检索结果-内蒙古大学图书馆

Navigated Locomotion and Controllable Splitting of a Microswarm in a Complex Environment

学校读者我要写书评

暂无评论

Navigated Locomotion and Controllable Splitting of a Microsw...

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

作者： Yuezhen Liu Guangjun Zeng Xingzhou Du Kaiwen Fang Jiangfan Yu School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS) Shenzhen China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Reconfigurable microswarms have received extensive attention recently. In this work, we propose a control strategy for a ribbon-like swarm to perform navigated locomotion with a stable pattern, and perform controllable splitting into double subswarms to reach two targets simultaneously. Two different behaviors of the ribbon-like swarm are firstly investigated, i.e., locomotion with a stable pattern, and controllable splitting. The two behaviors of the ribbon-like swarm are realized based on different aspect ratio of the swarm. Subsequently, we propose a morphology controller to keep the aspect ratio of the swarm within a desired range. The morphology controller consists of a feedforward controller and a PD controller. The feedforward controller containing a fitted model, and a fuzzy logic controller for online compensation of the model error. The control strategy combining the morphology planning, morphology controller, path planning, and motion controller is developed. Using the proposed control strategy, the ribbon-like swarm can be navigated to follow a desired path with a stable pattern while avoiding obstacles, and finally perform controllable splitting into double subswarms to reach two predefined targets simultaneously.

关键词： Fuzzy logic Motion planning Navigation Morphology Path planning Planning PD control Feedforward systems Intelligent robots

PSEUDO LABELS REFINEMENT WITH INTRA-CAMERA SIMILARITY FOR UNSUPERVISED PERSON RE-IDENTIFICATION

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Pengna Wu, Kangyi Zhou, Sanping Huang, Qianxin Wang, Jinjun Xi’an Jiaotong University Institute of Artificial Intelligence and Robotics 28 West Xianning Road Shaanxi Xi’an China

Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise caused by domain shifts among different cameras, leading to inevitable performance degradation. To address this challenge, we propose a novel label refinement framework with clustering intra-camera similarity. Intra-camera feature distribution pays more attention to the appearance of pedestrians and labels are more reliable. We conduct intra-camera training to get local clusters in each camera, respectively, and refine inter-camera clusters with local results. We hence train the Re-ID model with refined reliable pseudo labels in a self-paced way. Extensive experiments demonstrate that the proposed method surpasses state-of-the-art performance. © 2023, CC0.

关键词： Cameras

Structured Click Control in Transformer-based Interactive Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Long Chen, Yongquan Huang, Rui Wu, Feng Lai, Shiwu Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen China Maxvision Technology Corp. Shenzhen China

Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it’s hard for existing algorithms to obtain precise and robust responses after multiple clicks. In this case, the segmentation results tend to have little change or are even worse than before. To improve the robustness of the response, we propose a structured click intent model based on graph neural networks, which adaptively obtains graph nodes via the global similarity of user-clicked Transformer tokens. Then the graph nodes will be aggregated to obtain structured interaction features. Finally, the dual cross-attention will be used to inject structured interaction features into vision Transformer features, thereby enhancing the control of clicks over segmentation results. Extensive experiments demonstrated the proposed algorithm can serve as a general structure in improving Transformer-based interactive segmentation performance. The code and data will be released at SCC. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

Path Planning of Autonomous Underwater Vehicle Departing from Port Based on Improved Deep Q-Network

学校读者我要写书评

暂无评论

Path Planning of Autonomous Underwater Vehicle Departing fro...

International Conference on Intelligent Autonomous Systems (ICoIAS)

作者： Chen Li Meng Joo Er Tianhe Liu Guohong Jiang Institute of Artificial Intelligence and Marine Robotics College of Marine Electrical Engineering Dalian Maritime University Dalian China

This paper presents a path planning scheme for autonomous underwater vehicle (AUV) in port environment based on improved Deep Q-Network (DQN) algorithm. First, port map is gridded and binarized, and port area is separated from other areas according to port shape. Secondly, in order to enable the agent to leave port area, the range of agent exploration randomness is increased in port area. Finally, to solve the problem that the traditional DQN algorithm is difficult to make the agent find the target point after leaving port area quickly, the reward function of DQN is improved. Simulation results verify the effectiveness and efficiency of the proposed scheme.

