CN114684293A - Robot walking simulation algorithm - Google Patents
Robot walking simulation algorithm Download PDFInfo
- Publication number
- CN114684293A CN114684293A CN202011579027.2A CN202011579027A CN114684293A CN 114684293 A CN114684293 A CN 114684293A CN 202011579027 A CN202011579027 A CN 202011579027A CN 114684293 A CN114684293 A CN 114684293A
- Authority
- CN
- China
- Prior art keywords
- robot
- training
- gait
- biped
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D57/00—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track
- B62D57/02—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members
- B62D57/032—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members with alternately or sequentially lifted supporting base and legs; with alternately or sequentially lifted feet or skid
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/1605—Simulation of manipulator lay-out, design, modelling of manipulator
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1661—Programme controls characterised by programming, planning systems for manipulators characterised by task planning, object-oriented languages
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
Abstract
In order to improve the stability control effect of the biped robot in the cooperation state and optimize the algorithm, the invention samples special point values and simulates the following steps on a computer: establishing a neural network model based on a nerve cell layer, training by using gait point value data of the first biped robot obtained by a gait measuring device, and training the gait balance of the first biped robot; and adjusting according to the balance result. The biped robot not only can improve the training depth of a gait control model based on the experience data of the biped robot or other biped robots, but also can effectively cooperate with other biped robots to realize experience sharing, thereby achieving the effects of carrying the same goods together, quickly adapting to new environment so as to provide more important tasks and operate enough, and the like.
Description
Technical Field
The invention relates to the technical field of automatic control.
Background
The biped robot has better mobility than a conventional wheeled robot. The biped walking system has very rich dynamic characteristics and low requirements on walking environments. At present, most buildings and tools are designed according to the height and the shape of a person, so that the biped robot has better use flexibility as a robot platform. Meanwhile, the control of the gait stability of the biped robot is the premise and the basis for the smooth walking of the robot. Gait refers to the relationship between each joint in time and space during standing or walking, and can be described by the movement track of the joint.
The conventional gait stability research of the biped robot is based on a Zero Moment Point (ZMP) method, a mathematical model of the biped robot is established, and a control rule is derived according to the condition that the ZMP must fall in a stable area, such as the sole range of a robot foot. However, the walking of the robot is likely to fail due to factors such as road conditions, and even the biped robot falls down. This phenomenon is a fatal disaster for the cooperation of a plurality of biped robots.
Disclosure of Invention
In order to improve the stability control effect of the biped robot in a cooperation state, the invention provides a robot walking simulation algorithm, which comprises the following steps simulated on a computer: establishing a neural network model based on the neural cell layer, training by using gait data of the first biped robot obtained by the gait measuring device, and training the gait balance of the first biped robot; and adjusting according to the balance result.
Furthermore, the feet, the ankle joint and the knee joint of the robot are all three degrees of freedom.
Further, the gait data includes angular velocity and acceleration, which are angular velocity and acceleration in a forward direction.
Further, the gait measurement device includes a gyroscope and an accelerometer.
Further, the training of the gait data comprises:
obtaining road surface information data, wherein the road surface information data at least comprises route information and experience data which are in a communication relation with the current position in an electronic map;
acquiring gait data, training the pre-constructed neural network model based on the gait data to obtain a primary training model:
wherein p and q represent a positive integer randomly selected between 1 and 10, and 0 is taken when the two formula indices have no corresponding physical meaning;
and carrying out deep learning on the experience data by using the primary training model, wherein the learning result is used for carrying out Hopfield network training to obtain a secondary training model.
Further, training the gait balance comprises:
obtaining gait data of at least one second biped robot;
and carrying out deep learning on the gait data of each second biped robot by using the two-stage training model of the first biped robot, summarizing the learning results, and using the final learning result for sparse self-encoder training to obtain the three-stage training model of the first biped robot.
Further, the adjusting according to the balancing result comprises: gait data of the first biped robot is input into the three-level training model for differential training, and the obtained four-level training model outputs action settings of each degree of freedom of the biped, the ankle joint and the knee joint of the first biped robot.
Further, the first-level training model is selected by utilizing a random selection mode in a Monte Carlo search tree optimization algorithm.
Further, the empirical data is gait data from the first biped robot or the second biped robot when the robot has previously passed through a route having the greatest similarity to the route information.
The invention has the beneficial effects that: the biped robot not only can improve the training depth of the gait control model based on the experience data of the biped robot or other biped robots, but also can effectively cooperate with other biped robots to realize mutual experience sharing, thereby achieving the effects of carrying the same goods together, rapidly adapting to new environments so as to provide more important tasks and operate enough, and the like.
Drawings
Fig. 1 shows a block flow diagram of the method.
Detailed Description
A robot walking simulation algorithm comprises the following steps of simulating on a computer: establishing a neural network model based on the neural cell layer, training by using gait data of the first biped robot obtained by the gait measuring device, and training the gait balance of the first biped robot; and adjusting according to the balance result.
Preferably, the two feet, the ankle joint and the knee joint of the robot are all three degrees of freedom.
Preferably, the gait data includes angular velocity and acceleration, which are angular velocity and acceleration in a forward direction.
