CN115185277A - Artificial intelligence-based multi-legged robot motion planning method and system - Google Patents
Artificial intelligence-based multi-legged robot motion planning method and system Download PDFInfo
- Publication number
- CN115185277A CN115185277A CN202210821698.8A CN202210821698A CN115185277A CN 115185277 A CN115185277 A CN 115185277A CN 202210821698 A CN202210821698 A CN 202210821698A CN 115185277 A CN115185277 A CN 115185277A
- Authority
- CN
- China
- Prior art keywords
- program
- interrupt
- symbol
- artificial intelligence
- planning method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 42
- 230000006870 function Effects 0.000 claims abstract description 4
- 238000004891 communication Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 230000000903 blocking effect Effects 0.000 claims description 9
- 238000007726 management method Methods 0.000 claims description 9
- 230000002618 waking effect Effects 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000011084 recovery Methods 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012856 packing Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000007727 signaling mechanism Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a multi-legged robot motion planning method and system based on artificial intelligence, belonging to the technical field of artificial intelligence and comprising the following steps: s1, starting a machine; s2, operation control; s3, planning a path; s4, machine operation, wherein the operation control comprises the following steps: the function is mainly to control the execution of user program, and a user writes the problem to be solved into a program by a certain programming language and inputs the program execution requirement into the computer. The invention conveniently solves the problems that the existing planning method can not position the address of the robot in the using process, so that the position of the robot can not be changed in time and the operation of the robot is influenced by combining the space and address allocation, symbol analysis and repositioning.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a multi-legged robot motion planning method and system based on artificial intelligence.
Background
With the development and exploration of science and technology, robots are increasingly used by human production and life, and the multi-legged robot as one of mobile robots has the advantages of strong terrain adaptability, various motion modes, good stability and the like, and is widely applied to multiple fields, wherein the research on the motion planning method of the multi-legged robot is a hotspot in the fields. However, in the current research method, the mathematical modeling process of the robot and the obstacle and the mathematics of the related constraint conditions are complicated, and complicated parameter adjustment is required for different foot robots and different research scenes. The following problems exist in the prior art:
1. in the prior art, the problem that the existing planning method cannot position the address of the robot in the using process, so that the position of the robot cannot be changed in time and the operation of the robot is influenced exists;
2. in the prior art, when the existing planning system is used, the robot cannot be connected with a network, so that the robot cannot be controlled in time during operation, and further the original use purpose of the planning system cannot be achieved.
Disclosure of Invention
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a multi-legged robot motion planning method and system based on artificial intelligence comprises the following steps: s1, starting a machine; s2, operation control; s3, planning a path; and S4, running the machine.
The technical scheme of the invention is further improved as follows: the operation control comprises the following steps: the functions are mainly to control the execution of user program, a user writes the problem to be solved into a program with a certain programming language, then inputs the program with the requirement of the execution into the computer, the operating system controls the execution of the user program until the end according to the requirement, the operating system controls the execution of the user program, calls in the corresponding compiler to compile the source program written by a certain design language into the object program executable by the computer, allocates memory resource to call in the program to the memory and start, processes various events in the execution and the processing of accident related to the requirement of the operator contact according to the requirement specified by the user, etc.
The technical scheme of the invention is further improved as follows: the operation control comprises the following steps: A. waking up a process; B. protecting the process environment; C. transferring into a program; D. interrupting the process; F. a recovery process, the wake-up process: when the interrupt processing program starts to execute, firstly waking up the driving (program) process in the blocking state, if a semaphore mechanism is adopted, waking up the driving (program) process in the blocking state by executing signal operation; when a signaling mechanism is used, a signal is sent to the blocking process.
The technical scheme of the invention is further improved as follows: the protection process environment: the contents of the processor state word PSW and the Program Counter (PC) are normally saved automatically by hardware in an interrupt reservation (stack) and then the CPU context information of the interrupted process, i.e. including all CPU registers, such as general purpose registers, segment registers, etc., is pushed onto the interrupt stack, since these registers may be used during interrupt handling, the program is interrupted by instructions in the N position, the contents of the program counter are N +1, and the contents of all registers are kept on the stack.
