CN110262481B - Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system - Google Patents

Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system Download PDF

Info

Publication number
CN110262481B
CN110262481B CN201910483252.7A CN201910483252A CN110262481B CN 110262481 B CN110262481 B CN 110262481B CN 201910483252 A CN201910483252 A CN 201910483252A CN 110262481 B CN110262481 B CN 110262481B
Authority
CN
China
Prior art keywords
obstacle avoidance
numerical value
mobile robot
robot
control 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.)
Expired - Fee Related
Application number
CN201910483252.7A
Other languages
Chinese (zh)
Other versions
CN110262481A (en
Inventor
荣海娜
张葛祥
黄振
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest Jiaotong University
Original Assignee
Southwest Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southwest Jiaotong University filed Critical Southwest Jiaotong University
Priority to CN201910483252.7A priority Critical patent/CN110262481B/en
Publication of CN110262481A publication Critical patent/CN110262481A/en
Application granted granted Critical
Publication of CN110262481B publication Critical patent/CN110262481B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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

Abstract

The invention discloses a mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system, relates to the technical field of intelligent robots and control, and comprises the steps of obtaining and processing local environment information and designing an obstacle avoidance behavior enzyme numerical value membrane control system. The invention has the beneficial effects that: according to the mobile robot obstacle avoidance control method based on the enzyme numerical value membrane system, local environment information is obtained, n distance sensors around the mobile robot are used for obtaining distance values xi between an obstacle and corresponding sensors, xi is subjected to linear transformation, the obtained sensor values si are multiplied by weights and accumulated, the cruising speed is calculated, and the speed of left and right wheels is calculated, so that the control method is combined with the information of the plurality of sensors, the weighing value of the distance between the whole environment obstacle and the robot is obtained, the calculation cost of the robot for identifying the environment is reduced, the cruising speed of the robot is changed along with the self-adaption of the distance between the whole environment obstacle and the robot, and the obstacle avoidance effect is improved.

