Latest Publications & Patents on 3D SLAM
This is our latest selection of worldwide publications and patents in english on 3D SLAM, between many scientific online journals, classified and focused on SLAM, LiDAR, point cloud, scan matching, feature extraction, loop closure, simultaneous localization, localization and mapping, odometry, Kalman filter, object detection, iterative closest point, voxel grid and 3D reconstruction.
Tip: further to this selection on 3D SLAM, you can search and filter our:
* free publications search tool * by author, topic, keywords, date or journal.
* free patents search tool * for patents in english from the European Patent Office.
Intelligent Analysis of Flow Field in Cleaning Chamber for Combine Harvester Based on YOLOv8 and Reasoning Mechanism
Published on 2025-02-19 by Qinglin Li, Ruihai Wan, Zhaoyue Wu, Yuting Yan, Xihan Zhang @MDPI
Abstract: As the main working part of a combine harvester, the cleaning device affects the cleaning performance of the machine. The simulation of flow fields in a cleaning chamber has become an important part of the design. Currently, post-processing analyses of flow field simulation still rely on the researchers’ experience, so it is difficult to obtain information from post-processing automatically. The experience of researchers is difficult to describe and disseminate. This paper studied [...]
Our summary: Intelligent analysis of flow field in cleaning chamber for combine harvester based on YOLOv8 and reasoning mechanism. Study focuses on using object detection algorithm and reasoning mechanism to automatically analyze simulation result data for cleaning device performance improvement. System established in Python 3.10 software for automatic flow field characteristics and wind effects analysis.
Flow Field Analysis, Cleaning Chamber, YOLOv8, Reasoning Mechanism
Publication
Flexible Optimal Control of the CFBB Combustion System Based on ESKF and MPC
Published on 2025-02-19 by Lei Han, Lingmei Wang, Enlong Meng, Yushan Liu, Shaoping Yin @MDPI
Abstract: In order to deeply absorb the power generation of new energy, coal-fired circulating fluidized bed units are widely required to participate in power grid dispatching. However, the combustion system of the units faces problems such as decreased control performance, strong coupling of controlled signals, and multiple interferences in measurement signals during flexible operation. To this end, this paper proposes a model predictive control (MPC) scheme based on the extended state Kalman filter (ESK[...]
Our summary: This paper proposes a flexible optimal control scheme for the CFBB combustion system based on ESKF and MPC. The ESKF is used to filter output signals and estimate state and disturbance quantities in real time. The MPC framework is optimized to achieve optimal control signals within each control cycle, resulting in improved control performance and robustness.
ESKF, MPC, CFBB Combustion System, Optimal Control
Publication
Three-Dimensional Magnetotelluric Forward Modeling Using Multi-Task Deep Learning with Branch Point Selection
Published on 2025-02-19 by Fei Deng, Hongyu Shi, Peifan Jiang, Xuben Wang @MDPI
Abstract: Magnetotelluric (MT) forward modeling is a key technique in magnetotelluric sounding, and deep learning has been widely applied to MT forward modeling. In three-dimensional (3-D) problems, although existing methods can predict forward modeling results with high accuracy, they often use multiple networks to simulate multiple forward modeling parameters, resulting in low efficiency. We apply multi-task learning (MTL) to 3-D MT forward modeling to achieve simultaneous inference of apparent resistiv[...]
Our summary: Three-Dimensional Magnetotelluric Forward Modeling is enhanced through Multi-Task Deep Learning with Branch Point Selection, improving efficiency and accuracy with a novel network structure.
Three-Dimensional, Magnetotelluric, Forward Modeling, Multi-Task Deep Learning
Publication
CNN–Transformer Hybrid Architecture for Underwater Sonar Image Segmentation
Published on 2025-02-19 by Juan Lei, Huigang Wang, Zelin Lei, Jiayuan Li, Shaowei Rong @MDPI
Abstract: The salient object detection (SOD) of forward-looking sonar images plays a crucial role in underwater detection and rescue tasks. However, the existing SOD algorithms find it difficult to effectively extract salient features and spatial structure information from images with scarce semantic information, uneven intensity distribution, and high noise. Convolutional neural networks (CNNs) have strong local feature extraction capabilities, but they are easily constrained by the receptive field and l[...]
Our summary: Hybrid architecture combining CNN, Transformer, and Mamba for underwater sonar image segmentation, addressing challenges of salient object detection in images with scarce semantic information, uneven intensity distribution, and high noise. Achieves outstanding competitiveness among state-of-the-art methods with MAE and E values of 0.04 and 0.973.
Transformer, CNN, underwater sonar, image segmentation
Publication
Closed-Loop Transient Longitudinal Trajectory Tracking for Connected Vehicles
Published on 2025-02-19 by Lingyun Hua, Guoming Zhu @MDPI
Abstract: Vehicle longitudinal trajectory tracking plays a significant role in developing ecorouting and autonomous driving systems to handle various disturbances and uncertainties (e.g., road grade, gust wind, etc.) that are often ignored by the optimization strategies used to generate reference controls and trajectories. In this paper, based on a linearized vehicle model with the help of feedback linearization, a linear quadratic integral tracking (LQIT) control is utilized to generate regulation laws t[...]
Our summary: Linearized vehicle model with feedback linearization used to develop LQIT control for optimal speed and brake distance trajectories, unified Kalman filter for state estimation, simulation studies validate effectiveness.
Closed-Loop, Transient, Longitudinal, Trajectory Tracking
Publication
Wave Attenuation by Australian Temperate Mangroves
Published on 2025-02-19 by Ruth Reef, Sabrina Sayers @MDPI
Abstract: Wave attenuation by natural coastal features is recognised as a soft engineering approach to shoreline protection from storm surges and destructive waves. The effectiveness of wave energy dissipation is determined, in part, by vegetation structure, extent, and distribution. Mangroves line ca. 15% of the world’s coastlines, primarily in tropical and subtropical regions but also extending into temperate climates, where mangroves are shorter and multi-stemmed. Using wave loggers deplo[...]
Our summary: Effectiveness of wave energy dissipation by Australian temperate mangroves studied using wave loggers and UAV-derived point cloud. Wave attenuation coefficient and drag coefficient calculated, highlighting the significant role of near-bed friction.
wave attenuation, mangroves, vegetation structure, drag coefficient
Publication
Point cloud feature recognition and labeling algorithm based on improved pointnet++
Patent published on the 2025-01-30 in WO under Ref WO2025020476 by UNIV DALIAN TECH [CN] (Wang Ji [cn], Huo Shilin [cn], Cheng Xin [cn], Zhao Yirong [cn], Li Rui [cn], Liu Xiao [cn])
Abstract: Disclosed in the present invention are a point cloud feature recognition and labeling algorithm based on improved PointNet++. The algorithm comprises a supervoxel growth method suitable for a deep learning network, and a deep learning network suitable for large-component scan data. In the method, PointNet++ is improved, a deep learning network suitable for large-scale point cloud recognition is constructed, and point clouds in regions are processed, the interrelationship between the point clouds[...]
Our summary: Improved PointNet++ algorithm for point cloud feature recognition and labeling, including supervoxel growth method and deep learning network for large-component scan data, solving technical problem of processing large-scale point clouds.
point cloud, feature recognition, labeling algorithm, PointNet++
Patent
Deepgbm-based vehicle collision detection method and system based
Patent published on the 2025-01-29 in ZA under Ref ZA202404259 by UNIV HENAN URBAN CONSTRUCTION [CN] (Zhang Jingpu [cn], Yan Xiaoyan [cn], Zhao Junmin [cn], Wang Chong [cn])
Abstract: The present invention discloses a DeepGBM-based vehicle collision detection method and system, and relates to the field of vehicle collision detection. The method includes the following steps: acquiring driving data of vehicles to be detected; preprocessing the driving data to obtain preprocessed driving data; performing feature extraction on the preprocessed driving data to obtain feature data; and inputting the feature data into a DeepGBM model to obtain collision results of the vehicles to be[...]
Our summary: DeepGBM-based vehicle collision detection method and system utilizing driving data preprocessing, feature extraction, and DeepGBM model to enhance accuracy.
DeepGBM, vehicle collision detection, method, system
Patent
EN 
FR 
DE 
ES 
IT