In order to meet the application requirements of autonomous vehicles, this paper proposes a simultaneous localization and mapping (SLAM) algorithm, which uses a VoxelGrid filter to down sample the point cloud data, ...
详细信息
In order to meet the application requirements of autonomous vehicles, this paper proposes a simultaneous localization and mapping (SLAM) algorithm, which uses a VoxelGrid filter to down sample the point cloud data, with the combination of iterative closest points (ICP) algorithm and Gaussian model for particles updating, the matching between the local map and the global map to quantify particles' importance weight. The crude estimation by using ICP algorithm can find the high probability area of autonomous vehicles' poses, which would decrease particle numbers, increase algorithm speed and restrain particles' impoverishment. The calculation of particles' importance weight based on matching of attribute between grid maps is simple and practicable. Experiments carried out with the autonomous vehicle platform validate the effectiveness of our approaches.
A plant-friendly proportional-integral-derivative (PID) controller optimization framework is proposed to make tradeoffs among set-point response,controller output variations and *** objective function is chosen as t...
详细信息
A plant-friendly proportional-integral-derivative (PID) controller optimization framework is proposed to make tradeoffs among set-point response,controller output variations and *** objective function is chosen as the weighted sum of the integral of squared time-weighted error and the integral of squared timeweighted derivative of the control variable with respect to set-point response,while the robustness of the system is guaranteed by constraints on gain and phase *** to the complex structure of the constraints,the problem is solved by genetic *** analysis show the proposed method could efficiently reduce the controller output variations while maintaining a short settling *** on the simulation results,iterative tuning rules for the weighting factor in the objective function are obtained,which allows efficient simple proportional-integral(PI) tuning formulae to be derived.
Complicated nonlinear intensity differences, nonlinear local geometric distortions, noises and rotation transformation are main challenges in multimodal image matching. In order to solve these problems, we propose a m...
详细信息
This paper presents an interactive motion control method based on reinforcement learning, designed to assist children with autism who have social motor impairments through a mirror game intervention. The virtual teach...
详细信息
ISBN:
(数字)9798331521950
ISBN:
(纸本)9798331521967
This paper presents an interactive motion control method based on reinforcement learning, designed to assist children with autism who have social motor impairments through a mirror game intervention. The virtual teacher uses the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize its actions, guiding the participant to follow a Lissajous trajectory. To ensure safety, a motion-correction mechanism was developed, which automatically adjusts actions when the predicted trajectory surpasses predefined safety boundaries. The reward function considers both the distance between the virtual teacher and the target trajectory, as well as the distance between the virtual teacher and the participant, with dynamic adjustments applied by the motion-correction mechanism. Experimental results demonstrate that the virtual teacher effectively guides the participant towards the target trajectory while adhering to safety constraints.
Force reflection methods are widely used in teleoperation with force sensors on slave manipulator. However, force sensors would impair manipulator structure and may be installed or maintained difficultly on slave site...
详细信息
ISBN:
(纸本)9781467374439
Force reflection methods are widely used in teleoperation with force sensors on slave manipulator. However, force sensors would impair manipulator structure and may be installed or maintained difficultly on slave site. Additionally, in some tasks operator pays more attention to control the exerted force on environment than to fell the reflection force. Considering these factors, a force sending method is proposed in this paper with force sensors installed only on master manipulator. Adjusted virtual force is provided to operator on master site. Operator force sending and slave manipulator position tracking are achieved without conflict on slave site. Stability analysis is presented based on ISS(input-to-state stability) method and numerical simulations are given to show the effectiveness.
This paper presents the problem of optimal distributed weighted Kalman filter fusion for a class of multi-sensor unreliable networked systems with uncorrelated *** distributed multi-sensor data fusion system suffers m...