关键词：

From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Yabing Tian, Zhuotao Guo, Qingpei Qin, Zheng Zhou, Sanping Yang, Ming Wang, Le Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China Harbin Institute of Technology Shenzhen518071 China Ant Group Hangzhou310000 China

Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of annotating CIR triplet datasets, zero-shot (ZS) CIR has gained traction as a promising alternative. Existing studies mainly focus on projection-based methods, which map an image to a single pseudo-word token. However, these methods face three critical challenges: (1) insufficient pseudo-word token representation capacity, (2) discrepancies between training and inference phases, and (3) reliance on large-scale synthetic data. To address these issues, we propose a two-stage framework where the training is accomplished from mapping to composing. In the first stage, we enhance image-to-pseudo-word token learning by introducing a visual semantic injection module and a soft text alignment objective, enabling the token to capture richer and fine-grained image information. In the second stage, we optimize the text encoder using a small amount of synthetic triplet data, enabling it to effectively extract compositional semantics by combining pseudo-word tokens with modification text for accurate target image retrieval. The strong visual-to-pseudo mapping established in the first stage provides a solid foundation for the second stage, making our approach compatible with both high- and low-quality synthetic data, and capable of achieving significant performance gains with only a small amount of synthetic data. Extensive experiments were conducted on three public datasets, achieving superior performance compared to existing approaches. Copyright © 2025, The Authors. All rights reserved.

关键词： Photointerpretation

Monocular object SLAM using quadrics and landmark reference map for outdoor UAV applications

学校读者我要写书评

暂无评论

Monocular object SLAM using quadrics and landmark reference ...

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Shao, Pengtao Mo, Fan Chen, Yaqian Ding, Ning Huang, Rui Shenzhen Institute of Artificial Intelligence and Robotics for Society Institute of Robotics and Intelligent Manufacturing Chinese University of Hong Kong Shenzhen Guangdong Shenzhen518172 China

ISBN: (纸本)9781665436786

Localization is one of the core technologies commonly applied in Unmanned Aerial Vehicles (UAVs) in urban fields. Most UAVs use Global Navigation Satellite System (GNSS) to estimate their positions, whereas the GNSS signal can be affected by the occlusion of buildings in urban areas. We use a visual positioning method based on the monocular camera sensor information and offline reference map in the GNSS-denied environments to address this problem. Our goal is to obtain the UAV's pose data and the corresponding GPS position data by matching the simultaneous map with the reference landmark map. In order to adapt to the flight environment of different altitudes and different perspectives, we propose a monocular semantic SLAM system to provide long-range visual tracking and mapping of landmark buildings together with the feature points. Our SLAM system's landmark object is described in quadratic form, which contains information about its 3D position and poses to increase awareness of the environment. The system we propose provides positioning results with meter-level accuracy and improves the impact of accumulated visual SLAM errors. © 2021 IEEE.

关键词： Unmanned aerial vehicles (UAV)

LOCAL-PROMPT: EXTENSIBLE LOCAL PROMPTS FOR FEW-SHOT OUT-OF-DISTRIBUTION DETECTION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Fanhu Cheng, Zhen Zhu, Fei Wei, Hongxin Zhang, Xu-Yao State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS Hong Kong Department of Statistics and Data Science Southern University of Science and Technology China

Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories, has gained prominence in practical scenarios. Recently, the advent of vision-language models (VLM) has heightened interest in enhancing OOD detection for VLM through few-shot tuning. However, existing methods mainly focus on optimizing global prompts, ignoring refined utilization of local information with regard to outliers. Motivated by this, we freeze global prompts and introduce Local-Prompt, a novel coarse-to-fine tuning paradigm to emphasize regional enhancement with local prompts. Our method comprises two integral components: global prompt guided negative augmentation and local prompt enhanced regional regularization. The former utilizes frozen, coarse global prompts as guiding cues to incorporate negative augmentation, thereby leveraging local outlier knowledge. The latter employs trainable local prompts and a regional regularization to capture local information effectively, aiding in outlier identification. We also propose regional-related metric to empower the enrichment of OOD detection. Moreover, since our approach explores enhancing local prompts only, it can be seamlessly integrated with trained global prompts during inference to boost the performance. Comprehensive experiments demonstrate the effectiveness and potential of our method. Notably, our method reduces average FPR95 by 5.17% against state-of-the-art method in 4-shot tuning on challenging ImageNet-1k dataset, even outperforming 16-shot results of previous methods. Code is released at https://***/AuroraZengfh/Local-Prompt. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

Millipede-Inspired Multi-legged Magnetic Soft Robots for Targeted Locomotion in Tortuous Environments

学校读者我要写书评

暂无评论

Millipede-Inspired Multi-legged Magnetic Soft Robots for Tar...

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

作者： Yibin Wang Yiting Xiong Kaiwen Fang Jiangfan Yu School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS) Shenzhen China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Miniature robots capable of untethered operation hold great promise for performing diagnostic and therapeutic procedures in hard-to-reach regions within the human body. Nonetheless, navigating these complex and diverse physiological environments remains a significant challenge. To effectively navigate the tortuous pathways inside the human body, it is essential to equip miniature robots with flexible body structures that can adapt to complex geometries and develop efficient actuation strategies for deformed robots. In this study, we present a miniature soft robot featuring a zigzag body structure, imparting the robot with remarkable deformation capabilities that enable it to adapt to confined and tortuous spaces. This robot is equipped with arrays of magnetic legs, enabling robust locomotion propelled by traveling metachronal waves. We demonstrate that the robot can crawl on both flat surfaces and slopes. Leveraging its in-plane flexibility and discrete actuation system, this robot can navigate through intricate environments with precise control using magnetic fields. Our work provides valuable insights into the development of crawling robots with enhanced agility and adaptability, creating opportunities for their future use in a wide range of biomedical applications.

关键词： Legged locomotion Navigation Surface waves Magnetic resonance imaging Magnetic confinement Soft robotics Robot sensing systems Drug delivery Magnetosphere Robots

ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Zhiyuan Wei, Yuxiang Zhang, Yabin Zhu, Xiangyu Lei, Zhen Zhang, Lei The Hong Kong Polytechnic University PolyU Hong Kong Center for Artificial Intelligence and Robotics HKISI CAS Hong Kong State Key Laboratory of Multimodal Artificial Intelligence Systems CASIA China School of Artificial Intelligence University of Chinese Academy of Sciences UCAS China Harbin Institute of Technology HIT China

By leveraging the text-to-image diffusion priors, score distillation can synthesize 3D contents without paired text-3D training data. Instead of spending hours of online optimization per text prompt, recent studies have been focused on learning a text-to-3D generative network for amortizing multiple text-3D relations, which can synthesize 3D contents in seconds. However, existing score distillation methods are hard to scale up to a large amount of text prompts due to the difficulties in aligning pretrained diffusion prior with the distribution of rendered images from various text prompts. Current state-of-the-arts such as Variational Score Distillation finetune the pretrained diffusion model to minimize the noise prediction error so as to align the distributions, which are however unstable to train and will impair the model’s comprehension capability to numerous text prompts. Based on the observation that the diffusion models tend to have lower noise prediction errors at earlier timesteps, we propose Asynchronous Score Distillation (ASD), which minimizes the noise prediction error by shifting the diffusion timestep to earlier ones. ASD is stable to train and can scale up to 100k prompts. It reduces the noise prediction error without changing the weights of pre-trained diffusion model, thus keeping its strong comprehension capability to prompts. We conduct extensive experiments across different 2D diffusion models, including Stable Diffusion and MVDream, and text-to-3D generators, including Hyper-iNGP, 3DConv-Net and Triplane-Transformer. The results demonstrate ASD’s effectiveness in stable 3D generator training, high-quality 3D content synthesis, and its superior prompt-consistency, especially under large prompt corpus. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation