THE WORLD IS NOT STANDING STILL.RSS
BIG CHANGE.
BIG CHANGE, one tap away
BIG CHANGE, one tap away

Make room for the big picture.

Add BIG CHANGE to your home screen or desktop. It opens in its own window, with the latest stories when you’re online.

iPhone & iPad
Open bigchange.ai in Safari. Tap Share, then Add to Home Screen. Turn on Open as Web App if shown, then tap Add.
Android
Open bigchange.ai in Chrome. In the browser menu, choose Install app or Add to Home screen.
Desktop
In Chrome or Edge, use the install icon in the address bar or the browser’s app menu. In Safari on Mac, choose File → Add to Dock.

Markdown edition

# VABAR tests robot manipulation under variation

> Researchers test changing simulated manipulation tasks.

By BIGCHANGE.AI Editorial

Published: 2026-11-05T13:56:38.529Z
Updated: 2026-11-05T13:56:38.529Z
Canonical: https://bigchange.ai/blog/vabar-robotics-variation-benchmark

![Conceptual illustration of a robot gripper above gears on a workbench.](https://bigchange.ai/api/media/file/robot-gear-concept.png)
AI-generated conceptual illustration by BIG CHANGE.

The [November 4 VABAR preprint](https://arxiv.org/html/2611.06881) introduces a simulation benchmark for robot manipulation under changing conditions.

## The big change

- Six tasks include variations in pose, layout and clutter.
- Generated and human-authored programs share robot skills.
- Simulated results do not establish real-world reliability.

## Why variation matters

VABAR specifies permitted variations and success conditions. In gear meshing, a simulated arm assembles gears on axles; the harder tier adds a third gear.

VABAR provides skills for perception, grasping, planning and verification. The authors’ earlier [Graph-as-Policy paper](https://arxiv.org/abs/2607.05369) describes a system that composes such skills into executable graphs and rehearses them in simulation. In that design, simulation rehearsal can expose failures and guide revisions to a graph before deployment. It does not independently validate VABAR.

## What the baseline shows

The study evaluated 30 instances per task and difficulty condition. On easier gear meshing, an agent-generated graph succeeded in 70% of simulated trials versus 100% for a human-authored graph with the same perception, skill, planning and execution stack. The comparison concerns graph construction within that setup.

VABAR records observations, actions and simulated contacts to help diagnose failures. These simulations do not establish physical-robot performance or independent replication.

## Sources

- [VABAR preprint](https://arxiv.org/html/2611.06881) — Simulation benchmark and authors’ baselines.
- [Graph-as-Policy preprint](https://arxiv.org/abs/2607.05369) — Earlier robot program-generation research.