检索结果-内蒙古大学图书馆

Model-Free Dynamic control of a 3-DoF Delta Parallel Robot for Pick-and-Place Application based on Deep Reinforcement Learning

学校读者我要写书评

暂无评论

Model-Free Dynamic Control of a 3-DoF Delta Parallel Robot f...

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Hasan Jalali Saba Samadi Ahmad Kalhor Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781665454537

This article investigates the performance of the Delta robot using model-free controller. Since it is difficult to obtain an accurate dynamic model of the robot and identification methods are complex and challenging. Therefore, in this article, a new approach is presented which checks the performance of the Delta robot in pick-and-place operation using model-free dynamic controllers. For the purposes of this paper, Deep Reinforcement Learning (DRL) and also the Deep Deterministic Policy Gradient (DDPG) network is used. The DDPG algorithm is implemented for the first time on the Delta robot, and according to the obtained results, it reveals that it can provide a favorable approach for the pick-and-place operation. In this method, based on the science of DRL, a reward function based on the pick-and-place operation is also defined, which gives negative reward (punishment) or a positive reward according to the way the robot performs. It is noteworthy that according to the obtained results, it is possible to generalize other points for the pick-and-place operation. It should be noted that the robot was able to learn the target after a long episode and its graph converged after approximately 18,000 episodes.

关键词： Training Deep learning Parallel robots Actuators Mechatronics Heuristic algorithms Reinforcement learning

Experimental Study on Motion controller based on NN-ARX and ARMAX Actuator Identification for 3-DoF Delta Parallel Robot

学校读者我要写书评

暂无评论

Experimental Study on Motion Controller based on NN-ARX and ...

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Hasan Jalali Hossein Damavandi Ahmad Kalhor Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran Faculty of Computer Engineering and Information Technology Sadjad University Mashhad Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

Today, system identification plays a pivotal role in control science and offering a myriad of applications. This paper places its focus on the identification of actuator models within real-world delta robots for informing controller design. Two identification methods, namely NN-ARX and ARMAX, have been employed to extract the dynamic characteristics of the robot actuators, resulting in dynamic models of these integral components being derived. These dynamic models have been utilized in simulations for controller design, and due to the disparities in the identification models, distinct controllers have been realized. Subsequently, these controllers have been practically implemented on delta robots, and their performances have been subjected to a comprehensive comparative analysis. The results demonstrate that controllers integrating the identified actuator models outperformed those designed without the incorporation of the identification models. In practice, the implementation of controllers based on NN-ARX yielded the most favorable results among all the tested controllers. This research not only underscores the importance of accurate actuator models in control system design but also highlights the superior performance of neural network-based controllers in real-world robotic applications. In particular, the practical results of NN-ARX-based controllers were able to achieve significantly lower RMSE of 2.3562, 1.9531, and 2.1185 for the three motors, respectively, as opposed to the 4.1369, 3.0125, and 3.0363 achieved by the ARMAX-based controllers.

关键词：

Pseudo-LiDAR for Visual Odometry

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Deng, Huiying Wang, Guangming Feng, Zhiheng Jiang, Chaokang Wu, Xinrui Miao, Yanzi Wang, Hesheng Advanced Robotics Research Center AI Research Institute School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

As one of the important tasks in the field of robotics and machine vision, LiDAR/visual odometry provides tremendous help for various applications such as navigation, location, etc. In the existing methods, LiDAR odometry shows superior performance, but visual odometry is still widely used for its price advantage. Conventionally, the task of visual odometry mainly rely on the input of continuous images. However, it is very complicated for the odometry network to learn the epipolar geometry information provided by the images. In this paper, the concept of pseudo-LiDAR is introduced into the odometry to solve this problem. The pseudo-LiDAR point cloud back-projects the depth map generated by the image into the 3D point cloud, which changes the way of image representation. Compared with the stereo images, the pseudo-LiDAR point cloud generated by the stereo matching network can get the explicit 3D coordinates. Since the 6 Degrees of Freedom (DoF) pose transformation occurs in 3D space, the 3D structure information provided by the pseudo-LiDAR point cloud is more direct than the image. Compared with sparse LiDAR, the pseudo-LiDAR has a denser point cloud. In order to make full use of the rich point cloud information provided by the pseudo-LiDAR, a projection-aware dense odometry pipeline is adopted. Most previous LiDAR-based algorithms sampled 8192 points from the point cloud as input to the odometry network. The projection-aware dense odometry pipeline takes all the pseudo-LiDAR point clouds generated from the images except for the error points as the input to the network. While making full use of the 3D geometric information in the images, the semantic information in the images is also used in the odometry task. The fusion of 2D-3D is achieved in an image-only based odometry. Experiments on the KITTI dataset prove the effectiveness of our method. To the best of our knowledge, this is the first visual odometry method using pseudo-LiDAR. Copyright © 2022, The Authors. A

