Influence Maximization (IM) is a critical task in social network analysis, yet its application to large-scale networks is often hampered by computational complexity and the challenge of effectively identifying influential communities. Existing community-based IM algorithms frequently rely on traditional detection methods that may not scale well or adequately capture influence propagation dynamics. While deep learning has advanced community detection, the explicit integration of influence properties into these models remains a significant gap. This paper introduces the Deep Learning-based Community-aware Influence Maximization (DLCIM) algorithm, a novel approach that synergistically combines deep learning for community detection with a tailored focus on influence diffusion characteristics. DLCIM employs an autoencoder framework with a novel influence-aware modularity maximization objective to learn node representations that are sensitive to information propagation. Subsequently, it filters important communities and allocates seed quotas proportionally, followed by efficient seed selection using established techniques within these communities. Comprehensive experiments on real-world datasets demonstrate that DLCIM achieves superior influence spread and competitive computational efficiency compared to state-of-the-art baseline algorithms.

The essence of Influence Maximization (IM) lies in determining seed nodes that maximize influence under specific diffusion models. As social networks become increasingly vast and complex, the rapid and efficient identification of seed nodes for information diffusion has become a research priority. The reward mechanisms in Deep Reinforcement Learning (DRL) naturally align with the methods of selecting seed nodes based on the increment of the influence spread in the IM problem. Consequently, this alignment has attracted significant research attention and inspired various methodological innovations. Despite advancements in optimization techniques, significant challenges remain, particularly in terms of inadequate node feature embedding and value function overestimation. To address these limitations, we propose DKIM, a novel model integrating node embedding with DRL. This model incorporates Kshell positional encoding for effective node representation and employs a Multi-DQN algorithm designed with multi-target networks and adversarial loss (ALoss) function to enhance training efficiency. These innovations effectively mitigate boundary node effects and Q-value overestimation issues. We conduct comprehensive experiments comparing DKIM with state-of-the-art algorithms across four public datasets—Wiki-vote, LastFM-Asia, P2P-Gnutella08, and Facebook. The results demonstrate that DKIM achieves optimal performance on most IM tasks, providing a viable approach for RL-based models in addressing IM problems.

When a wheeled mobile robot (WMR) runs on loose soil (such as the planetary rover on surface of the planet), its wheels generally slip or skip. Since the slippage of the wheel directly affects the motion control and safety, it becomes urgent to effectively estimate the slippage. In this paper, an intuitive slippage estimation method is proposed based on wheel-ruts images, which aims to reduce the number of extra sensors and take advantages of the visual information effectively. Since the image samples sometimes are difficult to collect, a few-shot learning method is employed using distribution propagation graph network with dilated causal convolution layer (DCC-DPGN). The dilated causal convolution (DCC) layer is adopted in ResNet block to expand the receptive field and obtain the sequence information of wheel-ruts, which makes the model training more efficient. The proposed model is verified in the test set of images collected in real scene, which shows the potential of the proposed algorithm in slippage estimation.

In this paper, a dynamic model of a wheeled mobile robotic (WMR) system with coupled control input is developed, which will increase the complexity of its tracking control with time-varying advance angle. To deal with this problem, a partial reinforcement learning neural network (PRLNN)-based tracking algorithm is proposed for the WMR systems. The main contributions of the PRLNN adaptive tracking control method is that it is the first control method to introduce the PRLNN adaptive control to the WMR system, which determines to solve the WMR tracking control with the time-varying advance angle. The critic neural network (NN) and action NN adaptive laws for the decoupled controllers are designed using the standard gradient-based adaptation method. According to the Lyapunov stability analysis theorem, the uniform ultimate boundedness of all signals in the WMR system can be guaranteed with the design parameters chose properly, and the tracking error converge to a small compact set nearby zero. A numerical simulation is presented to verify the effectiveness of the proposed control algorithm.

Simulation of planetary rovers moving on complex terrains is critical for Mars exploration. Equivalent stiffness is proposed and used to characterize the pressure-sinkage property of terrain, while friction angle to characterize the shearing property. Terramechanics model for calculating forces between rigid wheel and soil is proved to be the same with that contact model for calculating forces between rigid wheel and rock. A Digital Elevation Map with Physical Properties is developed and applied to simulate terrain physical properties along with its geometry information. The established methods are validated using simulation and experimental tests with a three-wheel-rover.

In this paper, an adaptive neural network (NN)-based tracking control algorithm is proposed for the wheeled mobile robotic (WMR) system with full state constraints. It is the first time to design an adaptive NN-based control algorithm for the dynamic WMR system with full state constraints. The constraints come from the limitations of the wheels' forward speed and steering angular velocity, which depends on the motors' driving performance. By employing adaptive NNs and a barrier Lyapunov function with error variables, then, the unknown functions in the systems are estimated, and the constraints are not violated. Based on the assumptions and lemmas given in this paper and the references, while the design and the system parameters chose properly, our proposed scheme can guarantee the uniform ultimate boundedness for all signals in the WMR system, and the tracking error converge to a bounded compact set to zero. The numerical experiment of a WMR system is presented to illustrate the good performance of the proposed control algorithm.