检索结果-内蒙古大学图书馆

SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Views

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Song, Liang Wang, Guangming Liu, Jiuming Fu, Zhenyang 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

In recent studies, the generalization of neural radiance fields for novel view synthesis task has been widely explored. However, existing methods are limited to objects and indoor scenes. In this work, we extend the generalization task to outdoor scenes, trained only on object-level datasets. This approach presents two challenges. Firstly, the significant distributional shift between training and testing scenes leads to black artifacts in rendering results. Secondly, viewpoint changes in outdoor scenes cause ghosting or missing regions in rendered images. To address these challenges, we propose a geometric correction module and an appearance correction module based on multi-head attention mechanisms. We normalize rendered depth and combine it with light direction as query in the attention mechanism. Our network effectively corrects varying scene structures and geometric features in outdoor scenes, generalizing well from object-level to unseen outdoor scenes. Additionally, we use appearance correction module to correct appearance features, preventing rendering artifacts like blank borders and ghosting due to viewpoint changes. By combining these modules, our approach successfully tackles the challenges of outdoor scene generalization, producing high-quality rendering results. When evaluated on four datasets (Blender, DTU, LLFF, Spaces), our network outperforms previous methods. Notably, compared to MVSNeRF, our network improves average PSNR from 19.369 to 25.989, SSIM from 0.838 to 0.889, and reduces LPIPS from 0.265 to 0.224 on Spaces outdoor scenes. © 2023, CC BY.

关键词： Rendering (computer graphics)

Self-supervised Multi-frame Monocular Depth Estimation with Pseudo-LiDAR Pose Enhancement

学校读者我要写书评

暂无评论

Self-supervised Multi-frame Monocular Depth Estimation with ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Wenhua Wu Guangming Wang Jiquan Zhong Hesheng Wang Zhe Liu MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai 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 Insititute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Depth estimation is one of the most important tasks in scene understanding. In the existing joint self-supervised learning approaches of depth-pose estimation, depth estimation and pose estimation networks are independent of each other. They only use the adjacent image frames for pose estimation and lack the use of the estimated geometric information. To enhance the depth-pose association, we propose a monocular multi-frame unsupervised depth estimation framework, named PLPE-Depth. There are a depth estimation network and two pose estimation networks with image input and pseudo-LiDAR input. The main idea of our approach is to use the pseudo-LiDAR reconstructed from the depth map to estimate the pose of adjacent frames. We propose depth re-estimation with a better pose between the image pose and the pseudo-LiDAR pose to improve the accuracy of estimation. Besides, we improve the reconstruction loss and design a pseudo-LiDAR pose enhancement loss to facilitate the joint learning. Our approach enhances the use of the estimated depth information and strengthens the coupling between depth estimation and pose estimation. Experiments on the KITTI dataset show that our depth estimation achieves state-of-the-art performance at low resolution. Our source codes will be released on https://***/IRMVLabIPLPE-Depth.

关键词：

Thermally Drawn Monolithic Polymer Continuum Robot with Laser Cutting Profile

学校读者我要写书评

暂无评论

Thermally Drawn Monolithic Polymer Continuum Robot with Lase...

IEEE International Conference on robotics and Biomimetics

作者： Huanghua Liu Yun Zou Zheng Xu Anzhu Gao Department of Automation Institute of Medical Robotics Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai P. R. China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai P. R. China

Continuum robots have the great potential in endoluminal diagnosis and intervention toward narrow and confined workspace. However, fabrication of continuum robots still poses a grant challenge in its miniaturization. To solve this, this paper designs a thermally drawn monolithic polymer continuum robot with laser cutting profile. First, the continuum robot is designed with two degrees of freedom (DOF) for shape deflection, and it consists of four optical fibers with the fiber Bragg grating (FBG) sensor on each for tension sensing as driving cables. Second, its main body is a multi-channel polycarbonate (PC) tube produced by thermal drawing process, and a series of rectangular cutouts are made on it via laser cutting process. By combining these two fabrication processes, the developed continuum robot realizes the integration of the multi-channel structure and the notch feature. Third, a control framework of puller-follower controller using the integrated tension sensing is proposed for teleoperation control. Finally, experimental setup is built for the robot validation, and results show that the repeated positioning accuracy of the robot is 1.08 mm. Moreover, a micro endoscope and a needle are added to the end of the continuum robot, and a phantom study of auripuncture and drug delivery is completed to verify the preliminary feasibility. And the proposed fabrication approach enables the miniaturization and complex structure for the cable-driven continuum robots.

