This article presents a survey of simultaneous localization and mapping (SLAM) and data fusion techniques for object detection and environmental scene perception in unmanned aerial vehicles (UAVs). We critically evaluate some current SLAM implementations in robotics and autonomous vehicles and their applicability and scalability to UAVs. SLAM is envisioned as a potential technique for object detection and scene perception to enable UAV navigation through continuous state estimation. In this article, we bridge the gap between SLAM and data fusion in UAVs while also comprehensively surveying related object detection techniques such as visual odometry and aerial photogrammetry. We begin with an introduction to applications where UAV localization is necessary, followed by an analysis of multimodal sensor data fusion to fuse the information gathered from different sensors mounted on UAVs. We then discuss SLAM techniques such as Kalman filters and extended Kalman filters to address scene perception, mapping, and localization in UAVs. The findings are summarized to correlate prevalent and futuristic SLAM and data fusion for UAV navigation, and some avenues for further research are discussed.

This paper applies federated reinforcement learning (FRL) in cellular vehicle-to-everything (C-V2X) communication to enable vehicles to learn communication parameters in collaboration with a parameter server that is embedded in an unmanned aerial vehicle (UAV). Different sensors in vehicles capture different types of data, contributing to data heterogeneity. C-V2X communication networks impose additional communication overhead in order to converge to a global model when the sensor data are not independent-and-identically-distributed (non-i.i.d.). Consequently, the training time for local model updates also varies considerably. Using FRL, we accelerated this convergence by minimizing communication rounds, and we delayed it by exploring the correlation between the data captured by various vehicles in subsequent time steps. Additionally, as UAVs have limited battery power, processing of the collected information locally at the vehicles and then transmitting the model hyper-parameters to the UAVs can optimize the available power consumption pattern. The proposed FRL algorithm updates the global model through adaptive weighing of Q-values at each training round. By measuring the local gradients at the vehicle and the global gradient at the UAV, the contribution of the local models is determined. We quantify these Q-values using nonlinear mappings to reinforce positive rewards such that the contribution of local models is dynamically measured. Moreover, minimizing the number of communication rounds between the UAVs and vehicles is investigated as a viable approach for minimizing delay. A performance evaluation revealed that the FRL approach can yield up to a 40% reduction in the number of communication rounds between vehicles and UAVs when compared to gross data offloading.

In this paper, we propose an environment perception framework for autonomous driving using state representation learning (SRL). Unlike existing Q-learning based methods for efficient environment perception and object detection, our proposed method takes the learning loss into account under deterministic as well as stochastic policy gradient. Through a combination of variational autoencoder (VAE), deep deterministic policy gradient (DDPG), and soft actor-critic (SAC), we focus on uninterrupted and reasonably safe autonomous driving without steering off the track for a considerable driving distance. Our proposed technique exhibits learning in autonomous vehicles under complex interactions with the environment, without being explicitly trained on driving datasets. To ensure the effectiveness of the scheme over a sustained period of time, we employ a reward-penalty based system where a negative reward is associated with an unfavourable action and a positive reward is awarded for favourable actions. The results obtained through simulations on DonKey simulator show the effectiveness of our proposed method by examining the variations in policy loss, value loss, reward function, and cumulative reward for ‘VAE+DDPG’ and ‘VAE+SAC’ over the learning process.

Unmanned aerial vehicle (UAV)-enabled vehicular communications in the sixth generation (6G) are characterized by line-of-sight (LoS) and dynamically varying channel conditions. However, the presence of obstacles in the LoS path leads to shadowed fading environments. In UAV-assisted cellular vehicle-to-everything (C-V2X) communication, vehicle and UAV mobility and shadowing adversely impact latency and throughput. Moreover, 6G vehicular communications comprise data-intensive applications such as augmented reality, mixed reality, virtual reality, intelligent transportation, and autonomous vehicles. Since vehicles’ sensors generate immense amount of data, the latency in processing these applications also increases, particularly when the data are not independently identically distributed (non-i.i.d.). Furthermore, when the sensors’ data are heterogeneous in size and distribution, the incoming packets demand substantial computing resources, energy efficiency at the UAV servers and intelligent mechanisms to queue the incoming packets. Due to the limited battery power and coverage range of UAV, the quality of service (QoS) requirements such as coverage rate, UAV flying time, and fairness of vehicle selection are adversely impacted. Controlling the UAV trajectory so that it serves a maximum number of vehicles while maximizing battery power usage is a potential solution to enhance QoS. This paper investigates the system performance and communication disruption between vehicles and UAV due to Doppler effect in the orthogonal time–frequency space (OTFS) modulated channel. Moreover, a low-complexity UAV trajectory prediction and vehicle selection method is proposed using federated learning, which exploits related information from past trajectories. The weighted total energy consumption of a UAV is minimized by jointly optimizing the transmission window ($L_w$), transmit power and UAV trajectory considering Doppler spread. The simulation results reveal that the weighted total energy consumption of the OTFS-based system decreases up to 10% when combined with federated learning to locally process the sensor data at the vehicles and communicate the processed local models to the UAV. The weighted total energy consumption of the proposed federated learning algorithm decreases by 10–15% compared with convex optimization, heuristic, and meta-heuristic algorithms.

The paper studies a game theory model to ensure fairness and improve the communication efficiency in an unmanned aerial vehicle (UAV)-assisted cellular vehicle-to-everything (C-V2X) communication network using Markovian game theory in a federated learning (FL) environment. The UAV and each vehicle in a cluster utilized a strategy-based mechanism to maximize their model completion and transmission probability. We modeled a two-stage zero sum Markovian game with incomplete information to jointly study the utility maximization of the participating vehicles and the UAV in the FL environment. We modeled the aggregating process at the UAV as a mixed strategy game between the UAV and each vehicle. By employing Nash equilibrium, the UAV determined the probability of sufficient updates received from each vehicle. We analyzed and proposed decision-making strategies for several representative interactions involving gross data offloading and federated learning. When multiple vehicles enter a parameter transmission conflict, various strategy combinations are evaluated to decide which vehicles transmit their data to the UAV. The optimal payoff in a transmission window is derived using the Karush–Khun–Tucker (KKT) optimality conditions. We also studied the variation in optimal model parameter transmission probability, average packet delay, UAV transmit power, and the UAV–Vehicle optimal communication probabilities under different conditions.