检索结果-内蒙古大学图书馆

Closed-Loop Placement Planning for Regrasping and Reconstruction With Single-View RGB-D Images

学校读者我要写书评

暂无评论

IEEE Transactions on Automation Science and Engineering 2025年 22卷 14084-14095页

作者： Chen, Zhiyuan Liu, Jiangshan Chen, Ronghao Wang, Jiankun Southern University of Science and Technology Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Shenzhen518055 China Southern University of Science and Technology Jiaxing Research Institute Jiaxing030024 China

In robotic reorientation, achieving certain positions or orientations within a workspace can be difficult due to collisions and interference between objects and the environment. Regrasping is a technology that overcomes limitations on object reorientation using multiple pick-and-place actions. However, constructing a regrasping graph, which consists of predicted intermediate placements, is challenging with only partial observations of unknown objects. To address this challenge, we design a closed-loop placement planning system using single-view RGB-D images. This system seamlessly integrates perception and manipulation processes, capturing RGB-D images for object reconstruction while predicting intermediate placements for constructing regrasping graphs simultaneously. To optimize the regrasping graph construction, we propose a Truncated Signed Distance Function (TSDF)-based placement evaluation algorithm that selects the next-best-placement by estimating the information gain and retention of the placements. Additionally, we adopt a novel data fusion method based on predicted intermediate placements to enhance object reconstruction and TSDF updates, effectively mitigating in-hand errors. Our system surpasses baselines in accuracy and diversity of placement predictions. It demonstrates superior performance in object reconstruction, excelling in quantitative analysis and visualization. Real-world experiments validate the effectiveness of our system in reorientation and reconstruction tasks on real industrial parts, demonstrating its robustness and applicability in practical scenarios. © 2004-2012 IEEE.

关键词： Data fusion

A Hierarchical Progressive perception System for Autonomous Luggage Trolley Collection

学校读者我要写书评

暂无评论

IEEE Transactions on Automation Science and Engineering 2025年 22卷 14484-14497页

作者： Sun, Zhirui Zhang, Zhe Zhao, Jieting Ye, Hanjing Wang, Jiankun Southern University of Science and Technology Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Shenzhen518055 China Southern University of Science and Technology Jiaxing Research Institute Jiaxing314000 China Southern University of Science and Technology Shenzhen Key Laboratory of Robotics and Computer Vision Department of Electronic and Electrical Engineering Shenzhen518055 China

Advancements in intelligent vehicle technologies and autonomous driving are now used for tasks like collecting luggage trolleys at airports. The robotic autonomous luggage trolley collection system employs robots to gather and transport scattered luggage trolleys. However, existing methods for detecting and locating luggage trolleys often fail when they are not fully visible. To address this, we introduce the hierarchical progressive perception system, which enhances the detection and localization of luggage trolleys under partial occlusion. The proposed system integrates the hierarchical process structure and progressive perception strategy. This innovative structure processes the luggage trolley’s position and orientation separately. It can accurately determine the luggage trolley’s position with just one well-detected keypoint and estimate its orientation when partially occluded. Once the luggage trolley’s initial pose is detected, the progressive perception strategy continuously refines this information until the robot begins grasping. The proposed system only needs RGB images for labeling and training, eliminating the need for complex data collection and annotation. The experiments on detection and localization demonstrate that the proposed system is more reliable under partial occlusion compared to existing methods. Its effectiveness and robustness have also been confirmed through practical tests in actual luggage trolley collection tasks. © 2004-2012 IEEE.

关键词： Intelligent robots

FAST-LIVO2 on Resource-Constrained Platforms: LiDAR-Inertial-Visual Odometry with Efficient Memory and Computation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhou, Bingyang Zheng, Chunran Wang, Ziming Zhu, Fangcheng Cai, Yixi Zhang, Fu Laboratory Department of Mechanical Engineering University of Hong Kong Hong Kong Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden

This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a degeneration-aware adaptive visual frame selector into error-state iterated Kalman filter (ESIKF) with sequential updates, improving computation efficiency significantly while maintaining a similar level of robustness. Additionally, a memory-efficient mapping structure combining a locally unified visual-LiDAR map and a long-term visual map achieves a good trade-off between performance and memory usage. Extensive experiments on x86 and ARM platforms demonstrate the system’s robustness and efficiency. On the Hilti dataset, our system achieves a 33% reduction in per-frame runtime and 47% lower memory usage compared to FAST-LIVO2, with only a 3 cm increase in RMSE. Despite this slight accuracy trade-off, our system remains competitive, outperforming state-of-the-art (SOTA) LIO methods such as FAST-LIO2 and most existing LIVO systems. These results validate the system’s capability for scalable deployment on resource-constrained edge computing platforms. Copyright © 2025, The Authors. All rights reserved.

