This paper presents a type of machine learning is reinforcement learning, this approach is often used in the field of robotics. It aims to determine a control law for a mobile robot in an unknown environment. This kin...
详细信息
This paper presents a type of machine learning is reinforcement learning, this approach is often used in the field of robotics. It aims to determine a control law for a mobile robot in an unknown environment. This kind of technique applies when one assumes that the only information on the quality of actions performed by the mobile robot is a scalar signal which has a reward or punishment, the process of learning is to improve the choice of actions to maximize rewards. One of the most used algorithms for solving this problem is learning the Q-learning algorithm which is based on the Qfunction, and to ensure the generation of this latter function and the proper functioning of the apprenticeship system using an artificial neural network as the statements of changing environments where mobile robots have wide open spaces, the action performed by the mobile robot in its environment is ensured by using a selection function, this action is evaluated by a scalar signal which is -1, 0 and 1.
The proceedings contain 128 papers. The topics discussed include: a ubiquitous and cooperative service framework for network robot system;the hand-bot, a robot design for simultaneous climbing and manipulation;human m...
ISBN:
(纸本)3642108164
The proceedings contain 128 papers. The topics discussed include: a ubiquitous and cooperative service framework for network robot system;the hand-bot, a robot design for simultaneous climbing and manipulation;human multi-robots interaction with high virtual reality abstraction level;laser based people following behavior in an emergency environment;classifying 3D human motions by mixing fuzzy Gaussian inference with genetic programming;pointing gestures for a robot mediated communication interface;emergent behavior control patterns in robotic collectives;an improved road network modeling and map matching for precise vehicle localization;stereovision-based algorithm for obstacle avoidance;dynamic mechanism and key rectification techniques of shield machine in the vertical plane;and identification of abnormal operating conditions and intelligent decision system for earth pressure balance shield machine.
In this paper the problem of the autonomous navigation of a cooperative robot formation is studied. robots navigate in an unknown environment, encumbered by obstacles which have a circular shape or which can be modele...
详细信息
ISBN:
(纸本)9783642108167
In this paper the problem of the autonomous navigation of a cooperative robot formation is studied. robots navigate in an unknown environment, encumbered by obstacles which have a circular shape or which can be modeled by polygons. robots must move between an initial known position and a final known position. While going ahead robots discover the obstacles which block their passage and must avoid the collision and go to their final destination. This paper tackles two problems: 1. path planning, which is described as an optimal control problem under constraints (robot physical limits, collision avoidance). 2. localization, in order to plan its trajectory, the robot has to know its localization in the environment : a mono-landmark algorithm of localization in 2D is proposed. This mono-landmark algorithm tracks a landmark during the navigation and uses it to localize the robot in an algebraic framework.
Due to increased terrors and crimes, the use of the surveillance system like CCTV is increasing. The surveillance system has been operated for public interest such as prevention of crimes and fly-tipping by the police...
详细信息
In recent times, the chances of robot-human contact have increased;hence, safety is necessitated with regard to such contact. Thus, manipulators using a pneumatic rubber artificial muscle, which is lightweight and fle...
详细信息
ISBN:
(纸本)9783642108167
In recent times, the chances of robot-human contact have increased;hence, safety is necessitated with regard to such contact. Thus, manipulators using a pneumatic rubber artificial muscle, which is lightweight and flexible, are studied. However, this artificial muscle manipulator has faults such as slow response and limited instantaneous power due to operation by air pressure. Because of these faults, uncontrollable vibrations can occur, leading to instability in the arm when an object is held and lifted. In this study, an artificial muscle manipulator with 1 DOF and a variable rheological joint mechanism using MR fluid is developed. Vibration control of the arm using MR fluid is realized when an object is held and lifted, confirming the reduction in vibration due to the MR effect.
A distributed simulation environment is introduced in this paper that allows to simulate robot swarms as well as modular robots. This simulator is in use within the European projects 'SYMBRION' and 'REPLIC...
