Saved in:
Bibliographic Details
Main Authors: Liu, Fengkai, Su, Hao, Chi, Haozhuang, Geng, Rui, Ren, Congzhi, Liu, Xuqing, Xu, Yucheng, Ohsita, Yuichi, Zhang, Liyun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.23950
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918407648051200
author Liu, Fengkai
Su, Hao
Chi, Haozhuang
Geng, Rui
Ren, Congzhi
Liu, Xuqing
Xu, Yucheng
Ohsita, Yuichi
Zhang, Liyun
author_facet Liu, Fengkai
Su, Hao
Chi, Haozhuang
Geng, Rui
Ren, Congzhi
Liu, Xuqing
Xu, Yucheng
Ohsita, Yuichi
Zhang, Liyun
contents Assistance in collaborative manipulation is often initiated by user instructions, making high-level reasoning request-driven. In fluent human teamwork, however, partners often infer the next helpful step from the observed outcome of an action rather than waiting for instructions. Motivated by this, we introduce a shift from request-driven assistance to event-driven proactive assistance, where robot actions are initiated by workspace state transitions induced by human--object interactions rather than user-provided task instructions. To this end, we propose an event-driven framework that tracks interaction progress with an event monitor and, upon event completion, extracts stabilized pre/post snapshots that characterize the resulting state transition. Given the stabilized snapshots, the planner analyzes the implied state transition to infer a task-level goal and decide whether to intervene; if so, it generates a sequence of assistive actions. To make outputs executable and verifiable, we restrict actions to a set of action primitives and reference objects via integer IDs. We evaluate the framework on a real tabletop number-block collaboration task, demonstrating that explicit pre/post state-change evidence improves proactive completion on solvable scenes and appropriate waiting on unsolvable ones.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23950
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Event-Driven Proactive Assistive Manipulation with Grounded Vision-Language Planning
Liu, Fengkai
Su, Hao
Chi, Haozhuang
Geng, Rui
Ren, Congzhi
Liu, Xuqing
Xu, Yucheng
Ohsita, Yuichi
Zhang, Liyun
Robotics
Assistance in collaborative manipulation is often initiated by user instructions, making high-level reasoning request-driven. In fluent human teamwork, however, partners often infer the next helpful step from the observed outcome of an action rather than waiting for instructions. Motivated by this, we introduce a shift from request-driven assistance to event-driven proactive assistance, where robot actions are initiated by workspace state transitions induced by human--object interactions rather than user-provided task instructions. To this end, we propose an event-driven framework that tracks interaction progress with an event monitor and, upon event completion, extracts stabilized pre/post snapshots that characterize the resulting state transition. Given the stabilized snapshots, the planner analyzes the implied state transition to infer a task-level goal and decide whether to intervene; if so, it generates a sequence of assistive actions. To make outputs executable and verifiable, we restrict actions to a set of action primitives and reference objects via integer IDs. We evaluate the framework on a real tabletop number-block collaboration task, demonstrating that explicit pre/post state-change evidence improves proactive completion on solvable scenes and appropriate waiting on unsolvable ones.
title Event-Driven Proactive Assistive Manipulation with Grounded Vision-Language Planning
topic Robotics
url https://arxiv.org/abs/2603.23950