In the face of the Fourth Industrial Revolution (Industry 4.0), collaborative robots have become one of the key pillars of development. Thanks to their sensors, they allow increased flexibility and safety while workin...
详细信息
Grasping and manipulation of deformable objects are challenging problems in the food-processing industry. Food objects vary wildly in shape, size, mass, and stiffness. We present the design and control of an underactu...
Grasping and manipulation of deformable objects are challenging problems in the food-processing industry. Food objects vary wildly in shape, size, mass, and stiffness. We present the design and control of an underactuated tendon-driven finger-based gripper with as key features high adaptability and variable joint stiffness. We first present a kinematic analysis of tendon routing in the context of grasp force and adjustable stiffness, as well as a control strategy to leverage these features. We then present a proof-of-concept prototype, which is validated in experiment. The results show that stable grasps can be achieved adaptively, and that grasp force and joint stiffness can be regulated independently for fragile objects.
With the growing need for on-orbit servicing (OOS) technology to de-orbit and extend the life of satellites, unmanned systems with robotic arms have become increasingly promising as a versatile solution. This paper pr...
With the growing need for on-orbit servicing (OOS) technology to de-orbit and extend the life of satellites, unmanned systems with robotic arms have become increasingly promising as a versatile solution. This paper provides an overview of different tools for capturing a cooperative or non-cooperative target satellite. We provide a comparative analysis of eight grippers for capture using the launch adapter ring (LAR) of target satellites. They are characterized by the following aspects: 1) Having a jaw with suitable geometry for clamping the flange of the LAR, 2) Capture is carried out in steps of fast but soft capture and slow but rigid capture to prevent LAR escape, and 3) Typical capture envelope is in the order of tens of mm and typical load capacity is ~100-200 Nm, 4) They have a number of sensors, including trigger sensors to detect the presence of the LAR within the capture envelope and trigger the gripper closure. Upcoming missions within a few years will demonstrate on-orbit the capability of those LAR grippers.
One of the key issues in human-machine collaboration is human safety. Safe human-robot interaction can be implemented using an electronic skin (e-skin) that detects the human’s proximity to the collaborative robot (c...
详细信息
Prior gait analysis has played a crucial role in assessing overall health and well-being, particularly in individuals of different age groups. Nevertheless, acquiring gait data has necessitated the in-person presence ...
详细信息
For precise control, it can be achieved through a feedforward controller with a feedback control scheme. The feedforward controller can be automatically tuned with the datadriven methods through experimental results. ...
详细信息
For precise control, it can be achieved through a feedforward controller with a feedback control scheme. The feedforward controller can be automatically tuned with the datadriven methods through experimental results. However, these data-driven methods are interrupted when the input disturbance is applied. This problem can be solved using Disturbance Observer (DOB) in the control loop. In addition, a data-driven method derives accurate control performance by simultaneously tuning the feedforward controller and DOB model. Furthermore, a tuning algorithm with a rational model is proposed for the corresponding modeling to a flexible system. The simulation results verify that the proposed method accurately tunes the controller for an unknown plant under an input disturbance.
This paper presents a convolutional neural network (CNN) model for event detection from Unmanned Aerial Vehicles (UAV) in disaster environments. The model leverages the YOLOv5 network, specifically adapted for aerial ...
This paper presents a convolutional neural network (CNN) model for event detection from Unmanned Aerial Vehicles (UAV) in disaster environments. The model leverages the YOLOv5 network, specifically adapted for aerial images and optimized for detecting Search and Rescue (SAR) related classes for disaster area recognition. These SAR-related classes are person, vehicle, debris, fire, smoke, and flooded areas. Among these, the latter four classes lead to unique challenges due to their lack of discernible edges and/or shapes in aerial imagery, making their accurate detection and performance evaluation metrics particularly intricate. The methodology for the model training involves the adaptation of the pre-trained model for aerial images and its subsequent optimization for SAR scenarios. These stages have been conducted using public datasets, with the required image labeling in the case of SAR-related classes. An analysis of the obtained results demonstrates the model's performance while discussing the intricacies related to complex-shape classes. The model and the SAR datasets are publicly available.
A grasping detection module is presented to measure normal contact force on each link of the finger in robotic hand. A compact and embeddable design for detecting the grasping force on the contact surface is addressed...
A grasping detection module is presented to measure normal contact force on each link of the finger in robotic hand. A compact and embeddable design for detecting the grasping force on the contact surface is addressed and its sensing performance is evaluated.
This article presents sign language gestures application used for control of humanoid 3D printed hand with fingers, based on a modular principle. The 3D printed fingers are designed to be manufactured assembled, which...
详细信息
作者：
Możaryn, JakubDepartment of Mechatronics
Institute of Automatic Control and Robotics Warsaw Univeristy of Technology ul. Sw. A. Boboli 8 Warsaw02-525 Poland
The electronic skin described in the article comprises screen-printed graphene-based sensors, intended to be used for robotic applications. The precise mathematical model allowing the touch pressure estimation is requ...
详细信息
暂无评论