Long-Term Human Motion Prediction Using Spatio-Temporal Maps of Dynamics

2025-10-03

AI Summary

Long-horizon human motion prediction (LHMP) is critical for safe planning in human-robot coexistence scenarios; however, existing methods suffer from insufficient accuracy in 60-second predictions and fail to adequately model the time-varying nature of motion patterns. To address this, we propose a prediction framework based on time-conditioned dynamic motion graphs (MoDs). First, we construct multi-scale motion dynamic graphs to explicitly encode spatiotemporal dependencies. Second, we introduce a time-conditioning mechanism to adaptively capture stage-specific motion evolution. Third, we design a trajectory ranking module to select the optimal predicted path. Our method jointly models environmental context and historical motion sequences, enabling end-to-end long-horizon prediction. Experiments on two real-world datasets demonstrate that our approach reduces mean displacement error by up to 50% over prior methods; the time-conditioned variant achieves state-of-the-art performance.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Long-term human motion prediction (LHMP) is important for the safe and efficient operation of autonomous robots and vehicles in environments shared with humans. Accurate predictions are important for applications including motion planning, tracking, human-robot interaction, and safety monitoring. In this paper, we exploit Maps of Dynamics (MoDs), which encode spatial or spatio-temporal motion patterns as environment features, to achieve LHMP for horizons of up to 60 seconds. We propose an MoD-informed LHMP framework that supports various types of MoDs and includes a ranking method to output the most likely predicted trajectory, improving practical utility in robotics. Further, a time-conditioned MoD is introduced to capture motion patterns that vary across different times of day. We evaluate MoD-LHMP instantiated with three types of MoDs. Experiments on two real-world datasets show that MoD-informed method outperforms learning-based ones, with up to 50% improvement in average displacement error, and the time-conditioned variant achieves the highest accuracy overall. Project code is available at https://github.com/test-bai-cpu/LHMP-with-MoDs.git

Problem

• Predicting long-term human motion for autonomous systems
• Improving trajectory accuracy using spatio-temporal dynamics maps
• Capturing time-varying motion patterns for robotics applications

Innovation

• Uses spatio-temporal Maps of Dynamics for prediction
• Introduces time-conditioned variant for daily patterns
• Ranks trajectories to output most likely path