Factory robot arm in an industrial cell
Manipulation Foundation Model

Factory robots that generalize. Train once, adapt to any part.

RLWRLD's manipulation foundation model reads object geometry at pickup time, so a robot cell handles a new SKU without an engineer re-teaching every grasp.

Robot arm manipulating a precision part in a factory cell
94%
Zero-shot grasp success on novel SKUs
12 min
Average onboarding time per new part
3.2M
Manipulation demonstrations in training corpus
The Problem

Re-teaching a robot cell costs weeks and thousands of dollars

Every new part variant forces a robotics engineer to hand-program new grasp poses, update vision pipelines, and run hundreds of test cycles. That friction caps how fast manufacturers can iterate.

Weeks of downtime per SKU change

Traditional robot programming requires offline teach-in for every geometry variant. A mix of 50 part variants can mean months of integration work per cell.

Brittle pipelines that fail on edge cases

Grasp programs tuned for one part orientation break when parts arrive at a different angle or with cosmetic variation. Catch rate drops and rejects pile up.

Dependency on scarce robotics engineers

Re-teaching requires specialized knowledge that most manufacturers have to outsource. Lead times stretch to months; every iteration adds cost.

The Solution

A foundation model that reads geometry, not programs

RLWRLD captures point-cloud and force-torque data at pickup time, runs it through a transformer backbone pre-trained on 3.2 million manipulation demos, and outputs grasp parameters in real time.

Abstract visualization of the RLWRLD model architecture pipeline
View full architecture
Capabilities

Designed for industrial-grade manipulation

Geometry-agnostic grasping

The model infers grasp candidates directly from point-cloud geometry. No CAD file required. No prior training on that specific part.

Sub-100ms inference

Runs on embedded GPU at the cell edge. Latency under 80ms end-to-end from sensor input to joint command, compatible with standard PLC cycle times.

Force-torque feedback loop

Closes the manipulation loop with real-time force-torque sensing. Detects slip and replan mid-grasp, recovering failed picks without operator intervention.

Multi-robot controller API

REST and SDK interfaces for FANUC, KUKA, and ABB arms. Drop-in middleware layer; your existing PLC and MES integrations keep working.

Continuous learning from production data

Every production pick is a training signal. The model fine-tunes on cell-specific data, improving catch rates over weeks of operation without engineer input.

On-premise deployment option

Inference runs fully on-site. No part geometry, sensor data, or proprietary process information leaves the factory floor. ISO 27001 aligned deployment procedures.

Early Adopters

Running in precision manufacturing cells today

Selected pilot partners are deploying RLWRLD across high-mix, low-volume assembly lines where frequent SKU changes make traditional programming economically unviable.

Hiramoto Precision Components
Automotive Components, Aichi JP

Introduced 12 new part profiles over 6 weeks without reprogramming the pick cell. Zero offline teach-in sessions during that period.

Kassel Automation GmbH
Industrial Machinery, Stuttgart DE

SKU changeover time on a packing line trial reduced from 3 days to under 4 hours. Zero-shot grasp performance on cast aluminum parts from a supplier they had never processed before.

Solano Fab
Precision Fabrication, Monterey CA

94% pick success on metal stampings of varying thickness at first deployment, with no prior part-specific training. The model read their depth sensor data and generalized from geometry alone.

Research

Founded on peer-reviewed robotics science

Our team publishes at top robotics venues. The manipulation model is built on documented methods, not black-box engineering.

CoRL 2025
2025
Generalizing Robot Grasps Across Object Geometries via Point-Cloud Transformers
J. Ryu, S. Miyamoto, E. Vasquez

We introduce a point-cloud transformer architecture pre-trained on 3.2M manipulation demonstrations that achieves 94% zero-shot grasp success on never-seen industrial parts.

ICRA 2025
2025
Force-Torque Feedback Integration in Manipulation Foundation Models
E. Vasquez, J. Ryu

We show that closing the manipulation loop with force-torque feedback reduces mid-grasp slip by 61% compared to vision-only baselines on metallic parts under industrial lighting variation.

View all publications
Early Access Program

Ready to eliminate re-teaching from your production line?

We are onboarding a limited number of manufacturing partners for the 2026 early access program. Applications are reviewed by our engineering team.