The cost of autonomous drivings system is currently one of the key factors that will decide whether this technology can be widely deployed. In this paper, the control system design of an autonomous vehicle with low-co...
The cost of autonomous drivings system is currently one of the key factors that will decide whether this technology can be widely deployed. In this paper, the control system design of an autonomous vehicle with low-cost mechanical structure and electrical system is studied. The open-loop responses of the velocity and steering system illustrate that this vehicle is confronted with limited hardware performance. The mean goal of this research is applying high performance algorithm to stabilize the system and guarantee the stability as much as possible. In other words, sacrificing some computation to compensate the limited hardware. Model predictive control (MPC) is a control algorithm based on rolling optimization, although it requires more computation than traditional control algorithms it can taking multi complex constraints into account so that it can tackle various problems in this system. A constrained MPC is proposed to control this low-cost vehicle, it is tested on the simulation and real vehicle. By comparing the system performance in open-loop and close-loop, the algorithm is proved to be effective. Finally, the Lyapunov stability proof is also given out in this paper, which guarantees the theoretical stability of the algorithm.
This paper presented a prescribed-time model-free adaptive control (PTMFAC) scheme to achieve attitude-tracking control of a spacecraft system under denial-of-service (DoS) attacks. By using a finite-time performance ...
This paper presented a prescribed-time model-free adaptive control (PTMFAC) scheme to achieve attitude-tracking control of a spacecraft system under denial-of-service (DoS) attacks. By using a finite-time performance function (FTPF), an improved dynamic linearization module was presented to attain the prescribed-time convergence of output signal. At the same time, we presented a counter-attack strategy to reduce the effect of attacks. By employing the counter-attack strategy, a PTMFAC control algorithm was proposed to achieve attitude-tracking control within a prescribed time. Finally, the boundness analyses and simulations confirmed the effectiveness of developed control algorithm.
The Bundle Adjustment (BA) algorithm is a widely used nonlinear optimization technique in the backend of Simultaneous Localization and Mapping (SLAM) systems. By leveraging the co-view relationships of landmarks from ...
详细信息
This paper is concentrating on designing a control system to handle a low-cost autonomous vehicle. There are many shortcomings in this system such as time-delays, sensor noise and nonlinearities that cannot be modelle...
This paper is concentrating on designing a control system to handle a low-cost autonomous vehicle. There are many shortcomings in this system such as time-delays, sensor noise and nonlinearities that cannot be modelled with equations. In real experiments, the performances of this vehicle are recorded by data and diagram which quantifies the short-comings of this system. With these results, two problems are founded which are the research objectives of this paper. One is the uncertainty in this system, which makes it hard for a linear controller to stabilize this system. The other is that there are nonnegligible time-delays in the front wheel motor, and it can resist disturbance. To solve these problems, a backstepping control is applied to design a nonlinear tracking controller. Meanwhile, an Extended State Observer (ESO) is designed to solve the problems of the front wheels. The control system is tested in simulation and real vehicle, whose results prove the correctness and feasibility.
This paper proposes a denoising-based improved deformation estimation method for a self-balancing lower limb exoskeleton (SBLLE). A denoiser constructed by a residual network is utilized to improve the accuracy of def...
详细信息
ISBN:
(数字)9798331509644
ISBN:
(纸本)9798331509651
This paper proposes a denoising-based improved deformation estimation method for a self-balancing lower limb exoskeleton (SBLLE). A denoiser constructed by a residual network is utilized to improve the accuracy of deformation estimation for SBLLE. Specifically, we introduce a residual network-bidirectional long short-term memory network (ResNet-BiLSTM) denoising deformation estimator (RBDDE) to estimate and compensate for the deformation of SBLLE, based on force and torque (F/T) data. F/T data and deformation data are collected separately using F/T sensors embedded in the sole of SBLLE and a motion capture system. Initially, the empirical mode decomposition method is employed on the training set to construct a dataset for training the ResNet denoising network, enabling the denoising network with denoising capabilities. Subsequently, the ResNet-BiLSTM network is trained using both F/T and deformation data, enabling the estimation and compensation of SBLLE deformation at its center of mass. Comparative experiments with a deformation estimation network without denoising show that RBDDE improves the accuracy of deformation estimation.
