This paper presents a novel strategy to train keypoint detection models for robotics applications. Our goal is to develop methods that can robustly detect and track natural features on robotic manipulators. Such featu...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
This paper presents a novel strategy to train keypoint detection models for robotics applications. Our goal is to develop methods that can robustly detect and track natural features on robotic manipulators. Such features can be used for vision-based control and pose estimation purposes, when placing artificial markers (e.g. ArUco) on the robot's body is not possible or practical in runtime. Prior methods require accurate camera calibration and robot kinematic models in order to label training images for the keypoint locations. In this paper, we remove these dependencies by utilizing inpainting methods: In the training phase, we attach ArUco markers along the robot's body and then label the keypoint locations as the center of those markers. We, then, use an inpainting method to reconstruct the parts of the robot occluded by the ArUco markers. As such, the markers are artificially removed from the training images, and labeled data is obtained to train markerless keypoint detection algorithms without the need for camera calibration or robot models. Using this approach, we trained a model for realtime keypoint detection and used the inferred keypoints as control features for an adaptive visual servoing scheme. We obtained successful control results with this fully model-free control strategy, utilizing natural robot features in the runtime and not requiring camera calibration or robot models in any stage of this process.
Continuum robots have the advantage of flexibility and dexterity due to their elastic and bendable architecture. Nowadays, multi-segment robots are employed as various medical instruments. However, the multi-segment r...
详细信息
ISBN:
(纸本)9798350386523;9798350386530
Continuum robots have the advantage of flexibility and dexterity due to their elastic and bendable architecture. Nowadays, multi-segment robots are employed as various medical instruments. However, the multi-segment robot consists of complex kinematics and control, but it also enhances the robot's capabilities for complex procedures. The paper presents the path planning and motion control of basic robot motion to perform surgical tasks. The robot's 3D manipulation discussed in this paper includes insertion, point-to-point motion, and tool center point motion. The follow-the-leader motion approach was employed for the robot insertion. The point-to-point motion trajectory is generated in configuration space, and differential Jacobian base inverse kinematics is employed for Tool center point motion control of a tendon-driven threesegment continuum robot. The simulation results indicate that the obtained input parameters in joint space ensure smooth robot manipulation.
The paper presents the design and practical implementation by students of a control system using a classic PID controller and a controller using artificial neural networks. The control object is a Duckiebot robot, and...
详细信息
The banking sector faces a significant challenge when it comes to debt recovery. This process often involves complex workflows and requires considerable resource allocation. To address this issue, researchers have exp...
详细信息
With the advancement of technology and the development of human civilization, intelligent robots as "service robots" have been gradually integrated into the practical application of people's daily lives ...
详细信息
ISBN:
(纸本)9798350379822;9798350379815
With the advancement of technology and the development of human civilization, intelligent robots as "service robots" have been gradually integrated into the practical application of people's daily lives and the good assistants for people's family life, medical and health, entertainment, and social security. This paper designs and implements a novel vision-based intelligent human-following system for a mobile robot. To achieve human tracking using only RGB images, a monocular depth estimation network is combined with an object tracking network. Considering the speed, robustness, and accuracy in real applications, we optimized the network and added the target update strategy to achieve a good balance between speed and accuracy. Implemented on an NVIDIA Jetson AGX Xavier, the system achieved 97.8% accuracy on our customized dataset, with overall system performance averaging 5.57 FPS.
The research of humanoid multi-fingered hand aiming to be applied to people's daily life, but they are faced with the main contradiction between simplicity and functionality. Herein, we propose a novel rigid-flexi...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
The research of humanoid multi-fingered hand aiming to be applied to people's daily life, but they are faced with the main contradiction between simplicity and functionality. Herein, we propose a novel rigid-flexible coupling humanoid multi-fingered hand comprising finger and palm. Based on the rigid-flexible coupling finger designed in this paper, the mechanical deformation of rigid-flexible coupling finger structure is analyzed from the static point of view based on the theory of beam constraint model. The mechanic model of the rigid-flexible coupling finger is established according to the deformation of the designed rigid-flexible coupling finger structure driven by the cable, considering the friction force of the cable. The feasibility of the design method is proved by experiments, which can potentially bean alternative for manipulators in practicalapplications to complete the flexible works.