详细信息
ISBN:
(纸本)9783642108167
A distributed simulation environment is introduced in this paper that allows to simulate robot swarms as well as modular robots. This simulator is in use within the European projects 'SYMBRION' and 'REPLICATOR'. The project's main goal is to build robots that can aggregate to multi-robot organisms. These robots will be able to act individually, as a swarm or within an organism. The simulator needs to be able to simulate all of these behaviors. As the number of robots can be large, both in the swarm as well as in the organism, the simulator needs to be distributed on several computers. As the demand varies between the different behaviors swarm and organism behavior the behavior of the simulator needs to vary as well, e.g. for a swarm, a dynamic simulation is not necessary, whereas for an organism, a fast dynamic simulation is obligatory. We are therefore developing the Symbricator3D simulation environment, that will fulfill all the described requirements.
This paper presents a fully parameterised and highly scalable design prototype of FPGA (field programmable gate array) implementation of a biologically inspired auditory signal processing system. The system has been c...
详细信息
ISBN:
(纸本)9789898111654
This paper presents a fully parameterised and highly scalable design prototype of FPGA (field programmable gate array) implementation of a biologically inspired auditory signal processing system. The system has been captured and simulated using system-level integrated design tools, namely, System Generator (TM) and AccelDSP (TM) both from Xilinx (TM). The implemented hardware auditory periphery model consists of two sub-models-the Patterson's Gammatone filter bank and the Meddis' inner hair cell. The prototype has been successfully ported onto a Virtex (TM)-II Pro FPGA. Ultimately, it can be used as a front-end apparatus in a variety of embedded auditory signal processing applications.
A novel concept called gesture-changeable under-actuated (GCUA) function is proposed to improve the dexterities of traditional under-actuated hands and reduce the control difficulties of dexterous hands. Based on the ...
详细信息
ISBN:
(纸本)9783642108167
A novel concept called gesture-changeable under-actuated (GCUA) function is proposed to improve the dexterities of traditional under-actuated hands and reduce the control difficulties of dexterous hands. Based on the GCUA function, a new humanoid robot hand, GCUA Hand is designed and manufactured. The GCUA Hand can grasp different objects self-adaptively and change its initial gesture dexterously before contacting objects. The hand has 5 fingers and 15 DOFs, each finger is based on screw-nut transmission, flexible drawstring constraint and belt-pulley under-actuated mechanism to realize GCUA function. The analyses on grasping static forces and grasping stabilities are put forward. The analyses and Experimental results show that the GCUA function is very nice and valid. The hands with the GCUA function can meet the requirements of grasping and operating with lower control and cost, which is the middle road between traditional under-actuated hands and dexterous hands.
A hybrid functional electrical stimulation (FES) rehabilitation system for locomotion is proposed in this paper. It has a hierarchical structure. In upper level, brain-computer technology (BCI) is used to acquire the ...
详细信息
ISBN:
(纸本)9783642108167
A hybrid functional electrical stimulation (FES) rehabilitation system for locomotion is proposed in this paper. It has a hierarchical structure. In upper level, brain-computer technology (BCI) is used to acquire the subject's intention. In middle level, central pattern generator (CPG) is designed to generate appropriate rhythmic motor patterns. CPG is triggered by BCI command, and sendcontrol patterns to lower level. In lower level, FES technique is used to activate the muscles, and drive the lower limbs to achieve the expected movements (i.e. locomotion). The whole system is developed according to the general nervous structure of human being. The hybrid system aims at developing a neuroprosthetic bridge for the impaired nervous system of paralyzed patients. Some preliminary results on BCI are given.
Node localization is an important problem for location-dependent applications of wireless sensor networks. Aiming at the positioning problem of wireless sensor networks node location, an improved DV-Hop localization a...
详细信息
ISBN:
(纸本)9780769538044
Node localization is an important problem for location-dependent applications of wireless sensor networks. Aiming at the positioning problem of wireless sensor networks node location, an improved DV-Hop localization algorithm is proposed in this paper. The proposed method firstly recalculates the hop-size and sends different correction along different directions instead of computing a single correction to be broadcasted into the networks. Then we empirically evaluate the difference between distance estimate and actual distance through a number of simulation experiments statistical results. We find empirical parameter to improve the accuracy of distance estimate. Simulation results show that the performance of the proposed scheme outweighs classical DV-Hop algorithms, especially in lower connectivity.
暂无评论