The technical scheme of the invention is further improved as follows: the transfer-in program comprises the following steps: testing each interrupt source by the processor to determine the I/O device causing the interrupt, sending a response signal to the process sending the interrupt request to eliminate the interrupt request signal, loading the entry address of the interrupt processing program of the corresponding device into the program counter, and turning the processor to the interrupt processing program, wherein the interrupt processing: for different devices, there are different interrupt processing programs, which first read the device status from the device controller to determine whether the interrupt is a normal complete interrupt or an abnormal complete interrupt. If the result is the former, the interrupt program is processed; if there is still command, it can send new command to the controller to make new round of data transmission. If the abnormal ending interruption is detected, corresponding processing is carried out according to the reason of the abnormal ending interruption.
The technical scheme of the invention is further improved as follows: the recovery process comprises the following steps: after the interrupt processing is completed, the field information of the interrupted process stored in the interrupt stack is fetched and loaded into the corresponding registers, including the address N +1 of the instruction to be executed next by the program, the processor state word PSW, and the contents of the general purpose and segment registers, starting at N +1 and finally returning to the interrupted program when the processor re-executes the program.
The technical scheme of the invention is further improved as follows: the path planning comprises the following steps: a. space and address allocation; b. analyzing the symbol; c. relocation, the space and address allocation: scanning all input target files to obtain the lengths, attributes and positions of all stages of the input target files, collecting all symbol definitions and symbol references in a symbol table in the input target files, uniformly putting the symbol definitions and the symbol references into a global symbol table, so that a connector can obtain the lengths of all input target files, combining the symbol definitions and the symbol references, calculating the combined lengths and positions of all the sections in an output file, packing the ar without any option into a file, establishing a mapping relation, updating a symbol index table of a static library by a hash, if the file is updated and the ar needs to be rerandib, otherwise, finding no symbol and reporting a link error when the link is connected, and analyzing the symbol: resolving the symbols is to associate each symbol reference with a determined symbol definition in a symbol table in the relocatable object file that it inputs, and if not, a compile-time error occurs, and the relocating: different processor instructions differ in the format and manner of the address, and locate different IP addresses in different ways.
An artificial intelligence-based multi-legged robot motion system, comprising: an operating system, the operating system comprising: 1. a dynamic password module; 2. a password verification module; 3. a communication connection module, the dynamic cryptographic module: the password authentication module is used for connecting with at least one management user side, generating a dynamic password and sending the dynamic password to the at least one management user side, and comprises: the communication connection module is connected with a network transmission module of at least one unbound user terminal and used for verifying whether a dynamic password acquired by the at least one unbound user terminal from the at least one management user terminal is correct or not and verifying whether a request password is correct or not according to a preset password, and the communication connection module is used for: the system is respectively connected with the password authentication module, the at least one unbound user terminal and the gateway and used for establishing communication connection between the at least one unbound user terminal and the gateway when the results returned by the password authentication module are all correct so as to realize binding between the at least one unbound user terminal and the gateway and controlling the machine through a network.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the technical progress that:
1. the invention provides a multi-legged robot motion planning method and system based on artificial intelligence, which are ingenious in design and adopt combination of space and address allocation, symbol analysis and repositioning, so that the problems that the position of a robot cannot be timely changed and the operation of the robot is influenced due to the fact that the address of the robot cannot be positioned in the using process of an existing planning method are conveniently solved, and the address of the robot can be positioned and the position of the robot can be timely changed when the planning method is used through the combination of the structures, so that the operation of the robot is prevented from being influenced.
2. The invention provides a multi-legged robot motion planning method and system based on artificial intelligence, which can solve the problem that the robot cannot be controlled in time during operation due to the fact that the robot cannot be connected with a network when the existing planning system is used by adopting the combination of a dynamic password module, a password verification module and a communication connection module.