Description

Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system
Technical Field
The invention relates to the technical field of intelligent robots and control, in particular to a mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system.
Background
Buiu of the natural computing team of Romani Bulgaster university originally proposes that a membrane system is used for robot control, and the basic idea is to design a mobile robot cognition and behavior controller by utilizing the characteristics (regional parallel computing capability and regional internal information exchange) of the membrane system, wherein the controller is called a membrane controller, and the controller is applied to mobile robot behavior control by utilizing the characteristic that a numerical membrane system can carry out numerical computation, so that the barrier avoidance behavior, the wall following behavior and the behavior following film controller of a robot are realized.
The existing mobile robot obstacle avoidance control method based on the enzyme numerical value membrane system has the condition that the cruising speed parameter is fixed, and the obstacle avoidance effect and the advancing speed of the mobile robot cannot be considered at the same time.
Disclosure of Invention
The invention aims to provide a mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system, and solves the problems that the cruise speed parameter is fixed, and the obstacle avoidance effect and the advancing speed of the mobile robot cannot be considered simultaneously in the mobile robot obstacle avoidance control method based on the enzyme numerical value membrane system in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system comprises the steps of obtaining and processing local environment information and designing an obstacle avoidance behavior enzyme numerical value membrane control system.
Optionally, the specific steps of acquiring and processing the local environment information are as follows:
1) obtaining local environment information as input
Obtaining distance values x between obstacles and corresponding sensors by using n distance sensors around the mobile roboti；
2) For xiPerforming a linear transformation
By the following formula for xiPerforming a linear transformation, wherein siThe sensor value after linear transformation is M, and the maximum detection distance of the sensor is M.
si＝-xi+M
Optionally, the specific steps of designing the obstacle avoidance behavior enzyme numerical value film control system are as follows:
the following functions are realized through an enzyme numerical value membrane system, so that the obstacle avoidance speed calculation is realized.
1) Sensor value siMultiplied by the weight and accumulated
For each sensor value siWeight variable weight left is establishedi、weightRightiAnd wi. The sensor values are multiplied by the weights and accumulated, and the results are stored in variables SWL, SWR, SW, respectively. I.e. SWL ═ Σis*
Figure GDA0002951645910000021
SWR＝∑si*weightRighti、SW＝∑si*wi；
2) Cruisesespeed calculated cruise speed
The cruise speed is calculated using the following equation. Wherein, C0For setting speed, when there is no obstacle, C0(ii) cruiseed; a is base number (0)<a<1) The smaller the value of a is, the larger the CruiseSpeed decline amplitude is;
CruiseSpeed＝C0*aSW
3) calculating left and right wheel speeds leftSpeed and rightSpeed as outputs, calculating left and right wheel speeds using the following formula, using the calculated left and right wheel speeds as outputs for two-wheel control of the mobile robot,
leftSpeed＝CruiseSpeed+SWL
rightSpeed＝CruiseSpeed+SWR
4) and jumping to obtain local environment information as input until the robot finishes a motion task.
The invention provides a mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system, which has the following beneficial effects: obtaining the distance value x between the obstacle and the corresponding sensor by acquiring the local environment information and using n distance sensors around the mobile robotiAnd to xiLinear transformation to obtain sensor siMultiplying the weight value, accumulating, calculating the cruising speed and calculating the speed of the left wheel and the right wheel, so that the control method integrates information of a plurality of sensors to obtain a constant value of the distance between the whole environmental barrier and the robot, reduces the calculation cost of the environment recognition of the robot, is convenient for the cruising speed of the robot to change along with the self-adaption of the distance between the whole environmental barrier and the robot, improves the obstacle avoidance effect, and simultaneously, the control method has the advantages of being capable of achieving the aim of solving the problem of the obstacle avoidance effect and achievingThe method is convenient for the calculation efficiency of the obstacle avoidance left and right wheel speeds of the robot through the parallelism of the enzyme numerical value membrane system.
Drawings
FIG. 1 is a schematic diagram of a Pioneer3-DX sonar distribution of a mobile robot obstacle avoidance control method based on an enzyme numerical membrane system;
FIG. 2 is a schematic diagram of a simulation experiment environment of the mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system of the present invention;
fig. 3 is a schematic diagram of an obstacle avoidance control concept of the obstacle avoidance control method for the mobile robot based on the enzyme numerical value membrane system of the present invention;
fig. 4 is a schematic diagram of an enzyme numerical film system of an obstacle avoidance behavior of the mobile robot obstacle avoidance control method based on the enzyme numerical film system of the present invention;
fig. 5 is a schematic diagram of a simulation experiment of the fixed cruise speed obstacle avoidance control method based on the enzyme numerical value membrane system of the mobile robot obstacle avoidance control method based on the enzyme numerical value membrane system of the present invention;
fig. 6 is a schematic diagram of a simulation experiment of the mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system.
Detailed Description
