Blog

Research, methods, and what we are learning

Technical posts from the RLWRLD team on manipulation, point-cloud learning, and industrial deployment.

Abstract visualization of point cloud grasp geometry generalization
Research

Generalizing Robot Grasps Across Object Geometries

We present our approach to building grasp policies that transfer across object shape families, using point cloud patch tokenization and contrastive representation learning.

Point cloud visualization of industrial parts
Research

Point Cloud Transformers for Unseen Part Manipulation

A deep-dive into our transformer architecture choices for processing depth sensor inputs from novel industrial parts.

FANUC robot arm in an industrial cell
Engineering

Deploying Foundation Models on FANUC Robot Cells

What we learned running our model on FANUC LR Mate hardware for the first time, covering calibration, latency, and picking the right sensor configuration.

Sensor data visualization from force-torque feedback during assembly
Research

Force-Torque Feedback in Foundation Model Assembly Tasks

Integrating force-torque sensor signals into the model's action head to handle compliant placement with fragile or high-tolerance parts.

Grid of industrial parts used in the RMB-2K benchmark
Research

Building the RLWRLD Manipulation Benchmark (RMB-2K)

How we designed a 2,000-mesh evaluation suite covering 20 industrial part categories, and why existing grasping benchmarks do not fit the manufacturing setting.

Comparison of simulated and real robot manipulation environments
Research

Closing the Sim-to-Real Gap for Industrial Manipulation

Industrial settings are visually noisier than tabletop benchmarks. We describe our domain randomization strategy for factory lighting, surface reflectance, and part clutter.

Factory robot cell with workers
Industry

What Re-Teaching a Robot Cell Actually Costs Manufacturers

We interviewed a dozen automation engineers about SKU changeover costs. The numbers were worse than we expected, and mostly invisible in standard productivity metrics.

Japan Robot Association event
Company

RLWRLD Joins Japan Robot Association as Associate Member

We are now an associate member of the Japan Robot Association (JARA), giving us better access to industry standards, testing facilities, and manufacturing partners.

Object-centric scene decomposition for zero-shot pick and place
Research

Object-Centric Representations for Zero-Shot Pick and Place

Breaking the scene into object-centric representations lets us reason about each part independently, a key step toward flexible robot cells that need no part-specific programming.

Training curves for grasp policy across part categories
Research

Training a Unified Grasp Policy Across 20 Object Categories

Training data curation, category balancing, and augmentation strategies for a grasp policy that generalizes from bearings to brackets to connectors.

Language-conditioned manipulation research visualization
Research

Language-Conditioned Manipulation: Where the Latest Research Stands

A survey of recent work on using natural language to specify manipulation tasks, covering what transfers to industrial settings and what does not.

RLWRLD team working in the Tokyo office
Company

We Are Hiring Robotics Engineers in Tokyo

We are looking for Research Engineers, Robotics Software Engineers, and ML Engineers to join us in Bunkyo-ku. Here is what we are building and what the role looks like.