FlowMaps: Modeling Long-Term Multimodal Object Dynamics with Flow Matching

2026-06-18

AI Summary

This work addresses the challenge of reliably tracking dynamic objects in domestic environments, where human daily activities continuously alter object locations. To this end, the authors propose FlowMaps—a novel implicit model based on flow matching that, for the first time, introduces continuous multimodal spatiotemporal distribution modeling to predict future object positions. FlowMaps integrates historical human-object interaction data and explicitly captures spatiotemporal dependencies among objects, enabling multimodal and continuous 3D predictions of object locations through latent flow matching. Experimental results demonstrate that FlowMaps significantly outperforms state-of-the-art methods across over 600 dynamic navigation test sequences in both simulated and real-world settings, substantially enhancing robotic search and navigation capabilities in evolving home environments and enabling effective generalization to new spaces with similar object usage patterns.

Abstract

Joint spatial and temporal understanding of 3D scenes is a crucial requirement for robots deployed in everyday household environments. Such agents must not only comprehend and navigate spatial layouts, but also reason about how these spaces evolve over time. In particular, humans interact with objects daily, causing them to change position throughout the environment and making it difficult for robots to reliably associate current observations with previously seen objects. However, these interactions are not random: human habits and routines induce spatio-temporally consistent patterns in object locations, which robotic agents can potentially learn and then exploit for downstream tasks such as navigation. To this end, we introduce FlowMaps, a latent flow matching model for estimating multimodal distributions over the future locations of dynamic objects in a continuous 3D space. By learning the implicit dependencies among objects and their temporal evolution, FlowMaps predicts likely changes in object locations conditioned on past human interactions, while supporting generalization across previously unseen environments that share similar object routines. To demonstrate the utility of this method, we deploy FlowMaps in a downstream dynamic Object Navigation task in both simulated and real-world environments. Across more than 600 episodes, FlowMaps outperforms state-of-the-art approaches, showing that modeling object dynamics through continuous, multimodal spatio-temporal distributions improves robotic search and navigation in changing household environments. Code and additional material is available at https://fra-tsuna.github.io/flowmaps/.

Problem

• object dynamics
• spatio-temporal modeling
• dynamic object association
• robotic navigation
• multimodal distribution

Innovation

• Flow Matching
• Multimodal Dynamics
• 3D Scene Understanding
• Object Navigation
• Spatio-temporal Modeling