Preferably, the gait measurement device comprises a gyroscope and an accelerometer.
Preferably, the training of the gait data comprises:
obtaining road surface information data, wherein the road surface information data at least comprises route information and experience data which are in a communication relation with the current position in an electronic map;
acquiring gait data, training the pre-constructed neural network model based on the gait data to obtain a primary training model:
wherein i represents a degree of freedom, and takes the value of 1, 2 or 3; p and q represent a positive integer randomly selected from 1 to 10, and 0 is selected when the two formula corner marks have no corresponding physical meanings;
and carrying out deep learning on the experience data by using the primary training model, wherein the learning result is used for carrying out Hopfield network training to obtain a secondary training model.
Preferably, training the gait balance comprises:
obtaining gait data of at least one second biped robot:
and carrying out deep learning on the gait data of each second biped robot by using the two-stage training model of the first biped robot, summarizing the learning results, and using the final learning result for sparse self-encoder training to obtain the three-stage training model of the first biped robot.
Preferably, the adjusting according to the balancing result comprises: gait data of the first biped robot is input into the three-level training model for differential training, and the obtained four-level training model outputs action settings of each degree of freedom of the biped, the ankle joint and the knee joint of the first biped robot.
Preferably, the first-level training model is selected by using a random selection mode in a monte carlo search tree optimization algorithm.
Preferably, the empirical data is gait data from the first biped robot or the second biped robot when the robot has previously passed through a route having the greatest similarity to the route information.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (9)
1. A robot walking simulation algorithm is characterized by comprising the following steps of simulating on a computer: establishing a neural network model based on the neural cell layer, training by using gait data of the first biped robot obtained by the gait measuring device, and training the gait balance of the first biped robot; and adjusting according to the balance result.
2. The robot walking simulation algorithm of claim 1, wherein the feet, ankles and knees of the robot are all three degrees of freedom.
3. The robot walking simulation algorithm of claim 1, wherein the gait data includes angular velocities and accelerations, which are angular velocities and accelerations of a forward direction.
4. The robot walking simulation algorithm of claim 1, wherein the gait measurement device includes a gyroscope and an accelerometer.
5. The robot walking simulation algorithm of claim 1, wherein the training of gait data comprises:
obtaining road surface information data, wherein the road surface information data at least comprises route information and experience data which are in a communication relation with the current position in an electronic map;
acquiring gait data, training the pre-constructed neural network model based on the gait data to obtain a primary training model:
wherein p and q represent a positive integer randomly selected between 1 and 10, and 0 is taken when the two formula indices have no corresponding physical meaning;
and carrying out deep learning on the experience data by using the primary training model, wherein the learning result is used for carrying out Hopfield network training to obtain a secondary training model.
6. The robot walking simulation algorithm of claim 5, wherein training gait balance comprises:
obtaining gait data of at least one second biped robot;
and carrying out deep learning on the gait data of each second biped robot by using the two-stage training model of the first biped robot, summarizing the learning results, and using the final learning result for sparse self-encoder training to obtain the three-stage training model of the first biped robot.
7. The robot walking simulation algorithm of claim 6, wherein adjusting according to the balancing result comprises: gait data of the first biped robot is input into the three-level training model for differential training, and the obtained four-level training model outputs action settings of each degree of freedom of the biped, the ankle joint and the knee joint of the first biped robot.
8. The robot walking simulation algorithm of claim 7, wherein the primary training model is selected using a random selection in a monte carlo search tree optimization algorithm.
9. The robot walking simulation algorithm of claim 8, wherein the empirical data is gait data from the first biped robot or the second biped robot when it has previously passed through a route having the greatest similarity to the route information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011579027.2A CN114684293B (en) | 2020-12-28 | 2020-12-28 | Robot walking simulation algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011579027.2A CN114684293B (en) | 2020-12-28 | 2020-12-28 | Robot walking simulation algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114684293A true CN114684293A (en) | 2022-07-01 |
| CN114684293B CN114684293B (en) | 2023-07-25 |
Family
