unmanned aerial vehicle
PulseAugur coverage of unmanned aerial vehicle — every cluster mentioning unmanned aerial vehicle across labs, papers, and developer communities, ranked by signal.
- instance of Gotit.pub 90%
- instance of CatalyzeX 90%
- instance of DagsHub 90%
- used by 6G 80%
- used by Open Radio Access Network 80%
- used by alphaXiv 70%
- partners with unmanned ground vehicle 70%
- used by deep reinforcement learning 70%
- used by MLLMs 70%
- developed deep reinforcement learning 70%
- used by Gotit.pub 70%
- used by global navigation satellite system 70%
- 2026-07-19 research_milestone Engineers developed an AI-optimized drone that uses visual illusions for near-invisibility, presented at the 2026 Robotics: Science and Systems Conference. source
21 day(s) with sentiment data
-
New DAPM model enhances UAV depth estimation across diverse aerial viewpoints
Researchers have developed a new model called DAPM (Depth Estimation for Any Perspectives Model) specifically for unmanned aerial vehicles (UAVs). This model addresses the challenge of monocular depth estimation in aeri…
-
New frameworks boost UAV geo-localization accuracy with satellite imagery · 2 sources tracked
Two new research papers introduce novel frameworks for improving the geo-localization accuracy of unmanned aerial vehicles (UAVs) using satellite imagery, particularly in challenging off-nadir viewing conditions. The fi…
-
New DRGBT-1K benchmark released for dynamic RGBT tracking
Researchers have introduced DRGBT-1K, a new large-scale benchmark designed to evaluate the robustness of dynamic RGBT tracking systems. This benchmark comprises over 1,000 real-world sequences and nearly 800,000 RGBT fr…
-
UAV-assisted ISAC system optimizes sensing and communication with novel trajectory and beamforming
Researchers have developed a novel approach for optimizing unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) systems. This method jointly optimizes the UAV's trajectory and beamforming p…
-
New system enables GPS-free aerial geo-localization using satellite imagery
Researchers have developed a new system called NGPS (Next-Generation Positioning System) for high-altitude unmanned aerial vehicles (UAVs) that enables GPS-free absolute positioning. The system achieves this by matching…
-
New AI framework maps crop germination gaps using drone imagery
Researchers have developed a deep learning framework called CGMap to precisely map crop germination gaps using drone imagery. This system, which utilizes the YOLOv8 architecture, identifies germinated plants and "bald s…
-
New SARLA method enhances cross-modal UAV object tracking
Researchers have introduced SARLA, a novel approach for cross-modal Unmanned Aerial Vehicle (UAV) object tracking. SARLA addresses challenges arising from switching between visible light and thermal infrared sensors, wh…
-
New SkyEV dataset aims to improve UAV detection with synchronized RGB and event data
Researchers have introduced SkyEV, a new open-source dataset designed to improve the detection and tracking of unmanned aerial vehicles (UAVs). Existing datasets often fail to replicate realistic counter-UAV scenarios, …
-
New OREN-Bubble$^\star$ system enables real-time autonomous UAV navigation
Researchers have developed a novel approach for autonomous flight in cluttered environments by co-designing mapping and motion planning around signed distance functions (SDFs). Their system, OREN-Bubble$^\star$, integra…
-
LLM-DRL Hybrid Navigates UAVs in Complex Networks
Researchers have developed a new hierarchical control framework for Uncrewed Aerial Vehicles (UAVs) navigating complex Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). This system combines the strategic rea…
-
New method enhances VLM navigation for UAVs without retraining
Researchers have developed a new method for improving the navigation capabilities of vision-language models (VLMs) used in unmanned aerial vehicles (UAVs). This approach, detailed in a recent paper, enhances navigation …
-
Kanghui subsidiary inks 679M yuan AI computing power deal
Kanghui Co., Ltd. announced that its subsidiary, Beijing Kanghui Zhichuang Technology Co., Ltd., has signed a computing power service contract with a client identified as Company D. The contract, valued between 415 mill…
-
New Framework Enhances Drone-Based Urban Sensing with Reinforcement Learning
Researchers have developed a novel Two TimeScale Reinforcement Learning (TSRL) framework to address challenges in using delivery drones for urban sensing. The framework tackles scalability issues and the heterogeneity o…
-
New framework improves UAV-UGV heading prediction reliability
This paper introduces a confidence-gated framework for vision-based heading prediction in UAV-UGV cooperative systems. The proposed method uses bounding-box area and heading variation as reliability proxies to determine…
-
RGB-based framework enables aerial drones to identify robot deployment zones
Researchers have developed a new framework for analyzing traversability using only RGB camera data, enabling aerial drones to identify optimal deployment locations for ground robots in confined spaces. This system recon…
-
New MLLMs tackle small object detection in aerial video streams · 3 sources tracked
Researchers have developed new multimodal large language models (MLLMs) specifically designed for understanding small objects in streaming aerial videos. One approach, SkyVLaM, uses a temporal basis perceiver to create …
-
Withdrawn UAV resource management paper proposed Stackelberg game and DRL
A research paper, since withdrawn, proposed a novel framework for managing resources in low-altitude economies dominated by Unmanned Aerial Vehicles (UAVs). The approach integrates communication latency with physical co…
-
New framework enables real-time, secure AI control for UAVs
Researchers have developed a new framework called RT-SHCUA to address the challenges of using self-hosted computer-use agents (SHCUAs) for real-time unmanned aerial vehicle (UAV) control. The proposed system restructure…
-
New PRIME framework recovers dormant neurons in multi-agent AI systems
Researchers have developed PRIME (Plasticity Recovery In Multi-agent Environments), a novel framework designed to address the issue of dormant neurons in multi-agent reinforcement learning systems, particularly in dynam…
-
New UAV-DualCog benchmark reveals MLLM limitations in aerial reasoning
Researchers have introduced UAV-DualCog, a new benchmark designed to evaluate the dual-cognition capabilities of multimodal large language models (MLLMs) in unmanned aerial vehicle (UAV) scenarios. This benchmark assess…