← Back to Benchmarks
simmediummanipulationmetric · varies

MobileManiBench: Simplifying Model Verification for Mobile Manipulation

Description

Vision-language-action models have advanced robotic manipulation but remain constrained by reliance on the large, teleoperation-collected datasets dominated by the static, tabletop scenes. We propose a simulation-first framework to verify VLA architectures before real-world deployment and introduce MobileManiBench, a large-scale benchmark for mobile-based robotic manipulation. Built on NVIDIA Isaac Sim and powered by reinforcement learning, our pipeline autonomously generates diverse manipulatio

Source

http://arxiv.org/abs/2602.05233v1