In this paper, the two sliding surface part transformations are investigated for ITSMC (integral terminal sliding mode control) of second-order uncertain linear plants when the input gain uncertainty of the system is ...
详细信息
In this paper, a complete proof of Utkin's theorem is presented for the ITSMC(integral terminal sliding mode control) of second order uncertain linear plants when ∆b≠0. The addition of integral action to the TSMC...
详细信息
作者：
Jeung, Eun TaeDept. of Robot
Control and Instrumentation Engineering Changwon National University Korea Republic of
This investigation deals with the design method of a static output feedback controller for continuous-time T-S fuzzy systems via iterative linear matrix inequalities. First, a matrix inequality that guarantees the sta...
详细信息
Stroke survivors often experience balance disorders, significantly increasing the risk of falls. Accurate COP (Center of Pressure) measurements are essential for evaluating balance and rehabilitation outcomes. To meas...
详细信息
ISBN:
(数字)9798350353303
ISBN:
(纸本)9798350353310
Stroke survivors often experience balance disorders, significantly increasing the risk of falls. Accurate COP (Center of Pressure) measurements are essential for evaluating balance and rehabilitation outcomes. To measure COP, force plates are expensive and not user-friendly. Another system for measuring COP is Insole Pressure Sensors (IPS). However, IPS has limitations in accuracy and usability. In this paper, we suggested a cost-effective COP measurement algorithm based on high-resolution Tactile sensors which has electrodes aligned at right angles on each side of a commercial piezoresistive film, and can capture human footprints in great detail. Furthermore, a static experiment was conducted with weight plates to evaluate the COP measurement capability of the system. In future works, we will focus on validating the system's durability, usability, and integration into rehabilitation programs, as well as comparing dynamic COP measurements with force plate data.
S-curve is one of the most applied approaches for trajectory generation for the point-to-point movement in industrial drives. In this note, the asymmetric S-curve structure is addressed to develop a single-axis motion...
详细信息
In recent years, mapless navigation with a deep reinforcement learning approach in Autonomous Mobile robot has shown a considerable benefit in improving robot behavior flexibility. Specifically, the robot adapts to co...
详细信息
ISBN:
(数字)9781728189246
ISBN:
(纸本)9781728189253
In recent years, mapless navigation with a deep reinforcement learning approach in Autonomous Mobile robot has shown a considerable benefit in improving robot behavior flexibility. Specifically, the robot adapts to complex constraints and performs well in various environments without the need for a predetermined map and route plan. However, several previous studies show a lack of stability in the training of deep reinforcement learning networks for mapless navigation. Moreover, the exploration and exploitation in a specific work environment play an essential role in improving mapless navigation performance, which needs to be carefully considered. From the aforementioned issues, as well as inspired by the Proximal Policy optimization algorithm has shown that it does not only evaluates the advantages and disadvantages of policy but also prevents the policy from changing too much after each time weight update. In this paper, we propose to build a Convolutional Proximal Policy optimization network for the Mapless Navigation problem. Furthermore, the use of Boltzmann's policy to help balance exploration and exploitation also contributes to the robot's ability to explore more deeply in complex environments, and the performance of the mapless navigation problem is also significantly improved.
Distributed tactile sensing for multi-force detection is crucial for various aerial robot interaction tasks. However, current contact sensing solutions on drones only exploit single end-effector sensors and cannot pro...
详细信息
Autonomous driving refers to a vehicle driving by itself without human intervention. An autonomous vehicle must recognize the environment with an attached sensor, make judgments appropriate to the situation, and drive...
详细信息
ISBN:
(纸本)9781665490498
Autonomous driving refers to a vehicle driving by itself without human intervention. An autonomous vehicle must recognize the environment with an attached sensor, make judgments appropriate to the situation, and drive toward its destination. Although many studies have been conducted on autonomous driving in clear weather, the response to bad weather is insufficient because the sensor encounters difficulties recognizing the environment when it is backlight or raining. This study proposes a method for recognizing objects (e.g., vehicles, pedestrians, lanes) based on polarization cameras for safe autonomous driving in backlight conditions or rain. First, the camera’s light input is adjusted, altering its aperture backlight conditions. Then, the polarized image from the camera is synthesized and inputted into the object recognition network. The object detection network used Yolo v5, while the lane detection network used an ultrafast lane detection network. By extracting features from the same backbone, the inference speed of the object recognition network increased. On average, a speed of 23 fps and an object recognition accuracy of over 90% were shown in the Xavier environment.
In this paper, we propose the classification method of assembly defects in the surface mount technology process. We used a cascade convolution neural network which two convolutional neural networks were merged into on...
详细信息
Pedestrian detection plays an important role in the environmental perception and autonomous navigation for robotics, which provides critical information for the safe operation in complex environments. In this paper, a...
详细信息
暂无评论