paper-with-me

Papers

RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies

2026-04-10 · Xuning Yang, Rishit Dagli, Alex Zook, Hugo Hadfield, Ankit Goyal, Stan Birchfield, Fabio Ramos, Jonathan Tremblay arxiv

The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid performance saturation and a lack of true generalization testing. Existing benchmarks often exhibit significant domain overlap between training and evaluation, trivializing success rates and obscuring insights into robustness. We introduce RoboLab, a simulation benchmarking framework designed to address these challenges. Concretely, our framework is designed to answer two questions: (1) to what extent can we understand the performance of a real-world policy by analyzing its behavior in simulation, and (2) which factor most strongly affect policy behavior. First, RoboLab enables human-authored and LLM-enabled generation of scenes and tasks in a robot- and policy-agnostic manner within a high-fidelity simulation environment. We introduce an accompanying RoboLab-120 benchmark, consisting of 120 tasks categorized into three competency axes: visual, procedural, relational, across three difficulty levels. Second, we introduce a systematic analysis of real-world policies that quantify both their performance and the sensitivity of their behavior to controlled perturbations, exposing significant performance gap in current state-of-the-art models. By providing granular metrics and a scalable toolset, RoboLab offers a scalable framework for evaluating the true generalization capabilities of task-generalist robotic policies. Project website: https://research.nvidia.com/labs/srl/projects/robolab/.

📄 PDF Abstract BibTeX arXiv:2604.09860

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Manifold Alignment-Based Multi-Fidelity Reduced-Order Modeling Applied to Structural Analysis

2022-06-14 · Christian Perron, Darshan Sarojini, Dushhyanth Rajaram, Jason Corman 외

This work presents the application of a recently developed parametric, non-intrusive, and multi-fidelity reduced-order modeling method on high-dimensional displacement and stress fields arising from the structural analys…

Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation

2026-05-07 · Yixin Zhu, Zixiong Wang, Jian Yang, Jin Xie 외 arxiv

Reliable simulation evaluation of robot manipulation policies serves as a high-fidelity proxy for real-world performance. Although existing benchmarks cover a wide range of task categories, they lack visual realism, crea…

Robot Manipulation

Multifidelity Surrogate Modeling of Depressurized Loss of Forced Cooling in High-temperature Gas Reactors

2026-03-14 · Meredith Eaheart, Majdi I. Radaideh arxiv

High-fidelity computational fluid dynamics (CFD) simulations are widely used to analyze nuclear reactor transients, but are computationally expensive when exploring large parameter spaces. Multifidelity surrogate models …

Gaussian Processes

Field-level weak lensing cosmology with $<100$ simulations using multifidelity simulation-based inference

2026-06-22 · Alex A. Saoulis, Kiyam Lin, Niall Jeffrey, Maximilian von Wietersheim-Kramsta 외 arxiv

We perform a realistic KiDS-Legacy mock analysis with field-level neural compression and simulation-based inference using fewer than 100 $N$-body simulations. The weak lensing shear field encodes substantially more cosmo…

Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusion

2023-11-15 · Francis Ogoke, Quanliang Liu, Olabode Ajenifujah, Alexander Myers 외

Defects in laser powder bed fusion (L-PBF) parts often result from the meso-scale dynamics of the molten alloy near the laser, known as the melt pool. For instance, the melt pool can directly contribute to the formation …