Facts

• Company: Astribot
• Product type: Robotics Software
• Status: available
• Capability focus: Vla / Embodied Reasoning Model
• Website: https://arxiv.org/abs/2512.08580

Profile sections

• Summary
• Overview
• Market context
• Audience
• Workflow
• Capability
• Deployment environment
• Positioning tags
• Specifications
• Tags
• Timeline / Research
• Sources

Summary

Lumo-1 is Astribot vision-language-action model for embodied robot control. It unifies reasoning and action so robots can interpret tasks, understand context and execute manipulation behaviors from multimodal inputs.

Overview

Lumo-1 is Astribot vision-language-action model for embodied robot control. It unifies reasoning and action so robots can interpret tasks, understand context and execute manipulation behaviors from multimodal inputs.

Market context

Generalist VLA model designed to connect embodied reasoning with robot action generation.

• Target environment: Robot-learning labs, Astribot S1 workflows and cross-embodiment research environments.
• Workflow context: Vision-language-action reasoning, planning, trajectory prediction and action training on robot data.
• Customer context: Robot-learning researchers and teams studying embodied reasoning for manipulation.
• Deployment model: Research publication and model-development pathway.
• Commercial maturity: Research-stage model described through a public paper rather than a standalone commercial product.
• Adoption constraints: Adoption depends on model access, hardware compatibility, data quality, latency and real-task reliability.
• Market position: Robot foundation-model layer for reasoning-to-action control.
• Adjacent products: FluxVLA Engine, Gemini Robotics, LeRobot

Audience

Developers

Workflow

Vision-language-action reasoning, planning, trajectory prediction and action training on robot data.

Capability

VLA / embodied reasoning model

Deployment environment

Robot-learning labs, Astribot S1 workflows and cross-embodiment research environments.

Positioning tags

• Audience: Developers
• Workflow: Vision-language-action reasoning, planning, trajectory prediction and action training on robot data.
• Capability: VLA / embodied reasoning model
• Deployment environment: Robot-learning labs, Astribot S1 workflows and cross-embodiment research environments.

Specifications

• Training Pipeline: Continued VLM pre-training, cross-embodiment robot co-training and action training with reasoning process
• Evaluation Mode: Real-world evaluations across challenging robotic tasks
• Tasks Demonstrated: Long-horizon robot tasks responding to natural-language instructions
• Robot Platforms Tested: Astribot S1

Tags

• Peer Group: Robot foundation model
• Workflow: Robot learning data
• Deployment Environment: Research lab
• Commercial Stage: Developer platform

Timeline / Research

• 2025-12-09 - Research Publication - Astribot publishes Lumo-1 research paper on embodied reasoning and robotic control - Astribot researchers published the Lumo-1 paper describing a generalist vision-language-action mod…
• 2025-12-09 - Capability - Astribot introduces Lumo-1 model for embodied reasoning - Astribot introduced Lumo-1 as a generalist vision-language-action model designed to connect robot reasoning with robot action.