Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Junhui, Gong, Yuhe, Li, Changsheng, Duan, Xingguang, Figueredo, Luis
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.06031
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909900964102144
author Huang, Junhui
Gong, Yuhe
Li, Changsheng
Duan, Xingguang
Figueredo, Luis
author_facet Huang, Junhui
Gong, Yuhe
Li, Changsheng
Duan, Xingguang
Figueredo, Luis
contents We present GELATO -- the first language-driven trajectory reshaping framework to embed geometric environment awareness and multi-agent feedback orchestration to support multi-instruction in human-robot interaction scenarios. Unlike prior learning-based methods, our approach automatically registers scene objects as 6D geometric primitives via a VLM-assisted multi-view pipeline, and an LLM translates free-form multiple instructions into explicit, verifiable geometric constraints. These are integrated into a geometric-aware vector field optimization to adapt initial trajectories while preserving smoothness, feasibility, and clearance. We further introduce a multi-agent orchestration with observer-based refinement to handle multi-instruction inputs and interactions among objectives -- increasing success rate without retraining. Simulation and real-world experiments demonstrate our method achieves smoother, safer, and more interpretable trajectory modifications compared to state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06031
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GELATO: Multi-Instruction Trajectory Reshaping via Geometry-Aware Multiagent-based Orchestration
Huang, Junhui
Gong, Yuhe
Li, Changsheng
Duan, Xingguang
Figueredo, Luis
Robotics
We present GELATO -- the first language-driven trajectory reshaping framework to embed geometric environment awareness and multi-agent feedback orchestration to support multi-instruction in human-robot interaction scenarios. Unlike prior learning-based methods, our approach automatically registers scene objects as 6D geometric primitives via a VLM-assisted multi-view pipeline, and an LLM translates free-form multiple instructions into explicit, verifiable geometric constraints. These are integrated into a geometric-aware vector field optimization to adapt initial trajectories while preserving smoothness, feasibility, and clearance. We further introduce a multi-agent orchestration with observer-based refinement to handle multi-instruction inputs and interactions among objectives -- increasing success rate without retraining. Simulation and real-world experiments demonstrate our method achieves smoother, safer, and more interpretable trajectory modifications compared to state-of-the-art baselines.
title GELATO: Multi-Instruction Trajectory Reshaping via Geometry-Aware Multiagent-based Orchestration
topic Robotics
url https://arxiv.org/abs/2509.06031