AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gubernatorov, Konstantin, Voronov, Artem, Voronov, Roman, Pasynkov, Sergei, Perminov, Stepan, Guo, Ziang, Tsetserukou, Dzmitry
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909805901250560
author Gubernatorov, Konstantin
Voronov, Artem
Voronov, Roman
Pasynkov, Sergei
Perminov, Stepan
Guo, Ziang
Tsetserukou, Dzmitry
author_facet Gubernatorov, Konstantin
Voronov, Artem
Voronov, Roman
Pasynkov, Sergei
Perminov, Stepan
Guo, Ziang
Tsetserukou, Dzmitry
contents We address natural language pick-and-place in unseen, unpredictable indoor environments with AnywhereVLA, a modular framework for mobile manipulation. A user text prompt serves as an entry point and is parsed into a structured task graph that conditions classical SLAM with LiDAR and cameras, metric semantic mapping, and a task-aware frontier exploration policy. An approach planner then selects visibility and reachability aware pre grasp base poses. For interaction, a compact SmolVLA manipulation head is fine tuned on platform pick and place trajectories for the SO-101 by TheRobotStudio, grounding local visual context and sub-goals into grasp and place proposals. The full system runs fully onboard on consumer-level hardware, with Jetson Orin NX for perception and VLA and an Intel NUC for SLAM, exploration, and control, sustaining real-time operation. We evaluated AnywhereVLA in a multi-room lab under static scenes and normal human motion. In this setting, the system achieves a $46\%$ overall task success rate while maintaining throughput on embedded compute. By combining a classical stack with a fine-tuned VLA manipulation, the system inherits the reliability of geometry-based navigation with the agility and task generalization of language-conditioned manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21006
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation
Gubernatorov, Konstantin
Voronov, Artem
Voronov, Roman
Pasynkov, Sergei
Perminov, Stepan
Guo, Ziang
Tsetserukou, Dzmitry
Robotics
Artificial Intelligence
We address natural language pick-and-place in unseen, unpredictable indoor environments with AnywhereVLA, a modular framework for mobile manipulation. A user text prompt serves as an entry point and is parsed into a structured task graph that conditions classical SLAM with LiDAR and cameras, metric semantic mapping, and a task-aware frontier exploration policy. An approach planner then selects visibility and reachability aware pre grasp base poses. For interaction, a compact SmolVLA manipulation head is fine tuned on platform pick and place trajectories for the SO-101 by TheRobotStudio, grounding local visual context and sub-goals into grasp and place proposals. The full system runs fully onboard on consumer-level hardware, with Jetson Orin NX for perception and VLA and an Intel NUC for SLAM, exploration, and control, sustaining real-time operation. We evaluated AnywhereVLA in a multi-room lab under static scenes and normal human motion. In this setting, the system achieves a $46\%$ overall task success rate while maintaining throughput on embedded compute. By combining a classical stack with a fine-tuned VLA manipulation, the system inherits the reliability of geometry-based navigation with the agility and task generalization of language-conditioned manipulation.
title AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2509.21006