unmanned aerial vehicle
PulseAugur coverage of unmanned aerial vehicle — every cluster mentioning unmanned aerial vehicle across labs, papers, and developer communities, ranked by signal.
7 天有情绪数据
-
Event-centric world modeling framework enhances embodied decision-making for agents
Researchers have developed a new event-centric world modeling framework designed for embodied decision-making in autonomous agents. This system represents environments as semantic events, enabling efficient and interpre…
-
Vision Transformers 优化时空植被分类效率
研究人员开发了一种优化的 Vision Transformer (ViT) 方法，用于对植被像素进行时序分类，解决了植物物候监测中的计算挑战。与现有的多时序卷积网络 (CNNs) 相比，这种新方法在计算效率方面有了显著提高，浮点运算量 (FLOPs) 减少了一个数量级。ViT 方法在不考虑时间序列长度的情况下保持恒定的参数复杂度，使其成为监测生态系统和气候变化影响的资源受限系统的可扩展解决方案。
-
Spiking neural networks on Intel Loihi 2 achieve energy-efficient real-time object detection
Researchers have developed a method for designing and deploying Spiking Neural Networks (SNNs) for real-time object detection on edge neuromorphic hardware, specifically the Intel Loihi 2 processor. Their work demonstra…
-
Bayesian Neural Kalman Filter enhances UAV state estimation in noisy environments
Researchers have developed a new Bayesian Neural Kalman Filter (BNKF) to improve state estimation for unmanned aerial vehicles (UAVs) in challenging environments. This hybrid framework combines Bayesian Neural Networks …
-
Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark
Researchers have developed a Graph-based Semantic Calibration Network (GSCNet) to improve semantic segmentation for unaligned RGB-Thermal (RGBT) images captured by unmanned aerial vehicles (UAVs). The network addresses …
-
Researchers develop rule-based coaching for RL UAVs in search-and-rescue missions
Researchers have developed a new hierarchical decision-making framework for unmanned aerial vehicles (UAVs) designed for search-and-rescue missions. This system integrates a rule-based advisor with a reinforcement learn…
-
Amazon, IBM, and GitHub launch AI tools, SoftBank invests in AI robotics
Several major tech companies are integrating AI into their core products and services to enhance productivity and reshape workflows. IBM has made its AI coding partner 'Bob' globally available, while GitHub is adjusting…
-
China's PLA uses tech competitions to drive innovation in drone warfare and multi-domain integration
China's People's Liberation Army (PLA) is utilizing technology-focused challenges and competitions to enhance its preparedness for future conflicts. These events, spanning from January 2023 to December 2024, reveal the …
-
Researchers develop threat-oriented digital twinning for autonomous platform security evaluation
Researchers have developed a new methodology for evaluating the cybersecurity of autonomous systems through digital twinning. This approach creates a threat-oriented digital replica of an autonomy stack, allowing for co…
-
Paper proposes dynamic UGV-UAV path planning for uncertain environments
This paper introduces a cooperative path planning strategy for ground and aerial vehicles operating in uncertain environments. The system uses unmanned aerial vehicles (UAVs) to dynamically inspect road networks and ide…
-
UGV-UAVs plan cooperative paths in uncertain environments for disaster response
Researchers have developed a new framework for cooperative path planning between unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs) in uncertain environments. This system is designed for scenarios like …
-
无人机除草检测模型在准确性和速度之间取得平衡，适用于边缘设备
研究人员开发了一个框架，用于在资源受限的无人机上部署除草检测模型，以实现位点特异性管理。该研究评估了包括YOLO和RT-DETR变体在内的各种目标检测模型，这些模型部署在Jetson Orin Nano和Jetson AGX Xavier等不同的边缘设备上。结果表明，在检测准确性和计算效率之间存在权衡，高容量模型实现了更好的准确性但推理时间较慢。轻量级模型提供了实时性能，而RT-DETRv2-R50-M和YOLOv11s在实际无人机应…
-
Researchers explore aligning drone and close-up imagery for tree species classification
Researchers have identified a significant performance gap in classifying tropical tree species using drone imagery, with close-up photos yielding better results than top-view aerial images. This disparity is particularl…
-
Kerimov-Alekberli model links thermodynamics to AI safety for autonomous systems
Researchers have introduced the Kerimov-Alekberli model, an information-geometric framework designed to enhance AI safety and ethical alignment in autonomous systems. This model establishes a formal link between non-equ…
-
UAVs use vision-only system for altitude-adaptive geo-localization in GPS-denied environments
Researchers have developed a novel vision-only system for Unmanned Aerial Vehicles (UAVs) to determine their location even when GPS is unavailable. The system first estimates the UAV's altitude from a single image by an…
-
Pentagon seeks compact, rapidly deployable autonomous subs for strategic advantage
DARPA has initiated the Deep Thoughts program to develop compact, cost-effective autonomous undersea vehicles (AUVs) capable of reaching full-ocean depths. The initiative aims to significantly reduce the size, cost, and…
-
Event cameras enable accurate relative state estimation for multi-UAV systems
Researchers have developed a novel framework for estimating the relative states of quadrotors using event-based propeller sensing. This method leverages event cameras, which offer low latency and high dynamic range, to …