Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Peng, Kunyu, Zhou, Zhikun, Yang, Kailun, Wen, Di, Liu, Ruiping, Chen, Yufan, Zheng, Junwei, Shi, Hao, Zhou, Yi, Sarfraz, M. Saquib, Paudel, Danda Pani, Van Gool, Luc
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.18431
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910234140737536
author Peng, Kunyu
Zhou, Zhikun
Yang, Kailun
Wen, Di
Liu, Ruiping
Chen, Yufan
Zheng, Junwei
Shi, Hao
Zhou, Yi
Sarfraz, M. Saquib
Paudel, Danda Pani
Van Gool, Luc
author_facet Peng, Kunyu
Zhou, Zhikun
Yang, Kailun
Wen, Di
Liu, Ruiping
Chen, Yufan
Zheng, Junwei
Shi, Hao
Zhou, Yi
Sarfraz, M. Saquib
Paudel, Danda Pani
Van Gool, Luc
contents Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoints remains largely unexplored. We study this problem through multi-robot cooperative dynamic spatial reasoning, where a model must answer spatial, temporal, visibility, and coordination questions by integrating synchronized egocentric videos from a team of moving robots. To support this setting, we introduce CoopSR, the first benchmark for this task, together with EgoTeam, a multi-robot egocentric QA dataset. EgoTeam contains 114,227 QA pairs spanning 19 question types, four difficulty tiers, and three team sizes in Habitat and iGibson, along with a real-world test set of around 2,326 QAs collected using two quadruped robots. We further propose SP-CoR (Spectral and Physics-Informed Cooperative Reasoner), an MLLM framework for fine-grained cooperative spatial reasoning. SP-CoR combines dynamics-aware multi-robot frame sampling, spectral- and physics-guided view fusion, and physics-aligned prompt distillation, enabling the model to benefit from privileged robot-pose supervision during training while requiring only egocentric videos at test time. Across 22 MLLM baselines, SP-CoR consistently improves cooperative reasoning, outperforming the strongest fine-tuned baseline by +3.87% on Habitat and +7.12% on iGibson. It also shows stronger generalization to unseen team sizes and real-world robot tests. Code can be found at https://github.com/KPeng9510/seeing-together.git.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18431
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
Peng, Kunyu
Zhou, Zhikun
Yang, Kailun
Wen, Di
Liu, Ruiping
Chen, Yufan
Zheng, Junwei
Shi, Hao
Zhou, Yi
Sarfraz, M. Saquib
Paudel, Danda Pani
Van Gool, Luc
Computer Vision and Pattern Recognition
Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoints remains largely unexplored. We study this problem through multi-robot cooperative dynamic spatial reasoning, where a model must answer spatial, temporal, visibility, and coordination questions by integrating synchronized egocentric videos from a team of moving robots. To support this setting, we introduce CoopSR, the first benchmark for this task, together with EgoTeam, a multi-robot egocentric QA dataset. EgoTeam contains 114,227 QA pairs spanning 19 question types, four difficulty tiers, and three team sizes in Habitat and iGibson, along with a real-world test set of around 2,326 QAs collected using two quadruped robots. We further propose SP-CoR (Spectral and Physics-Informed Cooperative Reasoner), an MLLM framework for fine-grained cooperative spatial reasoning. SP-CoR combines dynamics-aware multi-robot frame sampling, spectral- and physics-guided view fusion, and physics-aligned prompt distillation, enabling the model to benefit from privileged robot-pose supervision during training while requiring only egocentric videos at test time. Across 22 MLLM baselines, SP-CoR consistently improves cooperative reasoning, outperforming the strongest fine-tuned baseline by +3.87% on Habitat and +7.12% on iGibson. It also shows stronger generalization to unseen team sizes and real-world robot tests. Code can be found at https://github.com/KPeng9510/seeing-together.git.
title Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.18431