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. 来源
11 天有情绪数据
-
InterFuserDVS integrates event cameras to enhance autonomous driving safety
Researchers have developed InterFuserDVS, an enhanced sensor fusion model for autonomous driving that integrates Dynamic Vision Sensors (DVS) with traditional RGB cameras and LiDAR. This novel approach uses a token-base…
-
HiPR framework improves camera-LiDAR 3D occupancy prediction with height-guided projection
Researchers have introduced HiPR, a novel framework for camera-LiDAR occupancy prediction that addresses limitations in traditional 2D-to-3D view transformations. HiPR utilizes a height-guided projection reparameterizat…
-
PROBE descriptor offers robust, learning-free LiDAR place recognition
Researchers have introduced PROBE, a novel learning-free descriptor for LiDAR place recognition. PROBE models Bird's-Eye View (BEV) cell occupancy as a Bernoulli random variable, analytically marginalizing over continuo…
-
BEVCALIB model uses bird's-eye view features for LiDAR-camera calibration
Researchers have developed BEVCALIB, a novel method for calibrating LiDAR and camera sensors, crucial for autonomous driving systems. This approach utilizes bird's-eye view (BEV) features extracted from both sensor type…
-
Rivian considers in-house lidar production for autonomous vehicles
Rivian's CEO has indicated the company is exploring the production of its own LiDAR sensors for autonomous vehicles. This move suggests a potential shift towards in-house manufacturing for critical self-driving components.
-
Rivian considers in-house lidar production for autonomous vehicles
Rivian's CEO has indicated that the electric vehicle company is exploring the possibility of manufacturing its own LiDAR sensors for autonomous driving systems. This potential move aligns with a broader trend of automak…
-
SaLF offers real-time multi-sensor simulation for autonomous driving
Researchers have developed SaLF, a novel volumetric representation for real-time multi-sensor simulation. This method uses a sparse set of 3D voxel primitives, each containing a local implicit field, to achieve faster t…
-
激光雷达单传感器高精地图构建方法通过知识蒸馏增强语义线索
研究人员开发了LIE，一种仅使用激光雷达数据构建自动驾驶高精地图的新方法。该方法通过利用知识蒸馏来增强对激光雷达点云和强度图的语义理解，克服了基于相机的局限性。与最先进的基于相机的模型相比，LIE表现出更优越的性能，在各种条件下实现了更高的准确性和鲁棒性，并显示出对新数据集的高效适应性。
-
PACE model slashes LiDAR point cloud compression latency by 90%
Researchers have introduced PACE, a novel framework designed to significantly improve the efficiency and reduce the latency of LiDAR point cloud compression for autonomous systems. PACE addresses existing bottlenecks by…
-
AI驱动的应用程序将视觉数据转化为盲人的听觉反馈
一款名为 SoundSight 的新 AI-Sight 应用程序已被开发出来，旨在为使用移动技术的视障人士提供听觉反馈。该应用程序利用 DeepLabV3、YOLOv5 和 YOLOv8 等 AI 模型来解释设备摄像头和 LiDAR 传感器的视觉信息。然后，系统将这些感官数据转化为语义听觉提示，旨在增强盲用户的导航和环境感知能力。
-
Car tech innovator discusses self-driving AI, Cybertruck, and future of autonomous vehicles
This podcast episode features a discussion with Ken Smiley, a car-tech builder, about the future of self-driving AI. The conversation touches on topics such as autonomous vehicles, computer vision, and the evolution of …
-
Ouster's new color lidar technology promises to revolutionize AI and sensor development
Ouster has introduced new color LiDAR sensors that aim to surpass traditional cameras in various applications. These sensors are expected to usher in a new phase for both artificial intelligence development and sensor t…
-
EdgeLPR paper explores neural network precision vs performance trade-offs for LiDAR place recognition
Researchers have developed EdgeLPR, a method for efficient LiDAR-based place recognition on edge devices. The approach utilizes Bird's Eye View representations to enable lightweight image-based networks for autonomous n…
-
Researchers introduce APCoTTA for continuous adaptation of LiDAR point cloud segmentation models.
Researchers have introduced APCoTTA, a new framework designed for continuous test-time adaptation in semantic segmentation of airborne LiDAR point clouds. This method addresses performance degradation in deployed models…
-
OmniLiDAR framework unifies 3D LiDAR generation across diverse domains
Researchers have developed OmniLiDAR, a unified diffusion framework capable of generating 3D LiDAR scans across diverse domains including varied weather, sensor configurations, and acquisition platforms. This unified ap…
-
New RAY-TOLD system enhances robot navigation in dense, dynamic crowds
Researchers have developed RAY-TOLD, a novel hybrid control architecture designed to improve obstacle avoidance for autonomous mobile robots in dense, dynamic environments. This system integrates a LiDAR-centric latent …
-
机器人利用AI驱动的深度估计进行导航，摒弃LiDAR
研究人员开发了一种新颖的机器人导航师生框架，该框架用基于视觉的单目深度估计取代了传统的LiDAR传感器。一个由特权LiDAR数据训练的教师策略，指导一个仅依赖于经过微调的Depth Anything V2模型生成的深度图的学生策略。这种纯视觉方法允许在NVIDIA Jetson Orin AGX等平台上进行完全的板载处理，在复杂3D环境中表现出优于标准LiDAR的性能。
-
Tesla's vision-only autonomy faces scrutiny amid costly retrofits and rival LiDAR advancements
Tesla's strategy of relying solely on cameras for autonomous driving faces scrutiny regarding its long-term viability. The company's approach is challenged by the significant cost of retrofitting millions of vehicles wi…
-
BEV segmentation models for autonomous driving lack generalizability across datasets
A new study published on arXiv evaluates the performance of Bird's-Eye View (BEV) segmentation models used in autonomous driving. Researchers found that models trained on single datasets, like nuScenes, tend to overfit …
-
New framework uses prior map data to improve camera-based 3D object detection
Researchers have developed a novel framework called DualViewMapDet for camera-only 3D object detection and tracking, particularly beneficial for autonomous driving systems that lack LiDAR sensors. This method leverages …