Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)network.After obtaining the network,theorems and related proofs are provided to guarantee the exponential ...Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)network.After obtaining the network,theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA network.Then,numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ones.Finally,the GD-k WTA network,backed with a consensus filter,is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination,thereby further demonstrating its effectiveness and feasibility.展开更多
In the RoboSot category, no central station or over head camera is allowed. Therefore several issues such as sensors, mechanisms and CPU boards must be taken into consideration before building an autonomous and intell...In the RoboSot category, no central station or over head camera is allowed. Therefore several issues such as sensors, mechanisms and CPU boards must be taken into consideration before building an autonomous and intelligent system for this category. Each robot must have appropriate sensors and must be able to communicate with other robots to have timely information concerning the ball and robot position in the field. Computing power also becomes and improtant factor in implementing intelligence and autonomy onboard. These issues are discussed. Then the robot structure of the Dreams Come True(DCT) from KAIST is introduced. Each robot has a Pentium Π single board computer, and Ethernet card, and USB camera and an omni directional mobile mechanism.展开更多
Given limited terrain adaptability,most existing multirobot cooperative transportation systems(MRCTSs)mainly work on flat pavements,restricting their outdoor applications.The connectors'finite deformation capabili...Given limited terrain adaptability,most existing multirobot cooperative transportation systems(MRCTSs)mainly work on flat pavements,restricting their outdoor applications.The connectors'finite deformation capability and the control strategies'limitations are primarily responsible for this phenomenon.This study proposes a novel MRCTS based on tracked mobile robots(TMRs)to improve terrain adaptability and expand the application scenarios of MRCTSs.In structure design,we develop a novel 6-degree-of-freedom passive adaptive connector to link multiple TMRs and the transported object(the communal payload).In addition,the connector is set with sensors to measure the position and orientation of the robot with respect to the object for feedback control.In the control strategy,we present a virtual leader-physical follower collaborative paradigm.The leader robot is imaginary to describe the movement of the entire system and manage the follower robots.All the TMRs in the system act as follower robots to transport the object cooperatively.Having divided the whole control structure into the leader robot level and the follower robot level,we convert the motion control of the two kinds of robots to trajectory tracking control problems and propose a novel double closed-loop kinematics control framework.Furthermore,a control law satisfying saturation constraints is derived to ensure transportation stability.An adaptive control algorithm processes the wheelbase uncertainty of the TMR.Finally,we develop a prototype of the TMR-based MRCTS for experiments.In the trajectory tracking experiment,the developed MRCTS with the proposed control scheme can converge to the reference trajectory in the presence of initial tracking errors in a finite time.In the outdoor experiment,the proposed MRCTS consisting of four TMRs can successfully transport a payload weighing 60 kg on an uneven road with the single TMR's maximum load limited to 15 kg.The experimental results demonstrate the effectiveness of the structural design and control strategies of展开更多
This paper addresses the problem of coordinating multiple mobile robots in searching for and capturing a mobile target,with the aim of reducing the capture time.Compared with the previous algorithms,we assume that the...This paper addresses the problem of coordinating multiple mobile robots in searching for and capturing a mobile target,with the aim of reducing the capture time.Compared with the previous algorithms,we assume that the target can be detected by any robot and captured successfully by two or more robots.In this paper,we assume that each robot has a limited communication range.We maintain the robots within a mobile network to guarantee the successful capture.In addition,the motion of the target is modeled and incorporated into directing the motion of the robots to reduce the capture time.A coordination algorithm considering both aspects is proposed.This algorithm can greatly reduce the expected time of capturing the mobile target.Finally,we validate the algorithm by the simulations and experiments.展开更多
A spatial orthogonal allocation method is devised for multirobot tasks allocation.A 3D space model is adopted to describe exploration mission;meanwhile spatial orthogonal tentative technology is utilized to update the...A spatial orthogonal allocation method is devised for multirobot tasks allocation.A 3D space model is adopted to describe exploration mission;meanwhile spatial orthogonal tentative technology is utilized to update the attractor position for load balance.Heterogeneous interactive cultural hybrid architecture is proposed to solve a robot route planning problem;it utilizes good-point-set to initialize population spaces,redefine novel evolution model and particle evolution ability,and introduce near-neighbor local search strategy in order to enhance search capability.Finally,spatial orthogonal allocation and heterogeneous cultural hybrid algorithm (SOAHCHA) are verified by simulation analysis and MORCS2 planning experiments;those results show that the proposed algorithm is efficient because of its successful performance and balanced allocation.展开更多
The layered control architecture is designed for the need of the multirobot intelligent team formation.There are three levels:the cooperation task level,the coordination behavior level and the action planning level.Th...The layered control architecture is designed for the need of the multirobot intelligent team formation.There are three levels:the cooperation task level,the coordination behavior level and the action planning level.The cooperation task level uses the potential grid method,which improves the safety of the path and reduces the calculation complexity.The coordination behavior level uses the reinforcement learning which can strengthen the robots’ intelligence.The action planning level uses the fuzzy planning methods to realize the action matching.The communication model transfers the message in different level.This architecture shows not only the independence and the intelligence of the single robot but also the cooperation and the coordination among the robots.In each level,the task is distributed reasonably and clearly.Finally the feasibility of the architecture is verified further in the simulation of the experiment.The expansibility of the architecture is good and the architecture can be used in the similar system.展开更多
基金supported in part by the National Natural Science Foundation of China(62176109)the Natural Science Foundation of Gansu Province(21JR7RA531)+6 种基金the Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province(2021-Z-003)the CAS“Light of West China”Programthe Natural Science Foundation of Chongqing(China)(cstc2020jcyjzdxm X0028)the Chongqing Entrepreneurship and Innovation Support Program for Overseas Returnees(CX2021100)the Supercomputing Center of Lanzhou Universitythe Science and Technology Project of Chengguan District of Lanzhou(2021JSCX0014)the Education Department of Gansu Province:Excellent Graduate Student“Innovation Star”Project(2021CXZX-122)。
文摘Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)network.After obtaining the network,theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA network.Then,numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ones.Finally,the GD-k WTA network,backed with a consensus filter,is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination,thereby further demonstrating its effectiveness and feasibility.