关键词： Pipelines

Coordinated Guiding Vector Field Design for Ordering-Flexible Multi-Robot Surface Navigation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Bin-Bin Zhang, Hai-Tao Yao, Weijia Sun, Zhiyong Cao, Ming The School of Artificial Intelligence and Automation The Engineering Research Center of Autonomous Intelligent Unmanned Systems The Key Laboratory of Image Processing and Intelligent Control The State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China The School of Robotics Hunan University Hunan410082 China The Institute of Engineering and Technology University of Groningen Groningen9747 AG Netherlands Department of Electrical Engineering Eindhoven University of Technology Netherlands

We design a distributed coordinated guiding vector field (CGVF) for a group of robots to achieve ordering-flexible motion coordination while maneuvering on a desired two-dimensional (2D) surface. The CGVF is characterized by three terms, i.e., a convergence term to drive the robots to converge to the desired surface, a propagation term to provide a traversing direction for maneuvering on the desired surface, and a coordinated term to achieve the surface motion coordination with an arbitrary ordering of the robotic group. By setting the surface parameters as additional virtual coordinates, the proposed approach eliminates potential singularity of the CGVF and enables both the global convergence to the desired surface and the maneuvering on the surface from all possible initial conditions. The ordering-flexible surface motion coordination is realized by each robot to share with its neighbors only two virtual coordinates, i.e. that of a given target and that of its own, which reduces the communication and computation cost in multi-robot surface navigation. Finally, the effectiveness of the CGVF is substantiated by extensive numerical simulations. Copyright © 2024, The Authors. All rights reserved.

关键词： Navigation

Autonomous inverse encoding guides 4D nanoprinting for highly programmable shape morphing

学校读者我要写书评

暂无评论

International Journal of Extreme Manufacturing 2025年第3期 472-488页

作者： Shuaiqi Ren Zhiang Zhang Ruokun He Jiahao Fan Guangming Wang Hesheng Wang Bing Han Yong-Lai Zhang Zhuo-Chen Ma Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Engineering University of Cambridge Institute of Medical Robotics School of Biomedical Engineering Shanghai Jiao Tong University State Key Laboratory of Integrated Optoelectronics College of Electronic Science and EngineeringJilin University

Highly programmable shape morphing of 4D-printed micro/nanostructures is urgently desired for applications in robotics and intelligent systems. However, due to the lack of autonomous holistic strategies throughout the target shape input, optimal material distribution generation,and fabrication program output, 4D nanoprinting that permits arbitrary shape morphing remains a challenging task for manual design. In this study, we report an autonomous inverse encoding strategy to decipher the genetic code for material property distributions that can guide the encoded modeling toward arbitrarily pre-programmed 4D shape morphing. By tuning the laser power of each voxel at the nanoscale, the genetic code can be spatially programmed and controllable shape morphing can be realized through the inverse encoding process. Using this strategy, the 4D-printed structures can be designed and accurately shift to the target morphing of arbitrarily hand-drawn lines under stimulation. Furthermore, as a proof-of-concept, a flexible fiber micromanipulator that can approach the target region through pre-programmed shape morphing is autonomously inversely encoded according to the localized spatial *** strategy may contribute to the modeling and arbitrary shape morphing of micro/nanostructures fabricated via 4D nanoprinting, leading to cutting-edge applications in microfluidics, micro-robotics, minimally invasive robotic surgery, and tissue engineering.

关键词：

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Chaokang Wang, Guangming Wu, Jinxing Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China The Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China

Promising complementarity exists between the texture features of color images and the geometric information of LiDAR point clouds. However, there still present many challenges for efficient and robust feature fusion in the field of 3D object detection. In this paper, first, unstructured 3D point clouds are filled in the 2D plane and 3D point cloud features are extracted faster using projection-aware convolution layers. Further, the corresponding indexes between different sensor signals are established in advance in the data preprocessing, which enables faster cross-modal feature fusion. To address LiDAR points and image pixels misalignment problems, two new plug- and-play fusion modules, LiCamFuse and BiLiCamFuse, are proposed. In LiCamFuse, soft query weights with perceiving the Euclidean distance of bimodal features are proposed. In BiLiCamFuse, the fusion module with dual attention is proposed to deeply correlate the geometric and textural features of the scene. The quantitative results on the KITTI dataset demonstrate that the proposed method achieves better feature-level fusion. In addition, the proposed network shows a shorter running time compared to existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Robotic Electrospinning Actuated by Non-Circular Joint Continuum Manipulator for Endoluminal Therapy

学校读者我要写书评

暂无评论

Robotic Electrospinning Actuated by Non-Circular Joint Conti...