详细信息
ISBN:
(纸本)9781509009107
This paper presents the problem of optimal distributed weighted Kalman filter fusion for a class of multi-sensor unreliable networked systems with uncorrelated *** distributed multi-sensor data fusion system suffers measurements delay or loss due to unreliability of networked systems with uncorrelated *** the addressed model,an optimal local Kalman filter with a finite buffer is derived for each subsystem,which can also be used as a centralized optimal Kalman filter fusion *** on the new optimal local Kalman filter,multi-sensor optimal distributed weighted Kalman filter fusion with finite buffers has been ***,compared with the centralized optimal Kalman filter fusion algorithm,the proposed distributed weighted Kalman filter fusion algorithm developed in this paper has stronger fault-tolerance *** results are provided to illustrate the effectiveness of the proposed approaches.
There being ample research in cluster-based Media Access control(MAC) protocols for Mobile Ad Hoc Networks (MANETs) recently makes it necessary having a stable clustering algorithm developed for *** in MANETs often ha...
详细信息
ISBN:
(纸本)9781479900305
There being ample research in cluster-based Media Access control(MAC) protocols for Mobile Ad Hoc Networks (MANETs) recently makes it necessary having a stable clustering algorithm developed for *** in MANETs often have highly mobility and sometimes present the characteristic of group *** the innovation perspective,we proposed a clustering algorithm by employing Learning Automata(LA) in a distributed manner considering nodes distance and nodes mobility to produce stable *** utilizing LA nodes can make intelligent and adaptive decisions based on the local information collected in the past *** to another mobility based clustering algorithm,simulation results present us the superior performance of the proposed algorithm.
Considering the uncertainties parameters and unknown dynamics of permanent-magnet synchronous motors in real applications,a composite controller strategy for electromechanical actuator is proposed in this *** composit...
详细信息
ISBN:
(纸本)9781479947249
Considering the uncertainties parameters and unknown dynamics of permanent-magnet synchronous motors in real applications,a composite controller strategy for electromechanical actuator is proposed in this *** composite strategy consists of a disturbances observer based on linear extended state observer that suppresses disturbances by feedforward compensation and a Lyapunov stability-based position controller.A non-singular terminal sliding mode position controller is used here due to its good performance,under which state errors would converge to zero in finite ***,special forms of load torque,hinge moment,and sinusoidal torque disturbances have been taken into consideration in this *** proposed control strategy is verified via *** performance with respect to position tracking and robustness to load disturbances and parametric uncertainties of the motor have been demonstrated.
This paper presents a new method for optimal design of controllers based on a "library" thought and differential *** first an extensible component library and a performance criteria library are established i...
详细信息
ISBN:
(纸本)9781467374439
This paper presents a new method for optimal design of controllers based on a "library" thought and differential *** first an extensible component library and a performance criteria library are established in the *** component library contains different types of system components which may be essential for controller *** components can be selected from the library and then combined to form a controller with richer *** performance criteria library includes some common control performance *** can choose one from it according to performance ***,the differential evolution algorithm is utilized to optimize the parameters of each component in order to find the optimal solution and ultimately obtain the controller structure and parameters which meet *** were done on different types of control *** results show that the controllers designed by the proposed method for different types of control objects generally have better comprehensive performance than the PID controllers designed by conventional methods,differential evolution and genetic ***,stability and generalizability of the proposed method were also tested and verified.
Hysteresis brake,which provides for step-less torque and high speed,is a stable and reliable device used for loading,but with some problems,such as the large time-lag,strong nonlinearity,and difficulty in modeling et ...
详细信息
ISBN:
(纸本)9781509009107
Hysteresis brake,which provides for step-less torque and high speed,is a stable and reliable device used for loading,but with some problems,such as the large time-lag,strong nonlinearity,and difficulty in modeling et *** to the above-mentioned issues,the special working conditions of hysteresis brake developed by our project team and the advantage of the dynamical performance of the Elman Multi-Hidden Layers Neural Network,this paper employs modified neural network algorithm with Elman dynamic recursive structure to accomplish the model of hysteresis brake,and guarantees the accuracy of output loaded *** this algorithm,we introduce the speed,the given and desired torque,and a directivity factor respectively as a disturbance variable and two input vectors of the system,and then train the model and *** numerical results validate the effectiveness of the algorithm proposed.
暂无评论