Introduction

2X Robotics

Here at 2X Robotics we are committed to deploying 1B robots.

Here at 2X Robotics we are committed to deploying 1B robots

Where VLAs struggle

  1. Non Markovian tasks
  2. Long horizon tasks
  3. Caching tasks that have already been performed and performing them better the next time.

Our answer

An Operating System layer that adds an helpful abstraction allowing for robots to include modules like Spatial memory, safety, navigation and AI in one click

We are starting with Spatial Memory (RAG) for VLAs and are already seeing a good amount of improvement in long horizon tasks.

Results

Put the three can of soda from the living room inside the trash can in the kitchen.

Watch Video 1

Turn on the radio receiver that's on the table in the living room.

Watch Video 2

Move the two storage containers from the living room to the garage. In the garage, place one container on the floor and stack the other container on top of it (either order is fine)

Watch Video 3

High Quality

Explore the high quality dataset