2021 IEEE International Conference on robotics and Automation, ICRA 2021

作者： Wu, Zicong Lou, Chuqian Jin, Zhu Huang, Shaoping Liu, Ning Zou, Yun Kovac, Mirko Gao, Anzhu Yang, Guang-Zhong The Institute of Medical Robotics Department of Bioengineering Shanghai Jiao Tong University Shanghai200240 China Imperial College London Empa-Swiss Federal Laboratories for Materials Science and Technology United Kingdom Limited 999077 Hong Kong Aerial Robotics Laboratory Imperial College London LondonSW7 2AZ United Kingdom The Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University The Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China The Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9781728190778

Electrospinning has exhibited excellent benefits to treat the trauma for tissue engineering due to its produced micro/nano fibrous structure. It can effectively adhere to the tissue surface for long-term continuous therapy. This paper develops a robotic electrospinning platform for endoluminal therapy. The platform consists of a continuum manipulator, the electrospinning device, and the actuation unit. The continuum manipulator has two bending sections to facilitate the steering of the tip needle for a controllable spinning direction. Non-circular joint profile is carefully designed to enable a constant length of the centreline of a continuum manipulator for stable fluid transmission inside it. Experiments are performed on a bronchus phantom, and the steering ability and bending limitation in each direction are also investigated. The endoluminal electrospinning is also fulfilled by a trajectory following and points targeting experiments. The effective adhesive area of the produced fibre is also illustrated. The proposed robotic electrospinning shows its feasibility to precisely spread more therapeutic drug to construct fibrous structure for potential endoluminal treatments. © 2021 IEEE

关键词： Electrospinning

FreeDriveRF: Monocular RGB Dynamic NeRF without Poses for Autonomous Driving via Point-Level Dynamic-Static Decoupling

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wen, Yue Song, Liang Liu, Yijia Zhu, Siting Miao, Yanzi Han, Lijun Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Dimanshen Technology Co. Ltd. China Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China

Dynamic scene reconstruction for autonomous driving enables vehicles to perceive and interpret complex scene changes more precisely. Dynamic Neural Radiance Fields (NeRFs) have recently shown promising capability in scene modeling. However, many existing methods rely heavily on accurate poses inputs and multi-sensor data, leading to increased system complexity. To address this, we propose FreeDriveRF, which reconstructs dynamic driving scenes using only sequential RGB images without requiring poses inputs. We innovatively decouple dynamic and static parts at the early sampling level using semantic supervision, mitigating image blurring and artifacts. To overcome the challenges posed by object motion and occlusion in monocular camera, we introduce a warped ray-guided dynamic object rendering consistency loss, utilizing optical flow to better constrain the dynamic modeling process. Additionally, we incorporate estimated dynamic flow to constrain the pose optimization process, improving the stability and accuracy of unbounded scene reconstruction. Extensive experiments conducted on the KITTI and Waymo datasets demonstrate the superior performance of our method in dynamic scene modeling for autonomous driving. Our implementation will be available at https://***/IRMVLab/FreeDriveRF. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical flows

Brain-inspired feedback for spatial frequency aware artificial networks

学校读者我要写书评

暂无评论

Brain-inspired feedback for spatial frequency aware artifici...

Asilomar Conference on Signals, Systems & Computers

作者： Ramin Toosi Mohammad Ali Akhaee Mohammad-Reza A. Dehaqani School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Cognitive Systems Laboratory Control and Intelligent Processing Center of Excellence (CIPCE) School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran School of Cognitive Sciences Institute for Research in Fundamental Sciences (IPM) Tehran Iran

Spatial frequency (SF) is a characteristic of an image that could dissociate course and fine shape information. Physiological and psychophysical studies widely investigated the role of various SF contents in image processing. Inspired by the primate brain structure, deep neural networks improved various computer vision tasks such as image classification. Physiological studies show that low SF (LSF) contents of an image could be processed faster to provide feedback to facilitate object recognition. However, this knowledge has not been considered in designing neural network structures. This study introduces SFNet, a new neural network structure that employs an LSF-based feedback mechanism. SFNet is a two-stream structure where one stream is used for LSF processing to provide feedback for image classification. The other stream combines the LSF-based feedback and the HSF processing to form the final decision. The role of the proposed LSF-based feedback in image classification is investigated utilizing the CIFAR100 dataset. The results show that SFNet improves the performance in the presence of SF filtering compared to the equivalent structures.

关键词： Band-pass filters Visualization Shape Filtering Streaming media Visual systems Physiology