3D human motion generation has seen substantial advancement in recent years. While state-of-the-art approaches have improved performance significantly, they still struggle with complex and detailed motions unseen in training data, largely due to the scarcity of motion datasets and the prohibitive cost of generating new training examples. To address these challenges, we introduce CoMA, an agent-based solution for complex human motion generation, editing, and comprehension. CoMA leverages multiple collaborative agents powered by large language and vision models, alongside a mask transformer-based motion generator featuring body part-specific encoders and codebooks for fine-grained control. Our framework enables generation of both short and long motion sequences with detailed instructions, text-guided motion editing, and self-correction for improved quality. Evaluations on the HumanML3D dataset demonstrate competitive performance against state-of-the-art methods. Additionally, we create a set of context-rich, compositional, and long text prompts, where user studies show our method significantly outperforms existing approaches.

The high bandwidth, low latency, and extensive coverage of Sixth Generation (6G) communication technology provide robust data support and communication guarantees for intelligent road network management. This study aims to explore the application of 6G communication technology and deep reinforcement learning (DRL) algorithms in smart road network management, with the goal of enhancing the intelligence of traffic management systems. DRL algorithms are capable of handling complex traffic environments and, through self-learning and optimization, can achieve intelligent decision-making and route planning. This study proposes a DRL-based traffic signal control method leveraging 6G communication technology. The core of this method lies in its capability to manage complex and dynamically changing traffic flows, adjusting traffic signal plans based on real-time data to adapt to various traffic conditions. By learning traffic distribution patterns, the model generates appropriate traffic signals for each intersection, thereby optimizing the traffic signal plans. Simulation experiments found that, compared to the Convolutional Neural Network (CNN) algorithm, DRL not only reduced the average travel time by 28.2% but also increased the average travel speed by 26.3%, and significantly reduced the average queue length by 42.9%. These results demonstrate that the proposed DRL algorithm shows significant advantages in alleviating traffic congestion and optimizing traffic signal control. This study offers a novel solution for intelligent road network management and validates the potential of 6G communication technology and DRL algorithms in this field.

The paper aims to explore the performance of short-term traffic flow prediction of the 5G (5th Generation Mobile Communication Technology) Internet of Vehicles (IoV) based on edge computing (EC) for the smart city and to further improve the intelligence of the smart city. Aiming at the current emergency of traffic congestion and road congestion, the present work adds EC to the current vehicle network, and integrates a deep convolution random forest neural network (DCRFNN). Additionally, it implements a model for short-term traffic flow prediction of a 5G vehicle network based on EC and deep learning (DL), and analyzes its performance by simulation. The results reveal that the proposed algorithm has a lower average delay cost, and the average unloading utility is stable at approximately 70%. In the prediction performance analysis, the recognition accuracy of the proposed algorithm reaches 98.06%. It is at least 1.14% higher than that of the advanced convolution neural network (CNN) algorithm proposed by other scholars and achieves a faster convergence rate. Therefore, the constructed short-term traffic prediction model implemented has a high-quality prediction performance while also ensuring a better unloading performance. The results can provide an experimental basis for traffic flow prediction and intelligent development of the smart city.

This article proposes an improved artificial bee colony algorithm (IABC) for maintaining a balance between the exploratory and exploitative abilities of the algorithm. Therefore, unmodeled dynamic characteristics can be effectively estimated, which can improve the estimation accuracy of the system and create conditions for later system modeling and control. The proposed IABC algorithm uses two new search expressions to generate new alternative solutions and the global optimal solution is considered in the search process. Exploiting the simple structure and fast global convergence of artificial bee colony algorithm, an improved clustering algorithm combining IABC and Kernel fuzzy c-means (KFCM) iteration is also proposed. KFCM algorithm is sensitive to the initial clustering center and can easily fall into local optimum; and the improved clustering algorithm solves this issue. Compared with other algorithms, IABC algorithm can converge faster and more accurately for a given parameter structure and number of cycles. Three sets of benchmark test functions and six sets of UC Irvine standard datasets were used in the simulation experiments conducted. Experimental results show that KFCM-IABC can aggregate datasets faster than generalized fuzzy c-means (GFCM)-IABC because of the use of IABC. The proposed algorithm improves class validity index from 1 to 4%, thereby exhibiting the advantages of strong robustness and high clustering accuracy.