In this paper, a novel joint source-channel coding (JSCC) scheme based on the residual vector quantized diffusion model is proposed for task-oriented agent communication. To make the agent communication compatible with existing digital communication systems, the feature vectors encoded by the parameterized encoder are quantized using multiple learnable codebooks, forming the quantized features. Furthermore, to improve the reliability of quantized feature transmission, a discrete channel denoising diffusion model (DCDDM) is designed. The DCDDM can learn the distribution of the sender agent’s quantized features, and then utilize this learned knowledge to correct the receiver agent’s received quantized features. Based on the corrected feature vectors, the parameterized decoder recovers task-related information for the receiver agent’s subsequent decision-making. Finally, the model parameters of the proposed scheme are trained within the reinforcement learning framework. In addition, we design a task-oriented agent communication proof-of-concept prototype. Simulation and experiment results show that the proposed scheme has better generalization capability than the existing schemes. That is, with the proposed scheme, the transmission of task-related information is more reliable, thus the multi-agent systems can collaborate better under different channel conditions.

In this paper, we propose an age of incorrect information (AoII)-aware data dissemination scheme for distributed multi-agent systems (MASs). In the proposed scheme, AoII is utilized to measure the importance of data in terms of timeliness and content. We formulate the joint optimization of time slot allocation and agent selection as a decentralized partially observable Markov decision process (Dec-POMDP), with the objective of minimizing the AoII. To solve the Dec-POMDP, a novel multi-agent reinforcement learning algorithm (DV-MAPPO) is proposed. In particular, to tackle challenges posed by the partial observability of global system information, each agent estimates the global system state using variational inference. Moreover, to improve the accuracy of global system state estimation, each agent is given an intrinsic reward that is dominated by the accuracy of estimates. The proposed data dissemination scheme is implemented and evaluated in various missions. Simulation results show that the proposed data dissemination scheme outperforms traditional data dissemination schemes in terms of AoII. Furthermore, in typical multi-agent collaborative tasks, the proposed scheme facilitates more efficient cooperation among multiple agents compared to the data distribution mechanisms that ignore the importance of data.

The challenge for functional magnetic resonance imaging (fMRI) is to determine when and where the response due to an external stimulus occurs in the images. The temporal clustering analysis (TCA) method has been used to study brain activity after eating and drinking, in both the time and spatial domains. We propose a new method, competitive subspace projection (CSP), to represent data optimally compared to other subspace projection methods. This method is used to detect spatial and temporal activation patterns in fMRI associated with such behavior. The CSP and TCA methods are compared using both synthetic and real fMRI data. The results on both data sets show consistent conclusions can be drawn from these two methods while CSP is observed to have a better noise rejection capability than TCA.