This study focuses on collaborative UAV/UGV routing problem in emergency logistics aiming to optimize the coordinated delivery efforts of both vehicles during disaster situations. By using a mixed integer model the study identifies the best delivery points and assigns specific drones to transport medical supplies to designated emergency assembly points. The research methodically assesses how UAV speed, UGV stops and cluster numbers affect delivery time. The results show that increasing UAV speeds and reducing stops and clusters generally lead to deliveries but achieving the time requires a careful balance due to their complex interactions. The study suggests that strategic coordination between UAVs and UGVs can significantly improve the efficiency of emergency logistics systems potentially reducing response times in disaster relief and medical supply deliveries. In conclusion the model highlights the potential for enhancements, in emergency response capabilities that could help save lives and lessen disaster impacts. Future studies should consider adapting the model for conditions and unpredictable scenarios to ensure resilience against demands.

This study researches smart agriculture and its components, robotic systems and machine learning algorithms, development of agricultural robots, and their effects on the industry. In application, it is aimed to collect the harvest of autonomous unmanned aerial vehicles and UGVs in communication with each other by means of time minimization of the target. It wanted to be tested with different approaches for an optimal number of stops by using particle swarm optimization. Deterministic, binary mixed (0-1) integer modeling was used to determine the optimal picking time of the apples allocated to the stalls with the k-means method. With this modeling, it has been determined which unmanned aerial vehicle will be collected and how it is calculated whether the air vehicle has collected the apple or not using 0-1 binary modeling. The route of the unmanned UGV was made by using the nearest neighbor, nearest insertion, and 2-opt methods. This study has been extended and reviewed by the summary paper at International OECD Studies Conference March 2020, Ankara, Turkey.

Günümüzde tarım sektörü yeni şirketler ve yatırımcılarla bir yüksek teknoloji endüstrisi haline gelmektedir. Teknolojinin hızlı gelişmesi sadece çiftçilerin üretim yeteneklerini geliştirmeyip, robotik ve otomasyon teknolojisini de geliştirmektedir. Çiftçiler artık hasat toplamada otonom hava araçları ve robotlar kullanarak üretim verimlerini artırmaktadırlar. Bu çalışmada, birbirleriyle iletişim halinde otonom insansız hava ve kara araçlarına tarım arazisinde hedefleri daha önceden belirlenmiş elmaların zaman minimizasyonu ile hasat toplatılması amaçlanmıştır. Mevcut çalışılan problemin çok büyük olmasından dolayı süre optimizasyonu yapılması amacıyla ana problem küçük alt problemlere bölünerek çözülmüştür. Kara araçlarının duraklarının yerlerinin belirlenmesi ve bu yerlerin belirlenme işlemini çözümlemek için k-ortalama kümeleme yönteminden yararlanılmıştır. Hesaplamalar için ise Julia programlama dili kullanılmıştır. Çalışmada örnek olarak toplatılması düşünülen 500 elma için optimal durak sayısı 3 olarak bulunmuştur. Her bir durakta hava araçlarının elma toplama sürelerini optimize etmek için hazırlanan model ise Gurobi çözücüsü yardımıyla çözümlenip sonuçlara ulaşılmıştır. Çalışmanın sonucunda kara aracının her bir durakta ortalama bekleme süresi yaklaşık 439 sn olarak elde edilmiştir. Today, the agricultural sector is becoming a high-tech industry with new companies and investors. Rapid development of technology not only improves farmers' production capabilities, but also improves robotics and automation technology. Farmers are now increasing their production efficiency by using autonomous aircraft and robots in harvesting. In this study, it is aimed to collect the harvest by the time minimization of the previously determined apples in the agricultural land in communication of autonomous unmanned aerial and ground vehicles. Due to the fact that the current problem is very large, the main problem is solved by dividing it into small sub-problems in order to make time optimization. K-means clustering method was used to determine the locations of the ground vehicles' stops and to analyze it. Julia programming language is used for calculations. In the study, the optimal number of stops for 500 apples was found to be 3. The model prepared to optimize the apple picking times of air vehicle at each stop was resolved with the help of the Gurobi solvent and the results were achieved. As a result of the study, the average waiting time of the ground vehicle at each stop was approximately 439 seconds.

Rapid localisation of trapped victims after urban disasters is essential but challenging because Bluetooth Low Energy (BLE) beacons are intermittent, radio propagation is obstructed by rubble, UAVs are energy-constrained, and real-world multi-UAV training is impractical in high-risk search-and-rescue (SAR) environments. This study formulates post-disaster victim localisation as a cooperative Dec-POMDP and adapts a model-aided federated multi-agent reinforcement learning framework based on FedQMIX. The proposed pipeline combines a lightweight LoS/NLoS surrogate channel model, PSO-based victim-position estimation, return-to-base and map-feasibility safety checks, an SAR-aligned shaped reward, and a leakage-free centralised training state based on estimated rather than ground-truth victim locations. Each UAV trains locally inside a learned digital-twin simulator and periodically shares only QMIX network parameters, avoiding the exchange of raw trajectories or RSSI logs. The framework is evaluated on two synthetic post-earthquake urban maps representing a compact return-to-base scenario and a larger reach-to-destination scenario. Across five independent seeds per method and map, Model-Aided FedQMIX achieves the highest and most stable victim-localisation performance, with the clearest advantage observed in the larger long-horizon scenario. Additional diagnostic tests examine reward-weight sensitivity, RF channel-shift robustness, BLE/smartphone hardware heterogeneity, non-IID client-data variation, and partial-client FedAvg under missing client updates. The results indicate that combining model-aided localisation cues, decentralised value factorisation, SAR-aligned objective design, and federated parameter sharing can improve the robustness of UAV-based victim-localisation policies. The framework also clarifies deployment considerations for federated SAR coordination, including communication payload, privacy boundaries, heterogeneous client experience, device variability, and intermittent connectivity. This study remains simulation-based, and future validation with real UAVs, BLE devices, and rubble-inspired testbeds is required before operational deployment.

Coordinating multiple unmanned aerial vehicles (UAVs) for inspection, delivery, and search-and-rescue missions demands routes that are globally efficient yet locally safe. Flat optimisation or single-level reinforcement-learning agents scale poorly as map size, obstacle density, or fleet size increase, because one policy must juggle long-horizon objectives and split-second collision avoidance. We reformu- late multi-UAV path planning as a hierarchical reinforcement-learning problem and introduce a two-tier controller for discrete grids under partial observability. A high-level manager selects coarse waypoints toward mission goals, while a shared recurrent worker—trained with proximal policy optimisation and an LSTM back- bone—executes short, collision-aware motion sequences. We prove that, given an expressive waypoint dictionary, every subgame-perfect equilibrium of the induced Markov game is collision-free and that enlarging the dictionary monotonically improves team return. To keep training practical we propose manager–worker curriculum optimisation: the worker is pre-trained on small grids and frozen, then the manager is trained on progressively larger maps. Experiments on three bench- marks—ranging from two to six UAVs with 20 %–40 % obstacle coverage—show that the hierarchy maintains ≥ 90 % mission success and reduces collisions by up to 74 % relative to plain PPO (62 % versus PPO + LSTM), while lengthening routes by no more than three primitive steps (≤ 2 compared with PPO + LSTM). Performance degrades only marginally as fleet size and obstacle density grow, confirming that a modest waypoint vocabulary combined with recurrent memory can turn simple reactive primitives into safe, scalable multi-UAV behaviour.