ID=82130043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011579027.2A Active CN114684293B (en) | 2020-12-28 | 2020-12-28 | Robot walking simulation algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114684293B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100093834A (en) * | 2009-02-17 | 2010-08-26 | 동아대학교 산학협력단 | Method for generating optimal trajectory of a biped robot for walking up a staircase |
| CN104238562A (en) * | 2013-06-13 | 2014-12-24 | 通用汽车环球科技运作有限责任公司 | Method and Apparatus for Controlling a Robotic Device via Wearable Sensors |
| KR20170074539A (en) * | 2015-12-22 | 2017-06-30 | 한국항공대학교산학협력단 | Unmanned aerial vehicle flight control system and method using deep learning |
| WO2018053187A1 (en) * | 2016-09-15 | 2018-03-22 | Google Inc. | Deep reinforcement learning for robotic manipulation |
| CN108983804A (en) * | 2018-08-27 | 2018-12-11 | 燕山大学 | A kind of biped robot's gait planning method based on deeply study |
| US20190204848A1 (en) * | 2017-12-29 | 2019-07-04 | Ubtech Robotics Corp | Gait control method, device, and terminal device for biped robot |
| CN109968355A (en) * | 2019-03-08 | 2019-07-05 | 北京工业大学 | A kind of method that humanoid robot gait's balance model is established |
| CN110262511A (en) * | 2019-07-12 | 2019-09-20 | 同济人工智能研究院(苏州)有限公司 | Biped robot's adaptivity ambulation control method based on deeply study |
| WO2019209681A1 (en) * | 2018-04-22 | 2019-10-31 | Google Llc | Systems and methods for learning agile locomotion for multiped robots |
| CN111546349A (en) * | 2020-06-28 | 2020-08-18 | 常州工学院 | New deep reinforcement learning method for humanoid robot gait planning |
-
2020
- 2020-12-28 CN CN202011579027.2A patent/CN114684293B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100093834A (en) * | 2009-02-17 | 2010-08-26 | 동아대학교 산학협력단 | Method for generating optimal trajectory of a biped robot for walking up a staircase |
| CN104238562A (en) * | 2013-06-13 | 2014-12-24 | 通用汽车环球科技运作有限责任公司 | Method and Apparatus for Controlling a Robotic Device via Wearable Sensors |
| KR20170074539A (en) * | 2015-12-22 | 2017-06-30 | 한국항공대학교산학협력단 | Unmanned aerial vehicle flight control system and method using deep learning |
| WO2018053187A1 (en) * | 2016-09-15 | 2018-03-22 | Google Inc. | Deep reinforcement learning for robotic manipulation |
| US20190204848A1 (en) * | 2017-12-29 | 2019-07-04 | Ubtech Robotics Corp | Gait control method, device, and terminal device for biped robot |
| WO2019209681A1 (en) * | 2018-04-22 | 2019-10-31 | Google Llc | Systems and methods for learning agile locomotion for multiped robots |
| CN108983804A (en) * | 2018-08-27 | 2018-12-11 | 燕山大学 | A kind of biped robot's gait planning method based on deeply study |
| CN109968355A (en) * | 2019-03-08 | 2019-07-05 | 北京工业大学 | A kind of method that humanoid robot gait's balance model is established |
| CN110262511A (en) * | 2019-07-12 | 2019-09-20 | 同济人工智能研究院(苏州)有限公司 | Biped robot's adaptivity ambulation control method based on deeply study |
| CN111546349A (en) * | 2020-06-28 | 2020-08-18 | 常州工学院 | New deep reinforcement learning method for humanoid robot gait planning |
Non-Patent Citations (2)
| Title |
|---|
| 夏泽洋: "仿人机器人运动规划研究进展", 高技术通讯，第17卷第10期, pages 1092 - 1099 * |
| 王立权;俞志伟: "基于ADAMS的双足机器人拟人行走动态仿真", 计算机仿真, vol. 26, no. 3, pages 160 - 182 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114684293B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Farley et al. | How to pick a mobile robot simulator: A quantitative comparison of CoppeliaSim, Gazebo, MORSE and Webots with a focus on accuracy of motion | |
| Khusainov et al. | Toward a human-like locomotion: modelling dynamically stable locomotion of an anthropomorphic robot in simulink environment | |
| Vundavilli et al. | Dynamically balanced optimal gaits of a ditch-crossing biped robot | |
| Wu et al. | Posture self-stabilizer of a biped robot based on training platform and reinforcement learning | |
| Gamus et al. | Dynamic bipedal walking under stick-slip transitions | |
| Seven et al. | Bipedal robot walking control on inclined planes by fuzzy reference trajectory modification | |
| US20220324109A1 (en) | Method and apparatus for controlling multi-legged robot, and storage medium | |
| CN107016411B (en) | Data processing method and device | |
| Xu et al. | Research on kinematics and stability of a bionic wall‐climbing hexapod robot | |
| CN114684293A (en) | Robot walking simulation algorithm | |
| Lee et al. | Time-dependent genetic algorithm and its application to quadruped’s locomotion | |
| CN112698656B (en) | Gait stability control method for biped robot | |
| Yue et al. | Simulation for senior undergraduate education of robot engineering based on Webots | |
| Clever et al. | A new template model for optimization studies of human walking on different terrains | |
| Moslemi et al. | Optimizing vertical jumping height of single-legged robots with passive TOE joints using the genetic algorithm | |
| Hwang et al. | Biped Balance Control by Reinforcement Learning. | |
| CN114690788A (en) | Robot gait optimization method | |
| Ferreira et al. | Human-like gait adaptation to slippery surfaces for the nao robot wearing instrumented shoes | |
| Tarokh et al. | Systematic method for kinematics modeling of legged robots on uneven terrain | |
| Yu et al. | Walking simulation of biped robot on inclined plane based on gait recognition | |
| Tarokh et al. | Kinematics modeling of multi-legged robots walking on rough terrain | |
| KR101310276B1 (en) | Method and system for dynamic simulation of articulated rigid body | |
| Fu et al. | Dynamic stability analyzes for a parallel–serial legged quadruped robot | |
| Suzuki et al. | Passive walking towards running | |
| Lathan et al. | Analytical approach for generating dynamically balanced gaits for obstacle crossing biped robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |