Adaptive Robotic Systems for Orbital Infrastructure

The construction and maintenance of sustainable orbital and lunar infrastructure including persistent platforms, space stations, space based solar power, space stations, large aperture observatories, and large fuel depots requires flexible, autonomous robotic assembly systems. PickNik Robotics proposes to develop an AI-driven robotic assembly system to revolutionize construction in space. Our solution addresses key limitations in current space-based robotic assembly by leveraging Large Language Models (LLMs) to autonomously generate behavior tree-based task plans from high-level procedural descriptions, removing the need for manual programming. Our system integrates real-time task success verification, allowing robots to self-assess and recover from errors autonomously, reducing reliance on human intervention. With funding from this SBIR Phase I, we will develop and validate our technology using MoveIt Pro, our advanced robotics development platform. We will use our simulation platform to generate training data and simulate orbital assembly conditions. We will train and test LLM-based task planning and verification models, equipping them with anomaly detection and autonomous correction capabilities. By demonstrating feasibility in high-fidelity simulations, we will lay the groundwork for future hardware integration in Phase II. Our target markets include NASA’s In-Space Servicing, Assembly, and Manufacturing (ISAM) and Moon to Mars initiatives, commercial satellite servicing, and future deep-space infrastructure projects. Beyond space, our technology extends to terrestrial automation in advanced construction, manufacturing, and logistics. By enabling intelligent, adaptable, and scalable robotic assembly, we are positioning this innovation to drive down costs, increase efficiency, and make long-term space infrastructure viable.

Our AI-driven robotic assembly system directly supports NASA’s In-Space Servicing, Assembly, and Manufacturing (ISAM) and Moon to Mars initiatives, enabling scalable and autonomous construction of lunar and orbital infrastructure. By integrating Large Language Models (LLMs) for task planning and autonomous verification, our system can transform mission procedures into executable robot instructions, eliminating the need for manual programming and extensive human oversight. Our technology enhances the efficiency and reliability of robotic systems and it reduces mission risk and operational costs by enabling robots to autonomously verify task success and adapt to anomalies. By advancing robotic systems capable of operating in dynamic, unstructured space environments with little to no human supervision we are creating a robotic system that will be critical for many of NASA’s priorities like the assembly of persistent orbital platforms, space stations, fuel depots, and space-based observatories. We will eliminate programming bottlenecks for critical tasks like assembling truss structures, joining solar panels, and routing cables to support lunar construction. Additionally, our development will reduce risk for astronauts by enabling robotic extravehicular capabilities. Our AI-driven robotic assembly system has significant commercialization potential across multiple industries that require intelligent automation for complex, high-precision assembly tasks. By leveraging Large Language Models (LLMs) for task planning and verification, our technology can reduce manual programming, increase operational efficiency, and enable autonomous adaptation to dynamic environments. This technology is well-positioned for commercial space station development, satellite servicing, and in-space manufacturing. Companies involved in Commercial LEO Development (CLD), such as Axiom Space, Sierra Space, and Blue Origin, require robotic solutions to assemble and maintain next-generation orbital platforms. Additionally, our self-verifying robotic behaviors align with satellite servicing and debris removal initiatives, providing autonomous repair and assembly capabilities for companies like Northrop Grumman, Astroscale, and Maxar. Beyond space, our system has applications in advanced manufacturing, precision construction, and logistics automation. Industries such as aerospace, automotive, and industrial robotics can benefit from AI-driven robotic planning and execution, reducing reliance on human oversight for complex tasks. This includes: Automated aircraft maintenance and assembly (e.g., Lockheed Martin, Boeing), Construction robotics for modular and 3D-printed buildings, and Industrial automation in oil & gas, mining, and logistics, where autonomous robotic systems improve safety and efficiency in hazardous environments By integrating our AI-powered planning and verification technology into MoveIt Pro, we will provide commercial customers with a scalable, simulation-validated robotic solution. This allows companies to deploy AI-driven automation rapidly, reducing programming costs while ensuring robust, adaptable robotic performance.

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.