Autonomous aerial vehicles have become increasingly important for data harvesting tasks in complex urban environments, where efficient area coverage, reliable data collection, and safe navigation are critical. Coverage path planning ensures that all regions of interest are visited with minimal redundancy, while data harvesting focuses on collecting data from distributed IoT sensor nodes under energy and safety constraints. In this work, we propose a Transformer-enhanced Double Deep Q-Network (TDDQN) framework that effectively integrates a Standard Transformer Encoder with a hierarchical global-local map representation for large-scale urban AAV navigation. This strategy combines a compressed global map with a local obstacle-aware map to enable scalable operation and temporal reasoning in complex urban landscapes. The proposed approach is evaluated through extensive simulations on Manhattan32 and Urban50 scenarios and compared against various existing models. Experimental results demonstrate that the proposed method consistently outperforms all baselines by achieving superior coverage efficiency, data collection performance, and landing success rates. Notably, in Urban50 environment, the proposed method improves the coverage ratio by 48.1% and the landing success rate by 14.3% over the baseline models. These results highlight the effectiveness of attention based architectures in enhancing AAV decision-making for coverage path planning and data harvesting tasks while maintaining stringent safety and energy requirements.
The telecommunication industry in India is undergoing a structural change, with the deployment of the 5G network, the widespread deployment of smart devices for the Digital India initiative and the need for ultra-low latencies, high-speed services for smart cities, healthcare, agriculture and industrial automation. Traditional network management methods, which are mostly based on static configuration and human intervention are increasingly proving to be insufficient for the scale, diversity and dynamism of these networks. This paper introduces an Artificial Intelligence (AI) centric network management framework that combines 5G radio access and core capabilities, Software-Defined Networking (SDN) for centralized and programmable control and Multi-access Edge Computing (MEC) for localized and low latency processing. This framework includes a traffic prediction module (based on Long Short-Term Memory (LSTM)) and a resource orchestration engine (Deep Q-Network (DQN)), both of which allow for closed-loop self-optimizing network actions. Mininet-WiFi and Ryu SDN controller were used to simulate a representative Indian metropolitan network topology and assess the proposed framework in comparison to a baseline configuration with conventional SDN. Experimental results show significant gains in end-to-end latency (53.3 %), throughput (53.2 %), jitter (60.7 %), packet loss (72.4 %) and resource-utilization efficiency (42.6 %). The results indicate that 5G-SDN-edge continuum orchestration can positively impact the Quality of Service (QoS) in India-specific use cases such as dense urban areas and rural areas with limited infrastructure. The paper also elaborates the deployment challenges pertinent to the Indian context like spectrum availability, fiber backhaul penetration, cost of edge infrastructure, and regulatory considerations, while proposing the directions for future research like federated learning in orchestrating with privacy constraints and upcoming 6G research initiatives.
Praveen Kumar, S. Hashmi, Preeti Singhwal et al.· International journal of com...· 0 citations
