
Astribot is a robotics company developing humanoid robots that combine artificial intelligence with physical manipulation and movement. Its technology is focused on embodied intelligence, where AI systems perceive their surroundings, reason about tasks, and execute actions through a physical robot. The company develops both robotic hardware and software infrastructure, including tools for AI deployment, simulation, data collection, and robot development. Its work places Astribot within the emerging field of general-purpose and humanoid robotics.
Astribot develops humanoid robotic systems designed to perform physical tasks and provide a platform for embodied AI development. Its S1 robot is designed for scientific research and supports developers working on robotics algorithms, AI models, simulation, and physical manipulation. Astribot also provides tools for collecting robot data and training AI systems, including VR teleoperation for generating physical interaction data. The company works with AI companies, universities, research institutes, data centers, and industry partners exploring applications for embodied intelligence.
Astribot’s technology combines robotic hardware with AI software through what the company calls a Design for AI (DFAI) software-hardware integrated architecture. The approach closely connects AI capabilities with robotic manipulation and physical action.
The company’s S1 platform uses a humanoid form with bimanual manipulation capabilities and is designed for AI and robotics research. Astribot reports seven degrees of freedom per arm, a 5 kg payload per arm at horizontal reach, positioning repeatability of ±0.1 mm, and 4–6 hours of endurance, with support for plug-in operation.
Astribot also develops an AI development toolchain that includes APIs, development guidance, visual development tools, simulation-platform support, and deployment guidance covering data collection, model training, and deployment. Its VR teleoperation technology is used for collecting robot-interaction data.
The company has also published Lumo-1, a vision-language-action (VLA) embodied foundation model that connects visual perception, language instructions, reasoning, and physical action. The model is trained using robot data collected from Astribot S1 and includes reinforcement learning for improving reasoning-action alignment.
Astribot is relevant to the development of embodied AI because it works across several layers of the robotics stack rather than focusing only on the physical robot. Its work combines humanoid hardware, manipulation, robot data collection, AI models, development tools, and deployment infrastructure.
This approach addresses a central challenge in humanoid robotics: connecting AI reasoning with reliable physical action. Astribot’s S1 platform provides a physical system for collecting robot data and testing AI models, while its toolchain and Lumo-1 research demonstrate the company’s work on the software and learning components required for embodied intelligence.
Astribot S1 is a humanoid robot designed for scientific research, AI development, and exploration of embodied intelligence. The robot combines a human-like physical structure with manipulation capabilities and an AI-oriented software and hardware architecture. Astribot provides developers with APIs, visual development tools, simulation support, deployment guidance, and other tools for developing and validating robotics algorithms and models.
The S1 is also used as a platform for collecting robot trajectories and physical interaction data. Astribot’s Lumo-1 embodied foundation model was trained in part using data collected from S1.
Astribot’s current website also features the T1, an AI robot offered from ¥89,900 CNY on the company’s Chinese-language homepage. The product is presented as an all-in-one AI robot designed for multiple scenarios, expanding Astribot’s product portfolio beyond its S1 research platform.
Lumo-1 is Astribot’s embodied foundation model research platform. It is a vision-language-action model designed to connect visual understanding, language instructions, reasoning, and physical robot actions. The model is intended to generalize across objects, environments, instructions, and tasks, with training that includes robot data and reinforcement learning.
Astribot’s technology is being developed for robotics research, embodied AI development, data collection, industrial automation exploration, and end-user robotic applications. The company specifically describes work with universities, research institutions, AI companies, data centers, and industry partners.
Potential application areas include physical task automation, manipulation research, human-robot interaction, industrial workflows, and AI model training. Astribot also describes its robots as being developed to operate with human tools and equipment and to assist with repetitive, difficult, or dangerous physical tasks.
Astribot S1 is a humanoid robot platform designed for scientific research, AI development, robotics experimentation, and embodied intelligence applications. It provides developers with access to APIs, development tools, simulation support, and AI deployment resources.
Lumo-1 is Astribot’s vision-language-action embodied foundation model. It connects visual information, language instructions, reasoning, and physical robot actions and was trained using data collected from Astribot S1.
Astribot uses robot trajectory data and VR teleoperation technology to collect physical interaction data. Its VR teleoperation solution allows operators to control robots while generating data that can be used for AI and embodied-model development.
Design for AI, or DFAI, is Astribot’s software-hardware integrated architecture that closely connects AI capabilities with robotic manipulation and physical operation. The company describes it as a foundation for enabling robots to learn, reason, and perform physical tasks.
Astribot is addressing both areas. S1 is positioned for scientific research, developers, and AI-model development, while the company also describes industry transformation and end-user applications as areas for collaboration and deployment. Its current website also lists the T1 as an available product.
Have an update, correction, or additional information about this company? Help us keep the futureTEKnow company database up to date by submitting the latest company information.

AI projects often stall because business data isn’t consistent or trustworthy. Here’s how to identify data gaps before they become

X Square Robot has raised $276M from Xiaomi, Sequoia China, and other internet giants to scale its WALL-A embodied AI

EVAS Intelligence has raised 1.5 billion yuan to mass‑produce its RISC-V Epoch AI chips, deepen its full‑stack platform, and accelerate

Orkes has raised 60 million dollars to turn its Netflix‑born workflow engine into a control plane for enterprise AI agents.

Paris-based Sillage has raised €1.7 million to launch an AI signal engine that helps enterprise sales teams follow the right

Cloneable is launching an agentic AI platform for infrastructure operations that captures institutional knowledge from retiring experts and turns it

Algorized is a deep-tech company developing edge-AI models that give machines real-time awareness of people using wireless sensors such as

Reliable Robotics has secured $160M to scale production and deployment of its Reliable Autonomy System. This funding marks a pivotal

Excerpt: Ricursive Superintelligence has raised at least $500 million to build self‑improving AI, with GV and Nvidia backing a four‑month‑old

Brazilian startup BOND has raised US$2M to automate accounting for SMEs in Brazil’s complex tax system. Combining AI with human

Loop just raised a $95M Series C to expand its AI-native supply chain platform, turning messy logistics data into early

Linkedin X-twitter-square Facebook-square Startups & Business News AI agents are finally moving from demos to the day-to-day stack of real
futureTEKnow is focused on identifying and promoting creators, disruptors and innovators, and serving as a vital resource for those interested in the latest advancements in technology.
© 2026 All Rights Reserved.