VABAR: A Variational Automation Benchmark for Agentic Robotics
VABAR: A Variational Automation Benchmark for Agentic Robotics
This paper introduces VABAR, a simulation-based benchmark designed to evaluate agentic robotics systems on six manipulation tasks involving variations in object shape and pose. The benchmark is built using open-source tools, features standardized task variations, difficulty tiers, success metrics, and a library of 33 generalizable skills with human-authored reference solutions. Initial baseline evaluations are provided using the Graph-as-Policy (GaP) harness and Isaac Lab Arena.
The authors propose VABAR, a simulation-based benchmark for agentic robotics that evaluates systems on six manipulation tasks with variations in object shape and pose, using open-source tools and an open agentic harness.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
anning industrial, medical, and infrastructure applications: tool sorting, tool hanging, gear meshing, syringe packing, cable insertion, and cable routing. We introduce the Variational Automation Benchmark for Agentic Robotics (VABAR), an open, easily replicable, simulation-based manipulation benchmark to systematically evaluating agentic robotics systems. Built fully on open-source tools, VABAR features detailed imp
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org