lidar
PulseAugur coverage of lidar — every cluster mentioning lidar across labs, papers, and developer communities, ranked by signal.
- 2026-05-18 research_milestone A new method for imaging hidden objects using consumer LiDAR was published. source
12 day(s) with sentiment data
-
New imitation learning policy enables autonomous driving in CARLA simulator
Researchers have developed a new imitation learning approach for autonomous driving within the CARLA simulator. This method trains a compact, multimodal policy using historical data including RGB images, LiDAR, vehicle …
-
Robotics startup founder highlights need for diverse talent beyond PhDs
A female founder with a background in liberal arts and marketing has successfully co-founded a robotics startup, Dexory, which has raised $280 million. She emphasizes that the robotics industry, currently dominated by m…
-
New graph-based method evaluates LiDAR simulation fidelity for autonomous driving
Researchers have developed a new graph-based framework to assess the structural fidelity of simulated LiDAR point clouds, which are crucial for validating autonomous driving systems. This method goes beyond traditional …
-
New transformer network RoofSeg improves end-to-end roof plane segmentation
Researchers have developed RoofSeg, a novel transformer-based network designed for end-to-end roof plane segmentation from LiDAR point clouds. This approach addresses limitations in existing methods, such as suboptimal …
-
LLM-based framework optimizes robot swarm perception
Researchers have developed CoAdapt, a new framework that uses a Large Language Model (LLM) to manage collaborative perception in industrial Internet of Things (IIoT) robotic swarms. This LLM-driven approach dynamically …
-
SAVTrack improves 3D LiDAR tracking with selective vote aggregation · 2 sources tracked
Researchers have developed SAVTrack, a new framework for 3D single object tracking in LiDAR point clouds that addresses challenges posed by sparse and incomplete data. The system employs Selective Vote Aggregation (SAV)…
-
New GRAFT-Stereo Method Enhances LiDAR-Guided Stereo Matching
Researchers have developed a new method called Guided RAFT-Stereo (GRAFT-Stereo) to improve stereo matching using sparse LiDAR data. Their analysis revealed that existing iterative stereo methods struggle to effectively…
-
ESAFusion framework enhances 3D object detection by fusing LiDAR and 4D radar data
Researchers have developed ESAFusion, a novel framework for 3-D object detection that enhances accuracy by fusing data from LiDAR and 4-D radar. The system addresses challenges like sparse radar data and differing spati…
-
New PRI-Net framework enhances 3D UAV localization with multimodal fusion
Researchers have developed PRI-Net, a novel lightweight framework designed to improve the 3D localization accuracy of unmanned aerial vehicles (UAVs). This framework addresses challenges such as sparse LiDAR data, imbal…
-
New multi-vehicle dataset released for autonomous driving research
A new multi-vehicle dataset has been released, featuring synchronized data from cameras, LiDAR, and radar sensors, along with scanned 3D models of vehicles. This dataset aims to provide a highly detailed reference for a…
-
LiDAR-only cone detection framework runs on CPU for driverless racing
Researchers have developed a lightweight, LiDAR-only perception system for Formula Student Driverless vehicles that runs efficiently on a CPU. This system utilizes a Random Forest classifier, ground removal, IMU-based m…
-
MC-DeTra enhances autonomous driving with unified detection and forecasting
Researchers have introduced MC-DeTra, a novel approach that unifies object detection and trajectory forecasting for autonomous driving systems. This method enhances the accuracy of predicting the movements of dynamic ac…
-
KODAMA pipeline reconstructs urban RF digital twins from geospatial data
Researchers have developed KODAMA, an automated pipeline for reconstructing radio frequency digital twins (RFDTs) of urban environments. This system utilizes off-the-shelf geospatial data such as aerial imagery, LiDAR, …
-
New DCReg method enhances LiDAR registration accuracy and speed
Researchers have developed DCReg, a novel method for improving LiDAR point cloud registration, particularly in challenging, degenerate environments like corridors. This new approach systematically detects, characterizes…
-
LiDAR diffusion model bridges 2D and 3D data representations
Researchers have developed a novel approach using a LiDAR-conditioned diffusion model to bridge the gap between 2D and 3D data representations. This model, trained on pseudo-labels derived from existing 2D foundation mo…
-
DAGLFNet improves pseudo-image point cloud segmentation with novel fusion techniques
Researchers have developed DAGLFNet, a new framework for semantic segmentation of pseudo-image point clouds. This method addresses the challenge of fusing 2D and 3D data by incorporating a Global-Local Feature Fusion En…
-
New Gaussian Linear Functional Manifold method reconstructs terrain from LiDAR data
Researchers have developed a new statistical framework called the Gaussian Linear Functional Manifold (GLFM) to reconstruct continuous terrain from massive airborne LiDAR point clouds. This method uses deterministic lin…
-
EgoNeMo framework uses LiDAR for transferable pedestrian motion maps
Researchers have developed EgoNeMo, a novel framework for creating transferable Maps of Dynamics (MoD) using egocentric 3D LiDAR scans. This approach addresses the limitations of traditional MoD methods, which require e…
-
New multi-modal perception pipeline enhances autonomous racing safety
Researchers have developed a new multi-modal perception pipeline designed for object detection and tracking in autonomous racing. This system integrates data from cameras, LiDAR, and RADAR using a late-fusion approach t…
-
TFTrack framework offers efficient template-free 3D point cloud tracking
Researchers have introduced TFTrack, a novel framework designed for efficient 3D point cloud tracking using LiDAR data. This template-free approach simplifies existing Siamese tracking methods by eliminating the need fo…