Drawings
FIG. 1 is a schematic structural diagram of the steps of the method of the present invention;
FIG. 2 is a schematic diagram of the operation control flow structure of the present invention;
FIG. 3 is a schematic diagram of a path planning process according to the present invention;
fig. 4 is a schematic view of the flow structure of the operation system of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples:
example 1
As shown in fig. 1-4, the present invention provides a method and a system for planning the motion of a multi-legged robot based on artificial intelligence, comprising the following steps: s1, starting a machine; s2, operation control; s3, planning a path; s4, machine operation, wherein the operation control comprises the following steps: the function is mainly to control the execution of user program, a user writes the problem to be solved into a program by a certain programming language, then inputs the program with the requirement of executing the program into the computer, the operating system controls the execution of the user program until the end according to the requirement, the operating system controls the execution of the user program, calls in a corresponding compiler to compile a source program written by a certain design language into a target program executable by the computer, allocates memory resources to call the program into a memory and start, processes various events occurring in the execution and the processing of accidents related to the contact of operators according to the requirement specified by the user, and the operation control comprises: A. waking up a process; B. protecting the process environment; C. transferring into a program; D. interrupting the process; F. a recovery process, the wake-up process: when the interrupt handler starts to execute, firstly awakening the driver (program) process in the blocking state, if a semaphore mechanism is adopted, awakening the driver (program) process in the blocking state by executing signal operation; when a signal mechanism is adopted, a signal is sent to a blocking process, and the process environment is protected: the contents of the processor state word PSW and the Program Counter (PC) are normally saved automatically by hardware in an interrupt reservation (stack) and then the CPU context information of the interrupted process, i.e. including all CPU registers, such as general purpose registers, segment registers, etc., is pushed onto the interrupt stack, since these registers may be used during interrupt handling, the program is interrupted by instructions in the N position, the contents of the program counter are N +1, and the contents of all registers are kept on the stack.
Example 2
As shown in fig. 1 to 4, on the basis of embodiment 1, the present invention provides a technical solution: the transfer-in program comprises the following steps: testing each interrupt source by the processor to determine the I/O device causing the current interrupt, sending a response signal to the process sending the interrupt request to eliminate the interrupt request signal, loading the entry address of the interrupt processing program of the corresponding device into the program counter, and turning the processor to the interrupt processing program, wherein the interrupt processing is as follows: for different devices, there are different interrupt handlers, which first read the device status from the device controller to determine whether the current interrupt is a normal complete interrupt or an abnormal end interrupt. If so, ending the processing of the interrupt program; if there is still command, it can send new command to the controller to make new round of data transmission. If the abnormal ending interrupt is detected, corresponding processing is carried out according to the reason of the abnormal ending interrupt, and the recovery process: after the interrupt processing is completed, the field information of the interrupted process stored in the interrupt stack can be fetched and loaded into the corresponding registers, which include the address N +1 of the instruction to be executed next by the program, the processor state word PSW, and the contents of the general purpose registers and segment registers, and when the processor is executing the program, it starts from N +1 and finally returns to the interrupted program, and the path plan includes: a. space and address allocation; b. analyzing the symbol; c. relocation, the space and address allocation: scanning all input target files to obtain the lengths, attributes and positions of all stages of the input target files, collecting all symbol definitions and symbol references in a symbol table in the input target files, unifying the symbol definitions and the symbol references into a global symbol table, so that a connector can obtain the segment lengths of all the input target files, combining the symbol definitions and the symbol references, calculating the combined length and position of all the segments in an output file, packing ar without any option into a file, establishing a mapping relation, updating a symbol index table of a static library by a hash, if the file is updated and the ar needs to be reranked, otherwise, finding no symbol and reporting a link error when the link is carried out, and analyzing the symbol: resolving the symbols is to associate each symbol reference with a determined symbol definition in a symbol table in the relocatable object file that it inputs, and if not, a compile-time error occurs, and the relocating: different processor instructions are different in address format and manner, and different IP addresses are located in different manners.
In a second aspect: an artificial intelligence-based multi-legged robot motion system, comprising: an operating system, said operating system comprising: 1. a dynamic password module; 2. a password verification module; 3. a communication connection module, the dynamic cryptographic module: the password authentication module is used for connecting with at least one management user side, generating a dynamic password and sending the dynamic password to the at least one management user side, and comprises: the communication connection module is connected with a network transmission module of at least one unbound user terminal and used for verifying whether a dynamic password acquired by the at least one unbound user terminal from the at least one management user terminal is correct or not and verifying whether a request password is correct or not according to a preset password, and the communication connection module is used for: the system is respectively connected with the password authentication module, the at least one unbound user side and the gateway and used for establishing communication connection between the at least one unbound user side and the gateway when the results returned by the password authentication module are all correct so as to bind the at least one unbound user side and the gateway and control a machine through a network.
