Inferring Group Intent as a Cooperative Game. An NLP-based Framework for Trajectory Analysis using Graph Transformer Neural Network

2025-10-27

AI Summary

This study addresses the critical problem of group trajectory intent recognition. Methodologically, it formalizes collective intent as a cooperative game characteristic function, differentiable and interpretable via Fisher information geometry. It integrates a syntax-driven NLP generative model with a Graph Transformer Neural Network (GTNN), augmented by Bayesian signal processing and Shapley value/nucleolus-based allocation mechanisms to robustly infer collaborative intent from noisy observations. Contributions include: (i) the first unified modeling framework bridging game-theoretic semantics with spatiotemporal trajectory generation; (ii) GTNN’s capability to accurately reconstruct group-level collaborative structures under noise; and (iii) strict adherence of generated trajectories to motion semantics constraints. Experiments demonstrate significant improvements in both intent recognition accuracy and interpretability over state-of-the-art approaches.

Technology Category

• Game Theory and Economic Paradigms: Cooperative Game Theory
• Natural Language Processing: Generation
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

This paper studies group target trajectory intent as the outcome of a cooperative game where the complex-spatio trajectories are modeled using an NLP-based generative model. In our framework, the group intent is specified by the characteristic function of a cooperative game, and allocations for players in the cooperative game are specified by either the core, the Shapley value, or the nucleolus. The resulting allocations induce probability distributions that govern the coordinated spatio-temporal trajectories of the targets that reflect the group's underlying intent. We address two key questions: (1) How can the intent of a group trajectory be optimally formalized as the characteristic function of a cooperative game? (2) How can such intent be inferred from noisy observations of the targets? To answer the first question, we introduce a Fisher-information-based characteristic function of the cooperative game, which yields probability distributions that generate coordinated spatio-temporal patterns. As a generative model for these patterns, we develop an NLP-based generative model built on formal grammar, enabling the creation of realistic multi-target trajectory data. To answer the second question, we train a Graph Transformer Neural Network (GTNN) to infer group trajectory intent-expressed as the characteristic function of the cooperative game-from observational data with high accuracy. The self-attention function of the GTNN depends on the track estimates. Thus, the formulation and algorithms provide a multi-layer approach that spans target tracking (Bayesian signal processing) and the GTNN (for group intent inference).

Problem

• Modeling group trajectory intent as cooperative game outcomes
• Developing NLP-based generative model for coordinated spatio-temporal patterns
• Inferring group intent from noisy observations using Graph Transformer Neural Network

Innovation

• Modeling group intent as cooperative game characteristic function
• Using NLP-based generative model with formal grammar
• Training Graph Transformer Neural Network for intent inference