IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS Flying through cluttered and dynamic environments with LiDAR Huajie Wu, Wenyi Liu, Y unfan Ren, Zheng Liu, Hairuo Wei, Fangcheng Zhu, Haotian Li, and Fu Zhang Abstract --Navigating unmanned aerial vehicles (UAVs) through cluttered and dynamic environments remains a significant challenge, particularly when dealing with fast-moving or sudden-appearing obstacles. This paper introduces a complete LiDAR-based system designed to enable UAVs to avoid various moving obstacles in complex environments. Benefiting the high computational efficiency of perception and planning, the system can operate in real time using onboard computing resources with low latency. For dynamic environment perception, we have integrated our previous work, M-detector, into the system. M-detector ensures that moving objects of different sizes, colors, and types are reliably detected. For dynamic environment planning, we incorporate dynamic object predictions into the integrated planning and control (IPC) framework, namely DynIPC. This integration allows the UAV to utilize predictions about dynamic obstacles to effectively evade them. We validate our proposed system through both simulations and real-world experiments. In simulation tests, our system outperforms state-of-the-art baselines across several metrics, including success rate, time consumption, average flight time, and maximum velocity. Index Terms --LiDAR-based UAV, dynamic obstacle avoidance, cluttered and dynamic environment I. I NTRODUCTION I N recent years, the development of lightweight and high-precision sensors, such as Light Detection and Ranging sensors (LiDAR), event cameras, and depth cameras, has significantly advanced the autonomous flight capabilities of unmanned aerial vehicles (UA Vs) or drones. This technological progress has facilitated the widespread application of drones across various industries, including agricultural spraying [1], product delivery [2], inspection [3], and search and rescue [4]. These applications have notably enhanced production efficiency, reduced costs, and driven economic growth within these sectors.

Rapid progress in intelligent unmanned systems has presented new opportunities for mobile crowd sensing (MCS). Today, heterogeneous air-ground collaborative multi-agent framework, which comprise unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), have presented superior flexibility and efficiency compared to traditional homogeneous frameworks in complex sensing tasks. Within this context, task allocation among different agents always play an important role in improving overall MCS quality. In order to better allocate tasks among heterogeneous collaborative agents, in this paper, we investigated two representative complex multi-agent task allocation scenarios with dual optimization objectives: (1) For AG-FAMT (Air-Ground Few Agents More Tasks) scenario, the objectives are to maximize the task completion while minimizing the total travel distance; (2) For AG-MAFT (Air-Ground More Agents Few Tasks) scenario, where the agents are allocated based on their locations, has the optimization objectives of minimizing the total travel distance while reducing travel time cost. To achieve this, we proposed a Multi-Task Minimum Cost Maximum Flow (MT-MCMF) optimization algorithm tailored for AG-FAMT, along with a multi-objective optimization algorithm called W-ILP designed for AG-MAFT, with a particular focus on optimizing the charging path planning of UAVs. Our experiments based on a large-scale real-world dataset demonstrated that the proposed two algorithms both outperform baseline approaches under varying experimental settings, including task quantity, task difficulty, and task distribution, providing a novel way to improve the overall quality of mobile crowdsensing tasks.

With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In this article, we introduce a novel multi-layered hierarchical HITL DRL algorithm that comprises three types of learning: self learning, imitation learning and transfer learning. In addition, we consider three forms of human inputs: reward, action and demonstration. Furthermore, we discuss main challenges, trade-offs and advantages of HITL in solving complex problems and how human information can be integrated in the AI solution systematically. To verify our technical results, we present a real-world unmanned aerial vehicles (UAV) problem wherein a number of enemy drones attack a restricted area. The objective is to design a scalable HITL DRL algorithm for ally drones to neutralize the enemy drones before they reach the area. To this end, we first implement our solution using an award-winning open-source HITL software called Cogment. We then demonstrate several interesting results such as (a) HITL leads to faster training and higher performance, (b) advice acts as a guiding direction for gradient methods and lowers variance, and (c) the amount of advice should neither be too large nor too small to avoid over-training and under-training. Finally, we illustrate the role of human-AI cooperation in solving two real-world complex scenarios, i.e., overloaded and decoy attacks.

A'flame in the sky,' eerie red glowing objects and swarms of UFOs over military bases are just some of the many sightings that have gravely concerned the US government. There are dozens of unsolved cases going back to the 1960s that occurred over nuclear missile installations, Navy ships and a desert in New Mexico. The FBI, CIA, and other government branches have spent years looking into these reports, but have yet to determine what the objects were and where they came from. One report in 2019 detailed how'drones' appeared over Colorado, Nebraska, Wyoming, and Kansas as locals reported spying a mothership hanging in the sky. In just the last few months, the skies over New Jersey were filled with unidentified aircraft and drones that required a formal response from both the Biden and Trump presidencies.

