InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories

2026-04-05

AI Summary

Existing approaches struggle to generate realistic, controllable, and semantically faithful GPS trajectories from natural language travel intents, primarily due to limited comprehension of complex semantics and inadequate modeling of human behavioral diversity. This work proposes a novel framework that integrates large language models with a multimodal trajectory diffusion Transformer, enabling, for the first time, direct high-fidelity trajectory generation from natural language instructions. By leveraging semantic parsing and a conditional diffusion mechanism, the method significantly outperforms current state-of-the-art approaches on real-world datasets, achieving superior performance in trajectory realism, diversity, and semantic fidelity. The proposed approach effectively bridges the gap between high-level semantic intent and low-level trajectory representation.

Abstract

The generation of realistic and controllable GPS trajectories is a fundamental task for applications in urban planning, mobility simulation, and privacy-preserving data sharing. However, existing methods face a two-fold challenge: they lack the deep semantic understanding to interpret complex user travel intent, and struggle to handle complex constraints while maintaining the realistic diversity inherent in human behavior. To resolve this, we introduce InsTraj, a novel framework that instructs diffusion models to generate high-fidelity trajectories directly from natural language descriptions. Specifically, InsTraj first utilizes a powerful large language model to decipher unstructured travel intentions formed in natural language, thereby creating rich semantic blueprints and bridging the representation gap between intentions and trajectories. Subsequently, we proposed a multimodal trajectory diffusion transformer that can integrate semantic guidance to generate high-fidelity and instruction-faithful trajectories that adhere to fine-grained user intent. Comprehensive experiments on real-world datasets demonstrate that InsTraj significantly outperforms state-of-the-art methods in generating trajectories that are realistic, diverse, and semantically faithful to the input instructions.

Problem

• trajectory generation
• travel intention
• semantic understanding
• realistic diversity
• controllable generation

Innovation

• diffusion models
• travel intention
• natural language guidance
• trajectory generation
• multimodal transformer