Cortex 2.0: Grounding World Models in Real-World Industrial Deployment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Aida, Adriana, Amer, Walid, Bankovic, Katarina, Behl, Dhruv, Busch, Fabian, Bhalla, Annie, Duong, Minh, Gienger, Florian, Godse, Rohan, Grachev, Denis, Gulde, Ralf, Hagensieker, Elisa, Hu, Junpeng, Joshi, Shivam, Knobloch, Tobias, Kumar, Likith, LaRocque, Damien, Lokesh, Keerthana, Moured, Omar, Nguyen, Khiem, Preyss, Christian, Sriganesan, Ranjith, Singh, Vikram, Sponner, Carsten, Tong, Anh, Tuscher, Dominik, Tuscher, Marc, Upputuri, Pavan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911618221211648
author Aida, Adriana
Amer, Walid
Bankovic, Katarina
Behl, Dhruv
Busch, Fabian
Bhalla, Annie
Duong, Minh
Gienger, Florian
Godse, Rohan
Grachev, Denis
Gulde, Ralf
Hagensieker, Elisa
Hu, Junpeng
Joshi, Shivam
Knobloch, Tobias
Kumar, Likith
LaRocque, Damien
Lokesh, Keerthana
Moured, Omar
Nguyen, Khiem
Preyss, Christian
Sriganesan, Ranjith
Singh, Vikram
Sponner, Carsten
Tong, Anh
Tuscher, Dominik
Tuscher, Marc
Upputuri, Pavan
author_facet Aida, Adriana
Amer, Walid
Bankovic, Katarina
Behl, Dhruv
Busch, Fabian
Bhalla, Annie
Duong, Minh
Gienger, Florian
Godse, Rohan
Grachev, Denis
Gulde, Ralf
Hagensieker, Elisa
Hu, Junpeng
Joshi, Shivam
Knobloch, Tobias
Kumar, Likith
LaRocque, Damien
Lokesh, Keerthana
Moured, Omar
Nguyen, Khiem
Preyss, Christian
Sriganesan, Ranjith
Singh, Vikram
Sponner, Carsten
Tong, Anh
Tuscher, Dominik
Tuscher, Marc
Upputuri, Pavan
contents Industrial robotic manipulation demands reliable long-horizon execution across embodiments, tasks, and changing object distributions. While Vision-Language-Action models have demonstrated strong generalization, they remain fundamentally reactive. By optimizing the next action given the current observation without evaluating potential futures, they are brittle to the compounding failure modes of long-horizon tasks. Cortex 2.0 shifts from reactive control to plan-and-act by generating candidate future trajectories in visual latent space, scoring them for expected success and efficiency, then committing only to the highest-scoring candidate. We evaluate Cortex 2.0 on a single-arm and dual-arm manipulation platform across four tasks of increasing complexity: pick and place, item and trash sorting, screw sorting, and shoebox unpacking. Cortex 2.0 consistently outperforms state-of-the-art Vision-Language-Action baselines, achieving the best results across all tasks. The system remains reliable in unstructured environments characterized by heavy clutter, frequent occlusions, and contact-rich manipulation, where reactive policies fail. These results demonstrate that world-model-based planning can operate reliably in complex industrial environments.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20246
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cortex 2.0: Grounding World Models in Real-World Industrial Deployment
Aida, Adriana
Amer, Walid
Bankovic, Katarina
Behl, Dhruv
Busch, Fabian
Bhalla, Annie
Duong, Minh
Gienger, Florian
Godse, Rohan
Grachev, Denis
Gulde, Ralf
Hagensieker, Elisa
Hu, Junpeng
Joshi, Shivam
Knobloch, Tobias
Kumar, Likith
LaRocque, Damien
Lokesh, Keerthana
Moured, Omar
Nguyen, Khiem
Preyss, Christian
Sriganesan, Ranjith
Singh, Vikram
Sponner, Carsten
Tong, Anh
Tuscher, Dominik
Tuscher, Marc
Upputuri, Pavan
Robotics
Artificial Intelligence
I.2.9; I.2.6; I.2.10
Industrial robotic manipulation demands reliable long-horizon execution across embodiments, tasks, and changing object distributions. While Vision-Language-Action models have demonstrated strong generalization, they remain fundamentally reactive. By optimizing the next action given the current observation without evaluating potential futures, they are brittle to the compounding failure modes of long-horizon tasks. Cortex 2.0 shifts from reactive control to plan-and-act by generating candidate future trajectories in visual latent space, scoring them for expected success and efficiency, then committing only to the highest-scoring candidate. We evaluate Cortex 2.0 on a single-arm and dual-arm manipulation platform across four tasks of increasing complexity: pick and place, item and trash sorting, screw sorting, and shoebox unpacking. Cortex 2.0 consistently outperforms state-of-the-art Vision-Language-Action baselines, achieving the best results across all tasks. The system remains reliable in unstructured environments characterized by heavy clutter, frequent occlusions, and contact-rich manipulation, where reactive policies fail. These results demonstrate that world-model-based planning can operate reliably in complex industrial environments.
title Cortex 2.0: Grounding World Models in Real-World Industrial Deployment
topic Robotics
Artificial Intelligence
I.2.9; I.2.6; I.2.10
url https://arxiv.org/abs/2604.20246