Implicit State Estimation via Video Replanning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ko, Po-Chen, Mao, Jiayuan, Fu, Yu-Hsiang, Yeh, Hsien-Jeng, Chen, Chu-Rong, Ma, Wei-Chiu, Du, Yilun, Sun, Shao-Hua
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915787808178176
author Ko, Po-Chen
Mao, Jiayuan
Fu, Yu-Hsiang
Yeh, Hsien-Jeng
Chen, Chu-Rong
Ma, Wei-Chiu
Du, Yilun
Sun, Shao-Hua
author_facet Ko, Po-Chen
Mao, Jiayuan
Fu, Yu-Hsiang
Yeh, Hsien-Jeng
Chen, Chu-Rong
Ma, Wei-Chiu
Du, Yilun
Sun, Shao-Hua
contents Video-based representations have gained prominence in planning and decision-making due to their ability to encode rich spatiotemporal dynamics and geometric relationships. These representations enable flexible and generalizable solutions for complex tasks such as object manipulation and navigation. However, existing video planning frameworks often struggle to adapt to failures at interaction time due to their inability to reason about uncertainties in partially observed environments. To overcome these limitations, we introduce a novel framework that integrates interaction-time data into the planning process. Our approach updates model parameters online and filters out previously failed plans during generation. This enables implicit state estimation, allowing the system to adapt dynamically without explicitly modeling unknown state variables. We evaluate our framework through extensive experiments on a new simulated manipulation benchmark, demonstrating its ability to improve replanning performance and advance the field of video-based decision-making.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17315
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Implicit State Estimation via Video Replanning
Ko, Po-Chen
Mao, Jiayuan
Fu, Yu-Hsiang
Yeh, Hsien-Jeng
Chen, Chu-Rong
Ma, Wei-Chiu
Du, Yilun
Sun, Shao-Hua
Robotics
Video-based representations have gained prominence in planning and decision-making due to their ability to encode rich spatiotemporal dynamics and geometric relationships. These representations enable flexible and generalizable solutions for complex tasks such as object manipulation and navigation. However, existing video planning frameworks often struggle to adapt to failures at interaction time due to their inability to reason about uncertainties in partially observed environments. To overcome these limitations, we introduce a novel framework that integrates interaction-time data into the planning process. Our approach updates model parameters online and filters out previously failed plans during generation. This enables implicit state estimation, allowing the system to adapt dynamically without explicitly modeling unknown state variables. We evaluate our framework through extensive experiments on a new simulated manipulation benchmark, demonstrating its ability to improve replanning performance and advance the field of video-based decision-making.
title Implicit State Estimation via Video Replanning
topic Robotics
url https://arxiv.org/abs/2510.17315