关键词： Kalman filters

DDH-Net:A Dual Dynamic Head Network for Transmission Line Inspection

学校读者我要写书评

暂无评论

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Yu, Junlong Mao, Jianxu Wang, Yaonan He, Zhenyu Yi, Junfei Tao, Ziming Zhang, Hui Wang, Shaoyuan Hunan University College of Electrical and Information Engineering Hunan Changsha410012 China Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Robotics Hunan Changsha410082 China

Transmission lines are a critical component of an electrical grid, and ensuring their effective detection is of utmost importance. However, problems such as fine-grained identification, target occlusion, and background complexity in aerial transmission line images challenge existing transmission line detection methods. This paper presents a dual dynamic head network (DDH-Net) to address the aforementioned issues. This network incorporates a dual dynamic head (DDH) composed of a multifeature fusion module (MFFM) and deformable convolution. DDH leverages deformable convolution to enhance the network's focus on the target of interest. Subsequently, the MFFM enhances the feature representation capabilities for individual targets, leading to discriminative feature extraction and improving the network's accuracy in detecting similar targets. Furthermore, we introduce the wise area intersection over union (WAIoU) loss, which reduces the network's attention on detection boxes that contain only partial target content through the adaptive allocation of loss weights to anchor boxes to mitigate occlusion-induced interference. Additionally, we incorporate area as a constraint to further enhance the network's localization accuracy. Finally, extensive experiments were conducted on a power transmission line dataset. The results demonstrated the superiority of the proposed module over other state-of-the-art (SOTA) methods. © 1963-2012 IEEE.

关键词： Convolution

ROLO-SLAM: Rotation-Optimized LiDAR-Only SLAM in Uneven Terrain with Ground Vehicle

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Yinchuan Ren, Bin Zhang, Xiang Wang, Pengyu Wang, Chaoqun Song, Rui Li, Yibin Meng, Max Q.-H. School of Control Science and Engineering Shandong University Jinan China Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

LiDAR-based SLAM is recognized as one effective method to offer localization guidance in rough environments. However, off-the-shelf LiDAR-based SLAM methods suffer from significant pose estimation drifts, particularly components relevant to the vertical direction, when passing to uneven terrains. This deficiency typically leads to a conspicuously distorted global map. In this article, a LiDAR-based SLAM method is presented to improve the accuracy of pose estimations for ground vehicles in rough terrains, which is termed Rotation-Optimized LiDAR-Only (ROLO) SLAM. The method exploits a forward location prediction to coarsely eliminate the location difference of consecutive scans, thereby enabling separate and accurate determination of the location and orientation at the front-end. Furthermore, we adopt a parallel-capable spatial voxelization for correspondence-matching. We develop a spherical alignment-guided rotation registration within each voxel to estimate the rotation of vehicle. By incorporating geometric alignment, we introduce the motion constraint into the optimization formulation to enhance the rapid and effective estimation of LiDAR's translation. Subsequently, we extract several keyframes to construct the submap and exploit an alignment from the current scan to the submap for precise pose estimation. Meanwhile, a global-scale factor graph is established to aid in the reduction of cumulative errors. In various scenes, diverse experiments have been conducted to evaluate our method. The results demonstrate that ROLO-SLAM excels in pose estimation of ground vehicles and outperforms existing state-of-the-art LiDAR SLAM frameworks. Copyright © 2025, The Authors. All rights reserved.

