Driving · 2026-10-21

Physical AI for Intralogistics: Benchmarking the NVIDIA Sim-to-Real Ecosystem for Cosmos-Enhanced COMPASS Navigation on Industrial Mobile Robots

Charbel Abi Hana (Idealworks), Rayan Zaitouni (Idealworks), Kameel Amareen (Idealworks), Mohamad Mostafa (Idealworks), Hasan Sayour (Idealworks), Wei Liu (NVIDIA), Yan Chang (NVIDIA), Mihir Acharya (NVIDIA), Anthony Rizk (Idealworks)

arXiv:2610.28432PDF

AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.

TL;DR

The authors benchmark NVIDIA X-Mobility + COMPASS for learned navigation on Idealworks industrial mobile robots, studying reliability under sim-to-real transfer. In sim, they extend COMPASS with iw.hub and HMP embodiments and an Idealworks R&D center digital twin. In the real facility, they fine-tune X-Mobility on digital-twin data, optionally augmented with NVIDIA Cosmos, then train COMPASS residuals and compare on success/efficiency/safety/smoothness/compute.

Why it matters

Industrial AMR navigation often needs per-robot/per-site re-engineering, while learning-based approaches promise adaptation via simulation data and fine-tuning. The authors report systematic real-robot testing of the X-Mobility/COMPASS workflow and quantify the sim-to-real gap and how much Cosmos-augmented data closes it, including deployment on the iw.hub’s onboard compute.

Method

  • Extend COMPASS simulation benchmark with iw.hub and HMP embodiments plus a digital twin of the Idealworks R&D center; evaluate success rate (SR) and weighted travel time (WTT).
  • Real-world benchmark on a physical iw.hub: compare Idealworks production navigation vs NVIDIA COMPASS (no R&D data), IW.COMPASS (fine-tune on digital twin), and IW.CE-COMPASS (fine-tune on Cosmos-augmented sim-to-real variants).
  • Deploy learned policies onboard (Jetson AGX Xavier) and evaluate on static scenarios in both digital-twin replicas and the real facility to measure sim-to-real gap.

Limitation

The digital-twin replica does not replicate the dynamic scenario S4 because moving obstacles in the digital twin are not explored in this work; no interaction metrics are reported and protective stops are not measured in simulation.

Abstract (from arXiv)

Classical robot navigation stacks are reliable but often require re-engineering for each new robot type and site. Learning-based navigation shifts this effort from hand-tuned parameters to data generation and training, where a policy adapts to each new embodiment or facility by fine-tuning in simulation. Whether policies adapted this way stay reliable on real industrial robots has seen little systematic testing. We study this for NVIDIA's X-Mobility and COMPASS workflow for training learned navigation policies on Idealworks robots. In simulation, we extend the COMPASS benchmark with two embodiments, the differential-drive iw.hub and an omnidirectional Humanoid Mobile Platform (HMP), and with a digital twin of the Idealworks R&D center. For the real world, we fine-tune X-Mobility on data from this digital twin, with and without sim-to-real variants generated by NVIDIA Cosmos, train COMPASS on top of it from scratch in the digital twin, deploy the resulting policies on the iw.hub's onboard Jetson AGX Xavier, and benchmark them in the Idealworks R&D center against COMPASS trained only on NVIDIA's environments and the existing Idealworks navigation stack on task success, efficiency, safety, smoothness and onboard compute. Running every static scenario both in a digital-twin replica and in the real facility measures the sim-to-real gap and how far Cosmos-augmented data closes it. Training in the digital twin with Cosmos sim-to-real augmentation raises the real-world success rate of learned navigation from 65.3% to 91.7% across four scenarios and nearly halves its weighted travel time compared with simulation-only training, bringing it within 8.3 points of the production navigation stack, fully onboard; with an integrated global planner, it also reaches far, occluded goals in every trial.

Related papers

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First public release: 2026-10-20 · Indexed by Pub-AI: 2026-10-21 UTC

preprint

Physical AI for Intralogistics: Benchmarking the NVIDIA Sim-to-Real Ecosystem for Cosmos-Enhanced COMPASS Navigation on Industrial Mobile Robots

Charbel Abi Hana, Rayan Zaitouni, Kameel Amareen, Mohamad Mostafa, Hasan Sayour, Wei Liu, Yan Chang, Mihir Acharya, Anthony Rizk

Preprint posted: 2026-10-20 · Original record ↗

arxiv
2610.28432
Explicit source versions (1)
  • v2 · 2026-10-21
  1. Preprint available

    Source date: 2026-10-20 · First detected: 2026-10-25 UTC · Historical baseline

    Source evidence (1)
  2. Explicit source version detected · v2

    Source date: 2026-10-21 · First detected: 2026-10-25 UTC · Historical baseline

    Source evidence (1)
Abstract · arxiv

Classical robot navigation stacks are reliable but often require re-engineering for each new robot type and site. Learning-based navigation shifts this effort from hand-tuned parameters to data generation and training, where a policy adapts to each new embodiment or facility by fine-tuning in simulation. Whether policies adapted this way stay reliable on real industrial robots has seen little systematic testing. We study this for NVIDIA's X-Mobility and COMPASS workflow for training learned navigation policies on Idealworks robots. In simulation, we extend the COMPASS benchmark with two embodiments, the differential-drive iw$\mkern-1.5mu.\mkern-1.5mu$hub and an omnidirectional Humanoid Mobile Platform (HMP), and with a digital twin of the Idealworks R&D center. For the real world, we fine-tune X-Mobility on data from this digital twin, with and without sim-to-real variants generated by NVIDIA Cosmos, train COMPASS on top of it from scratch in the digital twin, deploy the resulting policies on the iw$\mkern-1.5mu.\mkern-1.5mu$hub's onboard Jetson AGX Xavier, and benchmark them in the Idealworks R&D center against COMPASS trained only on NVIDIA's environments and the existing Idealworks navigation stack on task success, efficiency, safety, smoothness and onboard compute. Running every static scenario both in a digital-twin replica and in the real facility measures the sim-to-real gap and how far Cosmos-augmented data closes it. Training in the digital twin with Cosmos sim-to-real augmentation raises the real-world success rate of learned navigation from 65.3% to 91.7% across four scenarios and nearly halves its weighted travel time compared with simulation-only training, bringing it within 8.3 points of the production navigation stack, fully onboard; with an integrated global planner, it also reaches far, occluded goals in every trial.