Intention-aware Hierarchical Diffusion Model for Long-term Trajectory Anomaly Detection
On the map: Diffusion models → Diffusion and flow policies for robotics
Abstract (arXiv)
Long-term trajectory anomaly detection is a challenging problem due to the diversity and complex spatiotemporal dependencies in trajectory data. Existing trajectory anomaly detection methods fail to simultaneously consider both the high-level intentions of agents as well as the low-level details of the agent's navigation when analysing an agent's trajectories. This limits their ability to capture the full diversity of normal trajectories. In this paper, we propose an unsupervised trajectory anomaly detection method named Intention-aware Hierarchical Diffusion model (IHiD), which detects anomalies through both high-level intent evaluation and low-level sub-trajectory analysis. Our approach leverages Inverse Q Learning as the high-level model to assess whether a selected subgoal aligns with an agent's intention based on predicted Q-values. Meanwhile, a diffusion model serves as the low-level model to generate sub-trajectories conditioned on subgoal information, with anomaly detection based on reconstruction error. By integrating both models, IHiD effectively utilises subgoal transition knowledge and is designed to capture the diverse distribution of normal trajectories. Our experiments show that the proposed method IHiD achieves up to 30.2% improvement in anomaly detection performance in terms of F1 score over state-of-the-art baselines.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 17 of its 40 references that are in the map. First posted on arXiv 21 Sep 2025.
Builds on
17 of 40 references.
References · 17
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
- 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
- 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 215
- 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 193
- 2022BITS: Bi-level Imitation for Traffic Simulationcited by 80
- 2023On Diffusion Modeling for Anomaly Detectioncited by 72
- 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 59
- 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectioncited by 42
- 2021A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videoscited by 28
5 more
- 2020Sequential Anomaly Detection using Inverse Reinforcement Learningcited by 20
- 2021Adversarial Option-Aware Hierarchical Imitation Learningcited by 19
- 2023Time Series Anomaly Detection using Diffusion-based Modelscited by 12
- 2023GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimationcited by 6
- 2024IDIL: Imitation Learning of Intent-Driven Expert Behaviorcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Intention-aware Denoising Diffusion Model for Trajectory Prediction
- 2025Towards Physics-informed Diffusion for Anomaly Detection in Trajectories
- 2025CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection
- 2025Anomalous Decision Discovery using Inverse Reinforcement Learning
- 2026Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI
- 2025Intention-Aware Diffusion Model for Pedestrian Trajectory Prediction
- 2026Mobility Anomaly Generation using LLM-Driven Behavior with Kinematic Constraints
- 2026TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation