to the object, whether the robot collides with the object;

If it is determined that the robot is about to collide with the object, the protection mode is activated, and the robot is controlled to eject at least one of the buffer devices; wherein the buffer device at least partially covers the robot after being popped;

If it is determined that the robot does not collide with the object, it continues to determine the motion information of the recognized object.
The collision processing method according to claim 6, wherein the controlling the robot to eject at least one of the buffering devices comprises:

Obtaining identity information of the object;

And controlling the robot to pop up at least one of the buffer devices according to the collision prediction information corresponding to the object and the identity information of the object.
The collision processing method according to claim 6 or 7, wherein after the controlling the robot to eject at least one of the buffering devices, the collision processing method further comprises:

Determine the danger of lifting;

Exiting the protection mode, the at least one buffer device is retracted.
The collision processing method according to claim 8, wherein after the retracting the at least one buffer device, the collision processing method further comprises:

Obtaining state information of the robot, determining that the robot is injured, and making an alarm prompt.
The collision processing method according to any one of claims 1 to 8, wherein the buffer device is a buffer airbag.
A collision processing method is applied to a robot having at least one buffer device, the collision processing method comprising:

Obtaining state information of the robot;

Determining whether to control the robot to eject at least one of the buffer devices according to the state information of the robot.
The collision processing method according to claim 11, wherein the determining whether to control the robot to eject at least one of the buffering devices according to the state information of the robot comprises:

Determining whether the robot is in an unbalanced state according to state information of the robot;

If it is determined that the robot is in an unbalanced state, the protection mode is activated, and the robot is controlled to eject at least one of the buffer devices; wherein the buffer device at least partially covers the robot after being popped up.
The collision processing method according to claim 11 or 12, wherein after the controlling the robot to eject at least one of the buffering devices, the collision processing method further comprises:

Determine the danger of lifting;

Exiting the protection mode, the at least one buffer device is retracted.
The collision processing method according to claim 13, wherein after the retracting the at least one buffer device, the collision processing method further comprises:

Obtaining state information of the robot, determining that the robot is injured, and making an alarm prompt.
The collision processing method according to any one of claims 11 to 14, wherein the buffer device is a buffer airbag.
A collision processing apparatus is applied to a robot having at least one buffering device, the collision processing apparatus comprising: a motion information determining module, a collision prediction information determining module, and a buffering device pop-up determining module;

The motion information determining module is configured to determine motion information of the recognized object; wherein the motion information includes at least a relative motion direction and an absolute motion speed;

The collision prediction information determining module is configured to determine collision prediction information corresponding to the object according to the motion information of the object acquired by the motion information acquiring module;

The buffering device pop-up determining module is configured to determine, according to the collision prediction information, the collision prediction information corresponding to the object determined by the module, and determine whether to control the robot to pop-up at least one of the buffering devices.
A collision processing device is applied to a robot having at least one buffer device, the collision processing device comprising: a state information acquisition module, a state determination module, and a control module;

The status information acquiring module is configured to acquire status information of the robot;

The state determining module is configured to determine, according to the state information of the robot acquired by the state information acquiring module, whether the robot is in an unbalanced state;

The control module is configured to start a protection mode when the state determination module determines that the robot is in an unbalanced state, and control the robot to eject at least one of the buffer devices.
A robot that includes:

At least one processor, a memory communicatively coupled to the at least one processor; and at least one buffer device communicatively coupled to the at least one processor;

Wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of claims 1 to 10. The collision processing method described.
A robot that includes:

At least one processor, a memory communicatively coupled to the at least one processor; and at least one buffer device communicatively coupled to the at least one processor;

Wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of claims 11-15 The collision processing method described.
A computer readable storage medium storing computer instructions for causing the computer to perform the collision processing method of any one of claims 1 to 10.
A computer readable storage medium storing computer instructions for causing the computer to perform the collision processing method of any one of claims 11 to 15.