文摘In the RoboSot category, no central station or over head camera is allowed. Therefore several issues such as sensors, mechanisms and CPU boards must be taken into consideration before building an autonomous and intelligent system for this category. Each robot must have appropriate sensors and must be able to communicate with other robots to have timely information concerning the ball and robot position in the field. Computing power also becomes and improtant factor in implementing intelligence and autonomy onboard. These issues are discussed. Then the robot structure of the Dreams Come True(DCT) from KAIST is introduced. Each robot has a Pentium Π single board computer, and Ethernet card, and USB camera and an omni directional mobile mechanism.
基金supported by the National Natural Science Foundation of China(Grant No.52175237)Beijing Municipal Science and Technology Commission,China(Grant No.Z211100004021022).
文摘Given limited terrain adaptability,most existing multirobot cooperative transportation systems(MRCTSs)mainly work on flat pavements,restricting their outdoor applications.The connectors'finite deformation capability and the control strategies'limitations are primarily responsible for this phenomenon.This study proposes a novel MRCTS based on tracked mobile robots(TMRs)to improve terrain adaptability and expand the application scenarios of MRCTSs.In structure design,we develop a novel 6-degree-of-freedom passive adaptive connector to link multiple TMRs and the transported object(the communal payload).In addition,the connector is set with sensors to measure the position and orientation of the robot with respect to the object for feedback control.In the control strategy,we present a virtual leader-physical follower collaborative paradigm.The leader robot is imaginary to describe the movement of the entire system and manage the follower robots.All the TMRs in the system act as follower robots to transport the object cooperatively.Having divided the whole control structure into the leader robot level and the follower robot level,we convert the motion control of the two kinds of robots to trajectory tracking control problems and propose a novel double closed-loop kinematics control framework.Furthermore,a control law satisfying saturation constraints is derived to ensure transportation stability.An adaptive control algorithm processes the wheelbase uncertainty of the TMR.Finally,we develop a prototype of the TMR-based MRCTS for experiments.In the trajectory tracking experiment,the developed MRCTS with the proposed control scheme can converge to the reference trajectory in the presence of initial tracking errors in a finite time.In the outdoor experiment,the proposed MRCTS consisting of four TMRs can successfully transport a payload weighing 60 kg on an uneven road with the single TMR's maximum load limited to 15 kg.The experimental results demonstrate the effectiveness of the structural design and control strategies of
基金supported by the National Natural Science Foundation of China(No.60434030)
文摘This paper addresses the problem of coordinating multiple mobile robots in searching for and capturing a mobile target,with the aim of reducing the capture time.Compared with the previous algorithms,we assume that the target can be detected by any robot and captured successfully by two or more robots.In this paper,we assume that each robot has a limited communication range.We maintain the robots within a mobile network to guarantee the successful capture.In addition,the motion of the target is modeled and incorporated into directing the motion of the robots to reduce the capture time.A coordination algorithm considering both aspects is proposed.This algorithm can greatly reduce the expected time of capturing the mobile target.Finally,we validate the algorithm by the simulations and experiments.
基金supported by the National Natural Science Foundation of China (No. 90820302)the Research Fund for the Doctoral Program of Higher Education (No. 200805330005)+1 种基金Hunan S & T Funds (No. 06IJY3035)the Postdoctoral Science Foundation of Central South University
文摘A spatial orthogonal allocation method is devised for multirobot tasks allocation.A 3D space model is adopted to describe exploration mission;meanwhile spatial orthogonal tentative technology is utilized to update the attractor position for load balance.Heterogeneous interactive cultural hybrid architecture is proposed to solve a robot route planning problem;it utilizes good-point-set to initialize population spaces,redefine novel evolution model and particle evolution ability,and introduce near-neighbor local search strategy in order to enhance search capability.Finally,spatial orthogonal allocation and heterogeneous cultural hybrid algorithm (SOAHCHA) are verified by simulation analysis and MORCS2 planning experiments;those results show that the proposed algorithm is efficient because of its successful performance and balanced allocation.
基金Sponsored by the Scientific Research Foundation of Beijing Normal University and the Grants from the National Postdocteral Foundation of China.
文摘The layered control architecture is designed for the need of the multirobot intelligent team formation.There are three levels:the cooperation task level,the coordination behavior level and the action planning level.The cooperation task level uses the potential grid method,which improves the safety of the path and reduces the calculation complexity.The coordination behavior level uses the reinforcement learning which can strengthen the robots’ intelligence.The action planning level uses the fuzzy planning methods to realize the action matching.The communication model transfers the message in different level.This architecture shows not only the independence and the intelligence of the single robot but also the cooperation and the coordination among the robots.In each level,the task is distributed reasonably and clearly.Finally the feasibility of the architecture is verified further in the simulation of the experiment.The expansibility of the architecture is good and the architecture can be used in the similar system.