Membrane computing (or membrane system) is a new branch of natural computing, originally introduced in 1998 by the institute of Romania scientific institute, European academy of sciences, the institute of International mathematics and chemistry, Gheerghe P, and official papers published in 2000. Membrane calculations have received attention from a number of scholars since their introduction. Because the membrane system has the same computing power as a turing machine and has the characteristics of parallelism and distributivity, the design of the robot controller by utilizing the membrane system is beneficial to improving the computing efficiency of the controller.
Referring to fig. 1-6, the present invention provides a technical solution: a mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system comprises the steps of obtaining and processing local environment information and designing an obstacle avoidance behavior enzyme numerical value membrane control system.
Further, the specific steps of acquiring and processing the local environment information are as follows:
1) obtaining local environment information as input
Obtaining distance values x between obstacles and corresponding sensors by using n distance sensors around the mobile roboti；
2) For xiPerforming a linear transformation
By the following formula for xiPerforming a linear transformation, wherein siThe sensor value after linear transformation is M, and the maximum detection distance of the sensor is M.
si＝-xi+M
Further, the specific steps of designing the obstacle avoidance behavior enzyme numerical value film control system are as follows:
the following functions are realized through an enzyme numerical value membrane system, so that the obstacle avoidance speed calculation is realized.
1) Sensor value siMultiplied by the weight and accumulated
For each sensor value siWeight variable weight left is establishedi、weightRightiAnd wi. The sensor values are multiplied by the weights and accumulated, and the results are stored in variables SWL, SWR, SW, respectively. I.e. SWL ═ Σis*
Figure GDA0002951645910000041
SWR＝∑si*weightRighti、SW＝∑si*wi；
2) Cruisesespeed calculated cruise speed
The cruise speed is calculated using the following equation. Wherein, C0For setting speed, when there is no obstacle, C0(ii) cruiseed; a is base number (0)<a<1) The smaller the value of a is, the larger the CruiseSpeed decline amplitude is;
CruiseSpeed＝C0*aSW
3) calculating left and right wheel speeds leftSpeed and rightSpeed as outputs, calculating left and right wheel speeds using the following formula, using the calculated left and right wheel speeds as outputs for two-wheel control of the mobile robot,
leftSpeed＝CruiseSpeed+SWL
rightSpeed＝CruiseSpeed+SWR
4) and jumping to obtain local environment information as input until the robot finishes a motion task.
Example 1
Referring to fig. 3, the present invention takes the following steps:
acquiring and processing local environment information
Step 1, obtaining local environment information as input
Obtaining the distance value x between the obstacle and the corresponding sensor by using 16 sonar sensors around the mobile roboti。
Step 2, for xiPerforming a linear transformation
By the following formula for xiPerforming a linear transformation, wherein siThe sensor value after linear transformation is M, and the maximum detection distance of the sensor is M. Here, M is 1000mm
si＝-xi+M
Secondly, designing an enzyme numerical value film control system for obstacle avoidance behavior
An enzyme numerical membrane system for obstacle avoidance was designed as shown in fig. 4. The membrane system realizes the following functions through 3 times of iterative calculation, thereby realizing the calculation of the obstacle avoidance speed.
Step 3. sensor siMultiplied by the weight and accumulated
Creating 16 membranes iSensor(i ═ 1, sor add up, per membrane SensoriWith one sensor s inside i Product calculation with weight, i.e. si*weightLefti、si*weightRighti、si*wiE.g. membrane SensoriInternal rules 1, 2, 3. The 16 membranes complete the accumulation of the product of the 16 sensors and the weight, and the result is stored in the variables SWL, SWR, SW. This step is done in the first iteration of the membrane system.
Step 4, calculating cruise speed CruiseSpeed
Creating a cruise speed membrane completes the calculation of the cruise speed, as shown in fig. 4. Rule 1 in the membrane called _ cruise speed completes the cruise speed calculation, and rules 2 and 3 save the results SWL and SWR of the first iteration calculation through variables SWL _ temp and SWR _ temp.
Step 5, calculating left and right wheel speeds leftSpeed and rightSpeed as output
And (3) creating a coordinate _ Speed film to complete the calculation of the barrier-avoiding left and right wheel speeds, as shown in FIG. 4. Rule 1 in the membrane coordinate _ Speed completes the left wheel Speed leftSpeed calculation, and rule 2 completes the right wheel Speed rightSpeed calculation. And the calculation result is output to the mobile robot, so that the double-wheel speed of the robot is controlled, and the obstacle avoidance speed calculation of the one-wheel robot is realized.
And 6, jumping to the step 1 until the robot completes the motion task.
Example 2
From the experimental results of fig. 5 and 6, it can be seen that compared with the fixed cruise speed obstacle avoidance control method, the obstacle avoidance control method of the present invention can better avoid obstacles.
Example 3
The invention performs simulation on the PC. A computer used in a simulation experiment is an associative G4702.3GHz and 6G RAM, an operating system is Window7, a simulation platform is MobileSim, a simulation robot is Pioneer3-DX, and the size of the robot is 52 x 40 cm. The simulation robot is equipped with 16 sonar sensors, which are distributed as shown in fig. 1. The simulated environment is shown in fig. 2, and the environment comprises a channel of 100cm, a channel of 80cm, two obstacles spaced by 60cm, and the like.
To sum up, when the mobile robot obstacle avoidance control method based on the enzyme numerical value membrane system is used, firstly, local environment information is obtained and used as input, and then n distance sensors around the mobile robot are used for obtaining distance values x between obstacles and corresponding sensorsiAnd to xiAnd performing linear transformation, multiplying and accumulating the sensor and the weight, calculating the cruising speed, calculating the speeds of the left wheel and the right wheel to serve as output, judging whether to jump to obtain local environment information by judging whether to complete the motion task, and performing cycle operation again to serve as input until the robot completes the motion task.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.