关键词： Magnetic levitation vehicles

An Improved Dual Neural Network Method Based on Levy Flight for Multi-Robot Cooperative Area Coverage Search in 3D Unknown Environments

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Zhang, Fangfang Wang, Yongqi Wang, Wenhao Xin, Jianbin Peng, Jinzhu Wang, Yaonan Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471039 China National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

The research on multi-robot collaborative search in unknown 3D environments, based on bio-inspired neural networks, holds significant value and ***, challenges arise in 3D environments, including excessive turning and vertical movement, as well as the potential for collisions between robots. In response, we propose an improved Glasius Bio-Inspired Neural Network(GBNN) that mitigates decision conflicts among robots and considers the impact of turning and vertical movement on robot decision-making. Furthermore, to address the issue of robots getting trapped in local deadlocks during the search process, we present a dual neural network algorithm based on Levy flights. In the method Dual Glasius Bio-Inspired Neural Network based on Levy Flight(LF-DUAL-GBNN) proposed in this paper, robots obtain random target points through Levy flights and are then guided by a dual neural network to navigate to the vicinity of the target points, thus breaking free from local deadlock states. Finally, we conducted simulation experiments to validate the algorithm's effectiveness. © 2016 IEEE.

关键词： Microrobots

Learning-based Detection of GPS Spoofing Attack for Quadrotors

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Pengyu Yang, Zhaohua Li, Jialu Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

Safety-critical cyber-physical systems (CPS), such as quadrotor UAVs, are particularly prone to cyber attacks, which can result in significant consequences if not detected promptly and accurately. During outdoor operations, the nonlinear dynamics of UAV systems, combined with non-Gaussian noise, pose challenges to the effectiveness of conventional statistical and machine learning methods. To overcome these limitations, we present QUADFormer, an advanced attack detection framework for quadrotor UAVs leveraging a transformer-based architecture. This framework features a residue generator that produces sequences sensitive to anomalies, which are then analyzed by the transformer to capture statistical patterns for detection and classification. Furthermore, an alert mechanism ensures UAVs can operate safely even when under attack. Extensive simulations and experimental evaluations highlight that QUADFormer outperforms existing state-of-the-art techniques in detection accuracy. (Video1) Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

Optimal Actuator Attacks on Autonomous Vehicles Using Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Pengyu Li, Jialu Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

With the increasing prevalence of autonomous vehicles (AVs), their vulnerability to various types of attacks has grown, presenting significant security challenges. In this paper, we propose a reinforcement learning (RL)-based approach for designing optimal stealthy integrity attacks on AV actuators. We also analyze the limitations of state-of-the-art RL-based secure controllers developed to counter such attacks. Through extensive simulation experiments, we demonstrate the effectiveness and efficiency of our proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

E-3DGS: 3D Gaussian splatting with exposure and motion events

学校读者我要写书评

暂无评论

Applied Optics 2025年第14期64卷 3897-3908页

作者： Xiaoting Yin Hao Shi Yuhan Bao Zhenshan Bing Yiyi Liao Kailun Yang Kaiwei Wang State Key Laboratory of Modern Optical Instrumentation Zhejiang University Hangzhou China yinxiaoting@*** The Chair of Robotics AI and Real-Time Systems Technical University of Munich Munich Germany College of Information Science and Electronic Engineering Zhejiang University Hangzhou China School of Robotics and National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha China kailun.yang@***

Achieving 3D reconstruction from images captured under optimal conditions has been extensively studied in the vision and imaging fields. However, in real-world scenarios, challenges such as motion blur and insufficient illumination often limit the performance of standard frame-based cameras in delivering high-quality images. To address these limitations, we incorporate a transmittance adjustment device at the hardware level, enabling event cameras to capture both motion and exposure events for diverse 3D reconstruction scenarios. Motion events (triggered by camera or object movement) are collected in fast-motion scenarios when the device is inactive, while exposure events (generated through controlled camera exposure) are captured during slower motion to reconstruct grayscale images for high-quality training and optimization of event-based 3D Gaussian splatting (3DGS). Our framework supports three modes: high-quality reconstruction using exposure events, fast reconstruction relying on motion events, and balanced hybrid optimizing with initial exposure events followed by high-speed motion events. On the EventNeRF dataset, we demonstrate that exposure events significantly improve fine detail reconstruction compared to motion events and outperform frame-based cameras under challenging conditions such as low illumination and overexposure. Furthermore, we introduce EME-3D, a real-world 3D dataset with exposure events, motion events, camera calibration parameters, and sparse point clouds. Our method achieves faster and higher-quality reconstruction than event-based NeRF and is more cost-effective than methods combining event and RGB data. By combining motion and exposure events, E-3DGS sets a new benchmark for event-based 3D reconstruction with robust performance in challenging conditions and lower hardware demands. The source code and dataset are available on GitHub.

关键词： Camera calibration Image reconstruction Image resolution Imaging systems Point clouds Three dimensional reconstruction