Kyiv, Ukraine – Finishing a cigarette with a final deep puff outside a hospital building in central Kyiv, a wounded Ukrainian drone operator sums up Russian President Vladimir Putin's readiness to end the Ukraine war along the current front lines. "Don't trust these leaks, the … vampire is just dragging the talks out," Arseny, a 31-year-old recovering from a cranial wound that left him blind in one eye, told Al Jazeera while standing near a blossoming apple tree. He referred to a Financial Times report on Tuesday that suggested that Putin could "relinquish" Moscow's claims on four partly-occupied Ukrainian regions. In September 2022, seven months after Russia's full-scale invasion of Ukraine began, Moscow recognised the regions as part of Russia even though it did not fully control them – and began losing some occupied areas within weeks. In return for the Kremlin's concession, the US may recognise Crimea, a Black Sea peninsula Moscow annexed in 2014, as part of Russia, and "acknowledge" the Kremlin's de facto control over the four regions' occupied parts, the Financial Times claimed, citing officials familiar with the talks.

Tech expert Kurt Knutsson discusses how robots and drones are revolutionizing fruit farming with faster picking and smarter handling. Farming is undergoing a remarkable transformation thanks to cutting-edge technologies reshaping how fruit is picked and handled. While autonomous drones like Tevel's Flying Robots are already harvesting fruit globally, innovations like UC San Diego's GRIP-tape gripper represent the next frontier in gentle produce handling. Together, these advancements promise to make fruit production more efficient and precise, though one is a proven solution and the other is a glimpse into farming's future. GET SECURITY ALERTS & EXPERT TECH TIPS – SIGN UP FOR KURT'S'THE CYBERGUY REPORT' NOW Tevel's Flying Autonomous Robots (FARs) are redefining fruit harvesting by combining artificial intelligence with advanced computer vision.

Nine people have been killed after a Russian drone hit a bus transporting workers in Ukraine, officials say. The attack occurred on Wednesday morning in the south-central city of Marhanets. Serhiy Lysak, regional chief of Dnipropetrovsk, said at least 30 people were injured, adding that "the number of victims is constantly growing". The attack comes as diplomats from the UK, France, Germany, the US and Ukraine are preparing to hold talks in London aimed at securing a ceasefire in the conflict. Russia launched a full-scale invasion of Ukraine on 24 February 2022.

Overnight Russian drone attacks on east, south and central Ukraine damaged civilian infrastructure and businesses in the Poltava region and injured civilians in the Odesa region, Ukrainian officials said early on Wednesday. Odesa came under a "massive attack" by Russian drones overnight on Tuesday, wounding at least three people, the head of the regional administration, Oleh Kiper, wrote on his Telegram page. A residential building in a densely populated urban area of Odesa, civilian infrastructure and an educational facility were hit, he said. Air defence units repelled Russian air attacks on the Kyiv region and Ukraine's second largest city of Kharkiv, regional governors said in posts on Telegram channels. Russian forces said they have retaken St Nicholas Belogorsky monastery in the village of Gornal in Russia's Kursk region, where Ukrainian troops had been based, Russia's TASS news agency quoted a security source as saying.

With the exponential growth of Internet of Things (IoT) devices, edge computing (EC) is gradually playing an important role in providing cost-effective services. However, existing approaches struggle to perform well in graph-structured scenarios where user data is correlated, such as traffic flow prediction and social relationship recommender systems. In particular, graph neural network (GNN)-based approaches lead to expensive server communication cost. To address this problem, we propose GraphEdge, an efficient GNN-based EC architecture. It considers the EC system of GNN tasks, where there are associations between users and it needs to take into account the task data of its neighbors when processing the tasks of a user. Specifically, the architecture first perceives the user topology and represents their data associations as a graph layout at each time step. Then the graph layout is optimized by calling our proposed hierarchical traversal graph cut algorithm (HiCut), which cuts the graph layout into multiple weakly associated subgraphs based on the aggregation characteristics of GNN, and the communication cost between different subgraphs during GNN inference is minimized. Finally, based on the optimized graph layout, our proposed deep reinforcement learning (DRL) based graph offloading algorithm (DRLGO) is executed to obtain the optimal offloading strategy for the tasks of users, the offloading strategy is subgraph-based, it tries to offload user tasks in a subgraph to the same edge server as possible while minimizing the task processing time and energy consumption of the EC system. Experimental results show the good effectiveness and dynamic adaptation of our proposed architecture and it also performs well even in dynamic scenarios.

Aerial object detection using unmanned aerial vehicles (UAVs) faces critical challenges including sub-10px targets, dense occlusions, and stringent computational constraints. Existing detectors struggle to balance accuracy and efficiency due to rigid receptive fields and redundant architectures. To address these limitations, we propose Variable Receptive Field DETR (VRF-DETR), a transformer-based detector incorporating three key components: 1) Multi-Scale Context Fusion (MSCF) module that dynamically recalibrates features through adaptive spatial attention and gated multi-scale fusion, 2) Gated Convolution (GConv) layer enabling parameter-efficient local-context modeling via depthwise separable operations and dynamic gating, and 3) Gated Multi-scale Fusion (GMCF) Bottleneck that hierarchically disentangles occluded objects through cascaded global-local interactions. Experiments on VisDrone2019 demonstrate VRF-DETR achieves 51.4\% mAP\textsubscript{50} and 31.8\% mAP\textsubscript{50:95} with only 13.5M parameters. This work establishes a new efficiency-accuracy Pareto frontier for UAV-based detection tasks.