Has the advantages that: the method has the advantages that the method is ingenious in design, the combination of space and address allocation, symbol analysis and repositioning is adopted, the problems that the address of the robot cannot be located in the using process of the existing planning method, the position of the robot cannot be changed in time and the operation of the robot is influenced are solved conveniently, the planning method can be used for locating the address of the robot and changing the position of the robot in time through the combination of the above structures, and the operation of the robot is prevented from being influenced.
Through adopting dynamic password module, password verification module, communication connection module combination setting, can realize solving current planning system and when using, can't make the robot be connected with the network, lead to the problem that the robot can't in time obtain control when the operation, combine in order to reach through above structure and make planning system when using, can make the robot be connected with the network, in time control the robot through the network, improve the practicality of system.
The present invention has been described in general terms in the foregoing, but it will be apparent to those skilled in the art that modifications and improvements can be made thereto based on the present invention. Therefore, modifications or improvements are within the scope of the invention without departing from the spirit of the inventive concept.
Claims (8)
1. A multi-legged robot motion planning method and system based on artificial intelligence are characterized in that: the method comprises the following steps: s1, starting a machine; s2, operation control; s3, planning a path; and S4, running the machine.
2. The artificial intelligence based multi-legged robot motion planning method and system according to claim 1, characterized in that: the operation control comprises the following steps: the function is mainly to control the execution of user program, a user writes the problem to be solved into a program by a certain programming language, then inputs the program with the requirement of the program execution into the computer, the operating system controls the execution of the user program until the end of the execution of the user program according to the requirement, the operating system controls the execution of the user program, calls in a corresponding compiler to compile a source program written by a certain design language into a target program executable by the computer, allocates memory resources to call the program into a memory and start the program, processes various events in the execution and the processing of the accident related to the requirement of the contact of the operator according to the requirement specified by the user, and the like.
3. The artificial intelligence based multi-legged robot motion planning method and system according to claim 1, characterized in that: the operation control comprises the following steps: A. waking up a process; B. protecting the process environment; C. transferring into a program; D. interrupting the process; F. a recovery process, the wake-up process: when the interrupt processing program starts to execute, firstly waking up the driving (program) process in the blocking state, if a semaphore mechanism is adopted, waking up the driving (program) process in the blocking state by executing signal operation; when the signaling mechanism is used, a signal is sent to the blocking process.
4. The artificial intelligence based multi-legged robot motion planning method and system according to claim 3, characterized in that: the protection process environment: the contents of the processor state word PSW and the Program Counter (PC) are normally saved automatically by hardware in an interrupt reservation (stack) and then the CPU context information of the interrupted process, i.e. including all CPU registers, such as general purpose registers, segment registers, etc., is pushed onto the interrupt stack, since these registers may be used during interrupt handling, the program is interrupted by instructions in the N position, the contents of the program counter are N +1, and the contents of all registers are kept on the stack.
5. The artificial intelligence based multi-legged robot motion planning method and system according to claim 3, characterized in that: the transfer-in program comprises the following steps: testing each interrupt source by the processor to determine the I/O device causing the interrupt, sending a response signal to the process sending the interrupt request to eliminate the interrupt request signal, loading the entry address of the interrupt processing program of the corresponding device into the program counter, and turning the processor to the interrupt processing program, wherein the interrupt processing: for different devices, there are different interrupt handlers, which first read the device status from the device controller to determine whether the current interrupt is a normal complete interrupt or an abnormal end interrupt. If the result is the former, the interrupt program is processed; if there is still command, it can send new command to the controller to make new round of data transmission. If the abnormal ending interrupt is detected, corresponding processing is carried out according to the reason of the abnormal ending interrupt.
6. The artificial intelligence based multi-legged robot motion planning method and system according to claim 3, characterized in that: the recovery process comprises the following steps: after the interrupt processing is completed, the field information of the interrupted process stored in the interrupt stack is fetched and loaded into the corresponding registers, including the address N +1 of the instruction to be executed next by the program, the processor state word PSW, and the contents of the general purpose and segment registers, starting at N +1 and finally returning to the interrupted program when the processor re-executes the program.