Claims (1)

1. A mobile robot obstacle avoidance control method based on an enzyme numerical value membrane system comprises the steps of obtaining and processing local environment information and designing an obstacle avoidance behavior enzyme numerical value membrane control system;
the specific steps of the acquisition and processing of the local environment information are as follows:
1) obtaining local environment information as input:
obtaining distance values x between obstacles and corresponding sensors by using n distance sensors around the mobile roboti；
2) For xiPerforming linear transformation:
by the following formula for xiThe linear transformation is carried out, and the linear transformation,
si＝-xi+M；
wherein s isiThe sensor value after linear transformation is obtained, and M is the maximum detection distance of the sensor;
the specific steps of designing the obstacle avoidance behavior enzyme numerical value film control system are as follows:
the following functions are realized through an enzyme numerical value membrane system, so that the obstacle avoidance speed calculation is realized;
1) sensor value siMultiplying and accumulating by the weight:
for each sensor value siWeight variable weight left is establishedi、weightRightiAnd wi(ii) a Multiplying the sensor value by the weight and accumulating, and respectively storing the results in variables SWL, SWR and SW; i.e. SWL ═ Σ si*weightLefti、SWR＝∑si*weightRighti、SW＝∑si*wi；
2) Calculating a cruise speed Cruisesespeed:
calculating a cruise speed using the following equation;
CruiseSpeed＝C0*aSW；
wherein, C0For setting speed, when there is no obstacle, C0(ii) cruiseed; a is base number, 0<a<1, the smaller the value of a, the larger the decrease of CruiseSpeed;
3) calculating left and right wheel speeds leftSpeed, rightSpeed as output:
the left and right wheel speeds are calculated by the following formula, and the calculated left and right wheel speeds are used as output for double-wheel control of the mobile robot,
leftSpeed＝CruiseSpeed+SWL；
rightSpeed＝CruiseSpeed+SWR；
4) and jumping to obtain local environment information as input until the robot finishes a motion task.
CN201910483252.7A 2019-06-04 2019-06-04 Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system Expired - Fee Related CN110262481B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910483252.7A CN110262481B (en) 2019-06-04 2019-06-04 Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910483252.7A CN110262481B (en) 2019-06-04 2019-06-04 Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system

Publications (2)

Publication Number Publication Date
CN110262481A CN110262481A (en) 2019-09-20
CN110262481B true CN110262481B (en) 2021-06-22

Family

ID=67916716

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910483252.7A Expired - Fee Related CN110262481B (en) 2019-06-04 2019-06-04 Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system

Country Status (1)

Country Link
CN (1) CN110262481B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008021612A2 (en) * 2006-07-05 2008-02-21 Battelle Energy Alliance, Llc Autonomous navigation system and method
CN101776863B (en) * 2009-11-17 2011-07-27 中国科学院自动化研究所 Movement control method of pectoral fin impelling type machine fish
CN102313536A (en) * 2011-07-21 2012-01-11 清华大学 Method for barrier perception based on airborne binocular vision
US8355818B2 (en) * 2009-09-03 2013-01-15 Battelle Energy Alliance, Llc Robots, systems, and methods for hazard evaluation and visualization
EP2738637A2 (en) * 2012-11-30 2014-06-04 Samsung Electronics Co., Ltd Cleaning robot and control method thereof
CN205002259U (en) * 2015-08-27 2016-01-27 北京米微环保科技有限公司 Air purifier robot
CN107219850A (en) * 2017-05-25 2017-09-29 深圳众厉电力科技有限公司 A kind of automatic Pathfinding system of robot based on machine vision
CN107438873A (en) * 2017-07-07 2017-12-05 驭势科技（北京）有限公司 A kind of method and apparatus for being used to control vehicle to travel
CN107807669A (en) * 2017-12-01 2018-03-16 西华大学 Control method, device and read/write memory medium based on enzyme numerical value membrane structure
CN108469825A (en) * 2018-04-19 2018-08-31 河南科技学院 A kind of intelligent patrol system and its construction method based on bus or train route collaboration
CN109164812A (en) * 2018-10-23 2019-01-08 西南交通大学 Mobile robot multirow is fusion enzyme numerical value film control method under a kind of circumstances not known
CN109367537A (en) * 2018-12-06 2019-02-22 吉林大学 A kind of electric car adaptive cruise control system and method based on car networking
CN109542099A (en) * 2018-11-26 2019-03-29 江苏农牧科技职业学院 A kind of agricultural machinery control method

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4576445B2 (en) * 2007-04-12 2010-11-10 パナソニック株式会社 Autonomous mobile device and program for autonomous mobile device
JP6776513B2 (en) * 2015-08-19 2020-10-28 ソニー株式会社 Vehicle control device, vehicle control method, information processing device, and traffic information provision system
US10335952B2 (en) * 2017-01-18 2019-07-02 International Business Machines Corporation Monitoring and controlling the movement of mobile robots

