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

• URL: http://arxiv.org/abs/2606.20209v1
• Date: Thu, 18 Jun 2026 13:21:40 GMT
• Title: FlowMaps: Modeling Long-Term Multimodal Object Dynamics with Flow Matching
• Abstract summary: FlowMaps is a latent flow matching model for estimating multimodal distributions over the future locations of dynamic objects in a continuous 3D space.<n>We show that FlowMaps outperforms state-of-the-art approaches for modeling object dynamics in changing household environments.
• Score: 9.947963106290413
• License: http://creativecommons.org/licenses/by/4.0/
• 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/.

Related papers

• From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video [62.898774619819676]
  Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize them.<n>We introduce Coherent4D, a large-scale egocentric dataset for continuous 4D interaction forecasting, comprising approximately 233K samples across three domains.<n>We propose HIGFlow, a Hand Interaction Guided Residual Flow framework that models forecasting as a cascaded where-to-how process.
  arXiv  Detail & Related papers  (2026-09-08T12:06:23Z)
• SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation [13.431320718523017]
  We present SuperMap, a 4D-temporal mapping framework for language-guided navigation.<n>Our core contribution is principled consistency-driven mapping engine that combines 3D-aware instance association/label-reactivation with a existence-and-label confidence update to maintain stable object identities.<n>SuperMap produces a queryable 4D scene-graph representation that interfaces naturally with Vision-Language Models.
  arXiv  Detail & Related papers  (2026-08-24T07:25:14Z)
• OASIS-Map: Object-Level Change Detection in Multi-Session Mapping using Semantic Correspondence Matching [2.68828933665259]
  Map consistent across repeated visits to a real-world semi-static environment is useful for long-term robotic inspection.<n>Existing change-detection methods reason through geometry, category-level semantics, or object persistence.<n>We propose a multi-session mapping system that maintains a segmentation-temporally consistent object-level representations.
  arXiv  Detail & Related papers  (2026-07-16T12:16:52Z)
• OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation [55.56490813640669]
  VLA models typically act only on the current frame, while future prediction and object-aware reasoning are often learned in separate latent spaces.<n>We propose OFlow, a framework that addresses both limitations by unifying temporal foresight and object-aware reasoning in a shared semantic latent space.<n>Our method forecasts future latents with temporal flow matching, factorizes them into object-aware representations that emphasize physically relevant cues.
  arXiv  Detail & Related papers  (2026-04-20T06:38:01Z)
• Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation [67.68165784193556]
  Nav-$R2$ is a framework that explicitly models two types of relationships, target-environment modeling and environment-action planning.<n>Our SA-Mem preserves the most target-relevant and current observation-relevant features from both temporal and semantic perspectives.<n>Nav-R2 achieves state-of-the-art performance in localizing unseen objects through a streamlined and efficient pipeline.
  arXiv  Detail & Related papers  (2025-12-02T04:21:02Z)
• Dynamic Objects Relocalization in Changing Environments with Flow Matching [9.997314076120956]
  FlowMaps is a model based on Flow Matching that is able to infer multimodal object locations over space and time.<n>Our results present statistical evidence to support our hypotheses, opening the way to more complex applications of our approach.
  arXiv  Detail & Related papers  (2025-09-19T20:21:16Z)
• LookOut: Real-World Humanoid Egocentric Navigation [61.14016011125957]
  We introduce the challenging problem of predicting a sequence of future 6D head poses from an egocentric video.<n>To solve this task, we propose a framework that reasons over temporally aggregated 3D latent features.<n>Motivated by the lack of training data in this space, we present a dataset collected through this approach.
  arXiv  Detail & Related papers  (2025-08-20T06:43:36Z)
• One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation [2.022249798290507]
  We introduce a new benchmark for zero-shot multi-object navigation.<n>We build a reusable open-vocabulary feature map tailored for real-time object search.<n>We demonstrate that it outperforms existing state-of-the-art approaches both on single and multi-object navigation tasks.
  arXiv  Detail & Related papers  (2024-09-18T07:44:08Z)
• Flow as the Cross-Domain Manipulation Interface [73.15952395641136]
  Im2Flow2Act enables robots to acquire real-world manipulation skills without the need of real-world robot training data. Im2Flow2Act comprises two components: a flow generation network and a flow-conditioned policy. We demonstrate Im2Flow2Act's capabilities in a variety of real-world tasks, including the manipulation of rigid, articulated, and deformable objects.
  arXiv  Detail & Related papers  (2024-07-21T16:15:02Z)
• TAS: A Transit-Aware Strategy for Embodied Navigation with Non-Stationary Targets [55.09248760290918]
  We present a novel algorithm for navigation in dynamic scenarios with non-stationary targets.<n>Our novel Transit-Aware Strategy (TAS) enriches embodied navigation policies with object path information.<n> TAS improves performance in non-stationary environments by rewarding agents for synchronizing their routes with target routes.
  arXiv  Detail & Related papers  (2024-03-14T22:33:22Z)
• Object Goal Navigation with Recursive Implicit Maps [92.6347010295396]
  We propose an implicit spatial map for object goal navigation. Our method significantly outperforms the state of the art on the challenging MP3D dataset. We deploy our model on a real robot and achieve encouraging object goal navigation results in real scenes.
  arXiv  Detail & Related papers  (2023-08-10T14:21:33Z)
• TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction [57.1209039399599]
  We propose a map representation that allows maintaining a single volume for the entire scene and all the objects therein. In a multiple dynamic object tracking and reconstruction scenario, our representation allows maintaining accurate reconstruction of surfaces even while they become temporarily occluded by other objects moving in their proximity. We evaluate the proposed TSDF++ formulation on a public synthetic dataset and demonstrate its ability to preserve reconstructions of occluded surfaces when compared to the standard TSDF map representation.
  arXiv  Detail & Related papers  (2021-05-16T16:15:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.