Typically, universities with a focus on technical sciences provide courses where students have to design control systems, to implement these control systems on embedded hardware and to verify the functionality of thei...
详细信息
ISBN:
(纸本)9781665489218
Typically, universities with a focus on technical sciences provide courses where students have to design control systems, to implement these control systems on embedded hardware and to verify the functionality of their implementations. Hence, the students work in groups and implement practical demonstrators based on given problem statements. In order to design, implement, and test robotic applications, it is mandatory to utilize expertise within the field of robotics and the field of embedded systems. The combination of expertise within both fields (robotics and embedded systems) is a highly demanded skill set, which is required to work for companies with focus on aviation, automotive, and even emerging applications for agricultural technology. The technical complexity of these applications is increasing almost exponentially, which requires abstract model-based approaches to ease the design flow of such implementations. This paper introduces a model-based approach for students within robotics and/or embedded systems degree programs. Moreover, this paper describes the state-of-the-art workflow to implement problem statements within the field of robotics and embedded systems (tools, approach and test), gives and overview of the model-based approach for students within these field of applications, and shows the integration of the results into courses based on a control system model.
As large-scale lithium-ion battery energy storage power facilities are built, the issues of safety operations become more complex. The existing difficulties revolve around effective battery health evaluation, cell-to-...
详细信息
As large-scale lithium-ion battery energy storage power facilities are built, the issues of safety operations become more complex. The existing difficulties revolve around effective battery health evaluation, cell-to-cell variation evaluation, circulation, and resonance suppression, and more. Based on this, this paper first reviews battery health evaluation methods based on various methods and summarizes the selection of existing health factors in data-driven methods. Secondly, the paper discusses the new research hotspots in the existing battery state evaluation technologies from the perspectives of state evaluation using data fragments and edge computing. Thirdly, we focus and discuss on the safety operation technologies of energy storage stations, including the issues of inconsistency, balancing, circulation, and resonance. To address these issues, we present an intelligent inspection robot, enabling real-time data interaction with the EMS and fulfilling rapid inspection and real-time diagnosis. Above all, we focus on the safety operation challenges for energy storage power stations and give our views and validate them with practical engineering applications, building the foundation of the next-generation techniques that support the development of new power systems.
robot swarms are increasingly being applied in various domains. However, due to the inherent limitation imposed by low real-time communication bandwidth, the synchronization of environmental information among multiple...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
robot swarms are increasingly being applied in various domains. However, due to the inherent limitation imposed by low real-time communication bandwidth, the synchronization of environmental information among multiple robots remains a persistent and challenging problem in practicalapplications. In response to this challenge, we introduce a comprehensive framework for synchronizing occupancy grid maps (OGMs) in practical multi-robot systems that operate under communication bandwidth constraints. In our research, we elaborately design the data structure of transmitted local OGMs and employ the Hilbert space-filling curve for voxel sorting. By adopting this approach, data redundancy is effectively increased, resulting in lower information entropy for compression and significantly reducing the volume of communication data. Finally, our framework outperforms the benchmark method by reducing the average and maximum bandwidth usage by more than 10 times in high-resolution scenarios. Moreover, our method has been successfully applied in the multi-UAV autonomous navigation application, demonstrating its real-time and bandwidth-efficient nature, as well as its practical value.
Language-guided active sensing is a robotics sub-task where a robot with an onboard sensor interacts efficiently with the environment via object manipulation to maximize perceptual information, following given languag...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Language-guided active sensing is a robotics sub-task where a robot with an onboard sensor interacts efficiently with the environment via object manipulation to maximize perceptual information, following given language instructions. These tasks appear in various practicalrobotics applications, such as household service, search and rescue, and environment monitoring. Despite many applications, the existing works do not account for language instructions and have mainly focused on surface sensing, i.e., perceiving the environment from the outside without rearranging it for dense sensing. Therefore, in this paper, we introduce the first language-guided active sensing approach that allows users to observe specific parts of the environment via object manipulation. Our method spatially associates the environment with language instructions, determines the best camera viewpoints for perception, and then iteratively selects and relocates the best view-blocking objects to provide the dense perception of the region of interest. We evaluate our method against different baseline algorithms in simulation and also demonstrate it in real-world confined cabinet-like settings with multiple unknown objects. Our results show that the proposed method exhibits better performance across different metrics and successfully generalizes to real-world complex scenarios.
暂无评论