Bi-VLA: Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kobayashi, Masato, Buamanee, Thanpimon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916964340858880
author Kobayashi, Masato
Buamanee, Thanpimon
author_facet Kobayashi, Masato
Buamanee, Thanpimon
contents We propose Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action Generation (Bi-VLA), a novel framework that extends bilateral control-based imitation learning to handle more than one task within a single model. Conventional bilateral control methods exploit joint angle, velocity, torque, and vision for precise manipulation but require task-specific models, limiting their generality. Bi-VLA overcomes this limitation by utilizing robot joint angle, velocity, and torque data from leader-follower bilateral control with visual features and natural language instructions through SigLIP and FiLM-based fusion. We validated Bi-VLA on two task types: one requiring supplementary language cues and another distinguishable solely by vision. Real-robot experiments showed that Bi-VLA successfully interprets vision-language combinations and improves task success rates compared to conventional bilateral control-based imitation learning. Our Bi-VLA addresses the single-task limitation of prior bilateral approaches and provides empirical evidence that combining vision and language significantly enhances versatility. Experimental results validate the effectiveness of Bi-VLA in real-world tasks. For additional material, please visit the website: https://mertcookimg.github.io/bi-vla/
format Preprint
id arxiv_https___arxiv_org_abs_2509_18865
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bi-VLA: Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action Generation
Kobayashi, Masato
Buamanee, Thanpimon
Robotics
Machine Learning
We propose Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action Generation (Bi-VLA), a novel framework that extends bilateral control-based imitation learning to handle more than one task within a single model. Conventional bilateral control methods exploit joint angle, velocity, torque, and vision for precise manipulation but require task-specific models, limiting their generality. Bi-VLA overcomes this limitation by utilizing robot joint angle, velocity, and torque data from leader-follower bilateral control with visual features and natural language instructions through SigLIP and FiLM-based fusion. We validated Bi-VLA on two task types: one requiring supplementary language cues and another distinguishable solely by vision. Real-robot experiments showed that Bi-VLA successfully interprets vision-language combinations and improves task success rates compared to conventional bilateral control-based imitation learning. Our Bi-VLA addresses the single-task limitation of prior bilateral approaches and provides empirical evidence that combining vision and language significantly enhances versatility. Experimental results validate the effectiveness of Bi-VLA in real-world tasks. For additional material, please visit the website: https://mertcookimg.github.io/bi-vla/
title Bi-VLA: Bilateral Control-Based Imitation Learning via Vision-Language Fusion for Action Generation
topic Robotics
Machine Learning
url https://arxiv.org/abs/2509.18865