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008021612A2 (en) * 2006-07-05 2008-02-21 Battelle Energy Alliance, Llc Autonomous navigation system and method
US8355818B2 (en) * 2009-09-03 2013-01-15 Battelle Energy Alliance, Llc Robots, systems, and methods for hazard evaluation and visualization
CN101776863B (en) * 2009-11-17 2011-07-27 中国科学院自动化研究所 Movement control method of pectoral fin impelling type machine fish
CN102313536A (en) * 2011-07-21 2012-01-11 清华大学 Method for barrier perception based on airborne binocular vision
EP2738637A2 (en) * 2012-11-30 2014-06-04 Samsung Electronics Co., Ltd Cleaning robot and control method thereof
CN205002259U (en) * 2015-08-27 2016-01-27 北京米微环保科技有限公司 Air purifier robot
CN107219850A (en) * 2017-05-25 2017-09-29 深圳众厉电力科技有限公司 A kind of automatic Pathfinding system of robot based on machine vision
CN107438873A (en) * 2017-07-07 2017-12-05 驭势科技（北京）有限公司 A kind of method and apparatus for being used to control vehicle to travel
CN107807669A (en) * 2017-12-01 2018-03-16 西华大学 Control method, device and read/write memory medium based on enzyme numerical value membrane structure
CN108469825A (en) * 2018-04-19 2018-08-31 河南科技学院 A kind of intelligent patrol system and its construction method based on bus or train route collaboration
CN109164812A (en) * 2018-10-23 2019-01-08 西南交通大学 Mobile robot multirow is fusion enzyme numerical value film control method under a kind of circumstances not known
CN109542099A (en) * 2018-11-26 2019-03-29 江苏农牧科技职业学院 A kind of agricultural machinery control method
CN109367537A (en) * 2018-12-06 2019-02-22 吉林大学 A kind of electric car adaptive cruise control system and method based on car networking

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Development of membrane controllers for mobile robots;CatalinBuiu等;《Information Sciences》;20120315;第187卷;第33-51页 *
Real-time area-covering operations with obstacle avoidance for cleaning robots;Chaomin Luo等;《IEEE/RSJ International Conference on Intelligent Robots and Systems》;20021004;第2359-2364页 *
Using enzymatic numerical P systems for modeling mobile robot controllers;Pavel AB等;《Natural Computing》;20121231;第11卷(第3期);第387-393页 *
酶数值膜系统仿真器设计与实现;王争一;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170115(第01(2017)期);第I137-50页 *

Also Published As

Publication number Publication date
CN110262481A (en) 2019-09-20

Similar Documents

Publication Publication Date Title
US11331800B2 (en) Adaptive predictor apparatus and methods
US11488000B2 (en) Operation apparatus and method for acceleration chip for accelerating deep neural network algorithm
TWI759361B (en) An architecture, method, computer-readable medium, and apparatus for sparse neural network acceleration
CN107832844A (en) A kind of information processing method and Related product
US20180018555A1 (en) System and method for building artificial neural network architectures
CN105184362A (en) Depth convolution neural network acceleration and compression method based on parameter quantification
CN112183718A (en) Deep learning training method and device for computing equipment
Hassanzadeh et al. Mobile robot path planning based on shuffled frog leaping optimization algorithm
CN111260072A (en) Reinforced learning exploration method based on generation countermeasure network
CN113580129B (en) Multi-target cooperative capturing method, device and medium based on robot
Gankidi FPGA accelerator architecture for Q-learning and its applications in space exploration rovers
CN110147108B (en) Mobile robot obstacle avoidance control method based on membrane calculation
CN110262481B (en) Mobile robot obstacle avoidance control method based on enzyme numerical value membrane system
Chen et al. Particle swarm optimization based on genetic operators for sensor-weapon-target assignment
CN111091183A (en) Neural network acceleration system and method
Chaojun et al. Research on vehicle detection based on YOLOv3
CN106682733B (en) Unmanned plane motion state analysis method and device
Wichapong et al. Trajectory planning of a 6D robot based on Meta Heuristic algorithms
Suganya et al. Soft computing controller based path planning wheeled mobile robot
CN110389649B (en) Training method and system for environment awareness
CN114691345A (en) Calculation framework suitable for SLAM nonlinear parallelization chip and working method
Kim et al. Design based on a shared lookup-table for an obstacle avoidance fuzzy controller for mobile robots
CN112215338A (en) Neural network computing method and device, electronic equipment and storage medium
Liu et al. Hardware Acceleration of Monte-Carlo Sampling for Energy Efficient Robust Robot Manipulation
CN112561050A (en) Neural network model training method and device

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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210622