This paper proposed a real-time Unmanned Aerial Vehicle (UAV) autonomous localization framework based on onboard sensors, including 2D Lidar, Stereo Camera and Inertial Measurement Unit (IMU), built on the open-source...
This paper proposed a real-time Unmanned Aerial Vehicle (UAV) autonomous localization framework based on onboard sensors, including 2D Lidar, Stereo Camera and Inertial Measurement Unit (IMU), built on the open-source VINS-Fusion software to achieve real-time and drift-free UAV pose estimation. The proposed framework eliminates the motion distortion of Lidar during UAV motion by combining Visual-Inertial Odometry (VIO). It obtains global localization information of Lidar by PL-ICP algorithm based on a global point cloud map. Graph optimization method is used to fuse the local positional estimation and the global information from the Lidar, which eliminate the cumulative error caused by VIO. The feasibility of the method is verified by experiments and compared with the method of only running Visual-Inertial Navigation systems (VINS), the framework improves the accuracy of localization. In addition, we have implemented the construction of octree maps of 3D environments through the framework of this system.
This research aims to explore key issues in the field of walking robots and exoskeletons. By using a depth camera to record human walking data in different terrains and employing RGB and depth information for image cl...
详细信息
This research aims to explore key issues in the field of walking robots and exoskeletons. By using a depth camera to record human walking data in different terrains and employing RGB and depth information for image classification, our approach utilizes both early fusion and late fusion methods to explore their impact on terrain classification. This approach achieved fast and accurate performance in recognizing terrain. We captured data for walking upstairs, downstairs, upward ramps, downward ramps and level ground and used the vision transformer for data fusion. This work compares the performance of unimodal RGB model, unimodal deep model, Pre-Fusion model and Post-Fusion model in terms of accuracy, recall and processing frequency, with accuracies of 0.954, 0.934, 0.976, and 0.976, respectively. The results show that the Post-Fusion model slightly outperforms the Pre-Fusion model in terms of accuracy and recall with more reliable classification performance. To understand the attention mechanism better, we've been visualizing the weights of the model, observing how different attention heads may capture different features of the data from various dimensional perspectives. The visualization helps in interpreting the model's focus and how it distinguishes between features of different nature, such as color texture and spatial depth. These findings can inform the ongoing refinement of terrain classification systems for applications in robotics and autonomous navigation.
In this article, a rehabilitation exoskeleton assisted by lateral walking is designed to help patients with lower limb movement disorders to solve the problem of lateral walking assistance, so as to achieve the effect...
详细信息
In this paper, a flexible stretchable pressure sensor that can be combined with clothing is designed. Due to its excellent flexibility, it is no longer limited to conventional uses when combined with fabrics. This wea...
详细信息
In this paper, a flexible stretchable pressure sensor that can be combined with clothing is designed. Due to its excellent flexibility, it is no longer limited to conventional uses when combined with fabrics. This wearable flexible stretchable pressure sensor is easy to process and low in cost and can participate in human motion monitoring accurately, flexibly, and variably. The sensors show different performances when they are made of different flexible materials, microstructures, and processing technologies. They have ideal biocompatibility and adaptability and have considerable application prospects. Moreover, multiple sensors can be applied to various parts of the human body to measure the angle of the human body. Angle monitoring in the sagittal plane, coronal plane, and horizontal plane may also be realized in the future, In this report, the performance of the sensor integrated into the elastic tights was tested, and then the actual application and independence of the sensor clothing were demonstrated by measuring the angle of the hip joint in the sagittal plane. Finally, when the sensor clothing was worn, the synchronous gait measurement was carried out on the treadmill with the dynamic capture, and then the captured data was processed to obtain the human motion data. Through comparison with the dynamic capture system, To detect the initial actual performance of the sensor and characterize the defects in wearing measurement.
Thanks to high spatial resolution and multi-tactile mode perception, visual-tactile sensing technology has been widely used in various robot operations such as active perception, pose estimation and in-palm operation....
详细信息
暂无评论