EveryDayVLA: A Vision-Language-Action Model for Affordable Robotic Manipulation

TL;DR

EverydayVLA introduces an affordable, unified vision-language-action robotic system that achieves high success rates in manipulation tasks, combining cost-effective hardware with adaptive planning for reliable operation.

Contribution

The paper presents a low-cost, modular 6-DOF robot with a unified model for discrete and continuous actions, enhancing safety and reliability through adaptive re-planning.

Findings

Matches state-of-the-art success rates on LIBERO

Outperforms prior methods by 49% in-distribution

Outperforms prior methods by 34.9% out-of-distribution

Abstract

While Vision-Language-Action (VLA) models map visual inputs and language instructions directly to robot actions, they often rely on costly hardware and struggle in novel or cluttered scenes. We introduce EverydayVLA, a 6-DOF manipulator that can be assembled for under $300, capable of modest payloads and workspace. A single unified model jointly outputs discrete and continuous actions, and our adaptive-horizon ensemble monitors motion uncertainty to trigger on-the-fly re-planning for safe, reliable operation. On LIBERO, EverydayVLA matches state-of-the-art success rates, and in real-world tests it outperforms prior methods by 49% in-distribution and 34.9% out-of-distribution. By combining a state-of-the-art VLA with cost-effective hardware, EverydayVLA democratizes access to a robotic foundation model and paves the way for economical use in homes and research labs alike. Experiment videos and details: https://everydayvla.github.io/