关键词：

MAPPG: Multi-Agent Phasic Policy Gradient

学校读者我要写书评

暂无评论

MAPPG: Multi-Agent Phasic Policy Gradient

IEEE Conference on Decision and control

作者： Qi Zhang Xuetao Zhang Yisha Liu Xuebo Zhang Yan Zhuang Intelligent Robotic Laboratory School of Artificial Intelligence School of Control Science and Engineering Dalian University of Technology Dalian China School of Information Science and Technology Dalian Maritime University Dalian China Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Institute of Robotics and Automatic Information System (IRAIS) Nankai University Tianjin China

We propose a Multi-Agent Phasic Policy Gradient (MAPPG) algorithm, which can assist agents to further alleviate the non-stationarity of the environment. Different from the existing methods, the auxiliary phase is introduced to train the local policy directly by using the environment state, which can be naturally integrated into other algorithms. Specifically, the hidden layer feature sharing is proposed, which ensures feature sharing between the global value network and the local policy network for the first time. Meanwhile, mirror descent is utilized to iteratively update the policy in the auxiliary stage, which makes the policy update more robust. Through a series of evaluations on multi-agent Particle and multi-agent Mujoco benchmark environments, the experimental results show that our method achieves higher rewards than state-of-the-art benchmarks.

关键词：

Topology-Guided Perception-Aware Receding Horizon Trajectory Generation for UAVs

学校读者我要写书评

暂无评论

Topology-Guided Perception-Aware Receding Horizon Trajectory...

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Gang Sun Xuetao Zhang Yisha Liu Hanzhang Wang Xuebo Zhang Yan Zhuang Intelligent Robotic Laboratory School of Artificial Intelligence also School of Control Science and Engineering Dalian University of Technology Dalian China School of Information Science and Technology Dalian Maritime University Dalian China Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence the Institute of Robotics and Automatic Information System (lRAIS) Nankai University Tianjin China

The perception-aware motion planning method based on the localization uncertainty has the potential to improve the localization accuracy for robot navigation. How-ever, most of the existing perception-aware methods pre-build a global feature map and can not generate the perception- aware trajectory in real time. This paper proposes a topology- guided perception-aware receding horizon trajectory generation method, which contains a topology-guided position trajectory generation and a perception-aware yaw angle trajectory generation. Specifically, a memorable active map is built by selectively storing the visual landmarks. After that, a library of candidate topological trajectories are generated, which are then evaluated in terms of the perception quality based on the active map, smoothness, collision possibility and feasibility. In addition, the yaw angle trajectory is obtained through a front-end multiple refined path search and a back-end path- guided trajectory optimization. Comparative simulation and real-world experiments are carried out to confirm that the proposed method can keep more visual features in view and reduce the localization error.

关键词：

ROLL: Long-Term Robust LiDAR-based Localization With Temporary Mapping in Changing Environments

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Peng, Bin Xie, Hongle Chen, Weidong Institute Of Medical Robotics Department Of Automation Shanghai Jiao Tong University Key Laboratory Of System Control And Information Processing Ministry Of Education Shanghai200240 China

Long-term scene changes present challenges to localization systems using a pre-built map. This paper presents a LiDAR-based system that can provide robust localization against those challenges. Our method starts with activation of a mapping process temporarily when global matching towards the pre-built map is unreliable. The temporary map will be merged onto the pre-built map for later localization runs once reliable matching is obtained again. We further integrate a LiDAR inertial odometry (LIO) to provide motion-compensated LiDAR scans and a reliable initial pose guess for the global matching module. To generate a smooth real-time trajectory for navigation purposes, we fuse poses from odometry and global matching by solving a pose graph optimization problem. We evaluate our localization system with extensive experiments on the NCLT dataset including a variety of changing indoor and outdoor environments, and the results demonstrate a robust and accurate localization performance for over a year. The implementations are open sourced on GitHub. © 2022, CC BY.