7. The artificial intelligence based multi-legged robot motion planning method and system according to claim 1, characterized in that: the path planning comprises the following steps: a. space and address allocation; b. analyzing the symbol; c. relocation, the space and address allocation: scanning all input target files to obtain the lengths, attributes and positions of all stages of the input target files, collecting all symbol definitions and symbol references in a symbol table in the input target files, uniformly putting the symbol definitions and the symbol references into a global symbol table, so that a connector can obtain the lengths of all input target files, combining the symbol definitions and the symbol references, calculating the combined lengths and positions of all the sections in an output file, packing the ar without any option into a file, establishing a mapping relation, updating a symbol index table of a static library by a hash, if the file is updated and the ar needs to be rerandib, otherwise, finding no symbol and reporting a link error when the link is connected, and analyzing the symbol: resolving the symbols is to associate each symbol reference with a determined symbol definition in a symbol table in the relocatable object file that it inputs, and if not, a compile-time error occurs, and the relocating: different processor instructions are different in address format and manner, and different IP addresses are located in different manners.
8. The utility model provides a polypod robot motion system based on artificial intelligence which characterized in that: comprises the following steps: an operating system, the operating system comprising: 1. a dynamic password module; 2. a password verification module; 3. a communication connection module, the dynamic cryptographic module: the password authentication module is used for connecting with at least one management user side, generating a dynamic password and sending the dynamic password to the at least one management user side, and comprises: the communication connection module is connected with a network transmission module of at least one unbound user side and used for verifying whether a dynamic password acquired by the at least one unbound user side from the at least one management user side is correct or not and verifying whether a request password is correct or not according to a preset password, and the communication connection module is used for: the system is respectively connected with the password authentication module, the at least one unbound user side and the gateway and used for establishing communication connection between the at least one unbound user side and the gateway when the results returned by the password authentication module are all correct so as to bind the at least one unbound user side and the gateway and control a machine through a network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210821698.8A CN115185277A (en) | 2022-07-12 | 2022-07-12 | Artificial intelligence-based multi-legged robot motion planning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210821698.8A CN115185277A (en) | 2022-07-12 | 2022-07-12 | Artificial intelligence-based multi-legged robot motion planning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115185277A true CN115185277A (en) | 2022-10-14 |
Family
ID=83518800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210821698.8A Pending CN115185277A (en) | 2022-07-12 | 2022-07-12 | Artificial intelligence-based multi-legged robot motion planning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115185277A (en) |
-
2022
- 2022-07-12 CN CN202210821698.8A patent/CN115185277A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100555218C (en) | Be used to improve the apparatus and method of the simulation velocity of the middle-and-high-ranking language of analogue system on the sheet | |
| CN103778061B (en) | Automatically detection and the bearing calibration of Array Bound mistake | |
| CN101587455B (en) | Method for checking memory leak for vxWorks operating system | |
| JP5039428B2 (en) | Programmable controller and PLC system | |
| CN100590604C (en) | Debugging breakpoints on pluggable components | |
| US5495612A (en) | System for dynamically changing an execution program and method for doing the same | |
| CN100570558C (en) | A kind of chip firmware updating method | |
| CN111813428A (en) | Method and device for upgrading terminal firmware, electronic equipment and storage medium | |
| CN112558946A (en) | Method, device and equipment for generating code and computer readable storage medium | |
| US20090228861A1 (en) | Method and System for Improved Tool Interaction with a Target | |
| CN111385661B (en) | Method, device, terminal and storage medium for voice control of full screen playing | |
| CN110045952B (en) | Code calling method and device | |
| CN101237350B (en) | Global variant exception alteration and positioning method for multi-task environment single board machine | |
| CN112230848A (en) | NVM automatic configuration method, device and equipment | |
| CN109918082B (en) | Compiling system and method for software development | |
| CN110334031B (en) | Memory allocation code detection method and device, computer equipment and storage medium | |
| CN115185277A (en) | Artificial intelligence-based multi-legged robot motion planning method and system | |
| US10761892B2 (en) | Method and electronic device for executing data reading/writing in volume migration | |
| CN113342376B (en) | Method and device for upgrading operating system of Internet of things equipment | |
| US20040015876A1 (en) | Method and structure of implementing a safe pointer | |
| CN112711527A (en) | Debugging method and device of real-time process, target machine and storage medium | |
| CN112114811A (en) | Compiling method, device and equipment | |
| US10452408B1 (en) | System and method for intercepting data flow between a computer process and a file | |
| CN111176619A (en) | FPGA execution flow control method and device, computer equipment and storage medium | |
| CN114546480B (en) | Code automatic integration method, device and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |