PDES-Net: LiDAR point cloud semantic segmentation network based on point-wise distance encoding and pointed-seg head
To address the above problem, we propose a network model, PDES-Net.
Engineering 5.5 · Research 7.0 · Business 5.0
LiDAR Perception - Autonomous Driving Papers, Code and Research Roadmap
LiDAR-based 3D perception for autonomous driving — point cloud processing, 3D detection, segmentation, compression and sensor fusion with cameras and radar.
Design of a Deep Learning-Based Intelligent Driving Decision System for Vehicle Engineering and Adaptability Verification in Complex Road Conditions
An autonomous driving research paper: Design of a Deep Learning-Based Intelligent Driving Decision System for Vehicle Engineering and Adaptability Verification in Complex Road Conditions.
Engineering 5.5 · Research 7.0 · Business 5.0
A data efficiency study of synthetic fog for object detection using the Clear2Fog pipeline
In this paper, we propose Clear2Fog (C2F), an end-to-end, physics-based pipeline that simulates fog for clear-weather datasets under a unified camera and LiDAR framework.
Engineering 6.5 · Research 8.0 · Business 6.5
CRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Driving
To address this limitation, we propose CRUISE, a novel uncertainty-aware cross-modal sensor fusion framework.
Engineering 5.5 · Research 8.0 · Business 5.5
Generative AI for Autonomous Driving: Frontiers and Opportunities
Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for content creation, reasoning, planning, and multimodal understanding.
Engineering 7.5 · Research 7.0 · Business 7.0
Multi-Modality Sensing Powered by Laser Dynamics: Theory and Applications
The continued development of embodied intelligence and autonomous driving technologies necessitates comprehensive multi-dimensional environmental perception.
Engineering 5.0 · Research 7.0 · Business 5.0
Analyzing LiDAR Accuracy: Effects of Color and Lighting Conditions
LiDAR is widely used in self-driving vehicles, robotics, surveying, and mapping applications.
Engineering 5.0 · Research 7.0 · Business 5.0
Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute
Should a completion model spend extra test-time compute by iterating, or spend a similar parameter budget on a wider one-shot predictor?
Engineering 5.0 · Research 7.0 · Business 5.0
Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching
To bridge this gap, we introduce Talk2Sensors, the first multi-sensor 3D visual grounding dataset built upon camera, LiDAR, and 4D radar.
Engineering 5.5 · Research 8.0 · Business 5.5
Car-STAGE: Autonomous-Driving Dataset Generation for CARLA (Windows installer)
Car-STAGE is a Windows desktop application for generating annotated autonomous-driving datasets from the CARLA simulator (v0.9.15).
Engineering 6.5 · Research 7.0 · Business 5.0
Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models
We introduce Radar4D-VLM, a radar-only temporal vision-language model that reasons from ten consecutive 4D-radar point-cloud sweeps without camera or LiDAR input.
Engineering 5.0 · Research 7.0 · Business 5.0
Optimized Deep Convolve Grey Wolf NeuroNet for Robust LiDAR-Based Object Classification in Autonomous Systems
Abstract Accurate object classification with LiDAR data should ensure safe navigation in complex and dynamic environments, as it is a critical function of autonomous vehicles.
Engineering 5.0 · Research 8.0 · Business 5.0
A Comprehensive Toolkit for Semi-Automated HD Maps Production: Integrating AI-Driven Feature Extraction with 3D Interactive Validation and Editing
This paper presents a comprehensive toolkit for semi-automated High-Definition Maps (HD Maps) production that integrates Artificial Intelligence (AI)-driven feature extraction with 3D human-in-the-loop validation.
Engineering 5.0 · Research 7.0 · Business 6.0
MoRAL: Sensor-Grounded BEV Reasoning for Compact VLMs toward Edge-Oriented Autonomous Driving
We present MoRAL (Multimodal Reasoning for Autonomous Language Models), a two-stage fine-tuning pipeline that teaches Cosmos-Reason2-2B to first read a physics-encoded Bird's Eye View (BEV) representation and then reason over it for driving decisions.
Engineering 5.5 · Research 7.0 · Business 5.0
Object Detection and Scene Perception for Connected and Autonomous Vehicles Using LM-JEPA
This paper presents the latent model-joint embedding predictive architecture (LM-JEPA), a resource-efficient collaborative perception framework for connected and autonomous vehicles that integrates latent predictive representation learning with lightweight multi-modal reasoning.
Engineering 6.0 · Research 7.5 · Business 6.0
A unified geometry-aware framework for calibration-free cross-modal image-to-point cloud registration
Multi-view point cloud registration is critical for autonomous driving and 3D reconstruction.
Engineering 5.0 · Research 8.0 · Business 5.0
A multimodal BEV 3D object detection method with depth uncertainty and geometric saliency
(2) We propose geometric saliency pillar feature encoding, which enhances point cloud structural representation via point-wise saliency weighting and multi-statistic aggregation.
Engineering 5.5 · Research 7.0 · Business 5.0
GPFusion: enhancing multi-modal 3D object detection via geometric pseudo-image fusion and adaptive feature fusion
To address these limitations, we introduce a novel multi-modal fusion network for 3D object detection, consisting of two principal components: Geometric Pseudo-Image Feature Fusion and the Feature Fusion Encoder.
Engineering 5.5 · Research 8.0 · Business 5.0
Point-plane projections for accurate LiDAR semantic segmentation in small data scenarios
In this paper, we improve the performance of point-based methods by effectively learning features from 2D representations through point–plane projections, enabling the extraction of complementary information while relying solely on LiDAR data.
Engineering 6.5 · Research 7.0 · Business 5.0
Autonomous Vehicles and Transportation Safety: A Comprehensive Review of Risk and Challenges
Autonomous vehicles (AVs) are regarded as a cornerstone of future intelligent transportation systems, yet their safe deployment remains a critical challenge.
Engineering 5.5 · Research 8.0 · Business 6.5