关键词： Mapping

Unsupervised Learning of 3D Scene Flow from Monocular Camera

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Guangming Tian, Xiaoyu Ding, Ruiqi Wang, Hesheng Department of Automation Institute of Medical Robotics 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 Shanghai 200240 China

Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the ground truth of scene flow for training. Our method realizes the goal that training scene flow network with real-world data, which bridges the gap between training data and test data and broadens the scope of available data for training. Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions. Depth estimation and camera pose estimation obtain the depth maps and camera pose between two consecutive frames, which provide further information for the next scene flow estimation. After that, we used depth consistency loss, dynamic-static consistency loss, Chamfer loss, and Laplacian regularization loss to carry out unsupervised training of the scene flow network. To our knowledge, this is the first paper that realizes the unsupervised learning of 3D scene flow from monocular camera. The experiment results on KITTI show that our method for unsupervised learning of scene flow meets great performance compared to traditional methods Iterative Closest Point (ICP) and Fast Global Registration (FGR). The source code is available at: https://***/IRMVLab/3DUnMonoFlow. Copyright © 2022, The Authors. All rights reserved.

关键词： Unsupervised learning

Frame analysis based real time related indicators measurement of industrial ethernet Powerlink

学校读者我要写书评

暂无评论

Frame analysis based real time related indicators measuremen...

Science and Technology Innovation (IAECST), International Academic Exchange Conference on

作者： Jian Wang Chuang Xie Ce Dong Key Laboratory of Networked Control System Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences ShenYang China

The protocol Powerlink which is one of real-time Ethernet protocols included in the Standard IEC FDIS61784-2, has been widely used for the communication of both IO devices in industrial fields and drives for motor control applications to provide deterministic data transmission. When the Powerlink network is running in the industrial field environment, the online measurement of time related indicators is an appropriate method to evaluate the performance of the network in real time and detect communication faults between devices. In this paper, several time related indicators are proposed and analyzed to estimate the real time performance of the network when all devices get into the operate state. Further more, an efficient method to measure the proposed indicators based on frame analysis is presented and implemented on a PC-based monitor station that stores all the frames which transfer in the network and contain timestamp added by an FPGA-based probe. The measurement method is tested on a real network consisting of one master node and two slave nodes, and some experimental results are presented.

关键词： Performance evaluation Technological innovation Protocols Stability criteria Ethernet Real-time systems Time measurement

DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Mingrui Liu, Shuhong Deng, Tianchen Wang, Hongyu the Department of Computer Science Dalian University of Technology Dalian China the Department of Mechano-informatics Information Science and Technology The University of Tokyo Tokyo Japan Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education China

Gaussian SLAM systems excel in real-time rendering and fine-grained reconstruction compared to NeRF-based systems. However, their reliance on extensive keyframes is impractical for deployment in real-world robotic systems, which typically operate under sparse-view conditions that can result in substantial holes in the map. To address these challenges, we introduce DenseSplat, the first SLAM system that effectively combines the advantages of NeRF and 3DGS. DenseSplat utilizes sparse keyframes and NeRF priors for initializing primitives that densely populate maps and seamlessly fill gaps. It also implements geometry-aware primitive sampling and pruning strategies to manage granularity and enhance rendering efficiency. Moreover, DenseSplat integrates loop closure and bundle adjustment, significantly enhancing frame-to-frame tracking accuracy. Extensive experiments on multiple large-scale datasets demonstrate that DenseSplat achieves superior performance in tracking and mapping compared to current state-of-the-art methods. © 2025, CC BY.

关键词： Real time systems