Agile Autonomous Technical Data Package to Path Robotic Task Specification

Here is a draft for a Direct to Phase II SBIR solicitation topic based on the technical capabilities of the data extraction and automated path-planning pipeline. The content has been carefully structured to be precise and concise while protecting all proprietary text.Direct to Phase II Topic DraftTopic ObjectiveObjective: Develop and demonstrate an automated, end-to-end software platform capable of ingesting heterogeneous Technical Data Packages (TDPs)—including 3D CAD models, 2D engineering drawings, Bills of Materials (BOMs), and textual specifications—to autonomously extract engineering intent and generate optimized, collision-free robotic inspection trajectories without manual waypoint programming or hard-coded scripting.The resulting system must bridge the gap between enterprise digital design data and physical automation by converting complex tolerances, geometric constraints, and manufacturing annotations into a standardized data model, simulating the execution in a physics-accurate virtual sandbox, and deploying executable inspection commands directly to physical mobile robotic manipulators. The objective is to drastically compress quality control programming timelines from days to under two hours and enable rapid robotic reconfiguration in highly agile manufacturing environments.Topic DescriptionBackground & Problem Statement: Modern aerospace manufacturing and sustainment pipelines face severe bottlenecks due to legacy quality control (QC) practices. As defense systems shift toward highly modular, rapidly evolving, and low-cost attritable architectures, traditional fixed automation becomes commercially and operationally impractical. Traditional robotic inspection lines require highly specialized programmers to manually teach waypoints, configure physical sensor triggers, and execute tedious trial-and-error collision testing on vendor-specific offline programming utilities. This labor-intensive paradigm introduces severe production delays, as errors or dimensional variations are often caught late in the assembly stream, resulting in compounding downstream costs and extended lead times.While digital enterprise structures routinely house complete engineering intent within comprehensive Technical Data Packages (TDPs)—complete with 3D geometry, Geometric Dimensioning and Tolerancing (GD&T) markers, material specifications, and assembly metadata—translating this multi-format data into actionable instructions remains a manual and error-prone process. To meet the demand for rapid production scaling and point-of-need deployment, the Department of the Air Force requires an intelligent software layer that dynamically parses TDP data and translates it directly into autonomous robotic execution paths.Phase II Expected Outcomes: Proposers responding to this Direct to Phase II topic must demonstrate a mature conceptual foundation, such as completed preliminary software blocks or data-parsing prototypes originally validated under related early-stage research. Phase II efforts must deliver a hardened, end-to-end software prototype validated against representative aerospace assembly geometries.Key technical deliverables include the ingestion/planning software, documentation for enterprise data interfaces, and localized simulation proof-of-concepts. The system performance will be benchmarked against key parameters, targeting a setup time reduction to under 8 hours for novel manufacturing configurations and compressing numerical programming timelines down to less than 1.5 hours. Final validation should culminate in a software-driven execution demo using either high-fidelity simulations or physical manufacturing hardware within a pilot production framework.

Objective

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 3.5 of the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

Develop and demonstrate an automated, end-to-end software platform capable of ingesting heterogeneous Technical Data Packages (TDPs)—including 3D CAD models, 2D engineering drawings, Bills of Materials (BOMs), and textual specifications—to autonomously extract engineering intent and generate optimized, collision-free robotic inspection trajectories without manual waypoint programming or hard-coded scripting.The resulting system must bridge the gap between enterprise digital design data and physical automation by converting complex tolerances, geometric constraints, and manufacturing annotations into a standardized data model, simulating the execution virtually, and deploying executable inspection commands directly to physical mobile robotic manipulators. (Design and fabrication of the physical manipulator is not within scope - this project will focus on translating TDPs to robot-ingestible task specification and pathing.) The objective is to drastically compress quality control programming timelines from days to under two hours and enable rapid robotic reconfiguration in highly agile manufacturing environments.

Phase I

As this is a Direct-to-Phase-II (D2P2) topic, no Phase I awards will be made as a result of this topic. To qualify for this D2P2 topic, Offerors must demonstrate completion of Phase I feasibility research and development that is not based upon or logically extend from any prior or ongoing federally funded SBIR or STTR work. Applicant(s) should provide documentation demonstrating a clear understanding of the technical challenges associated with processing enterprise data, extracting design intent, and validating automated path execution.

The purpose of this Feasibility Documentation is to substantiate that the small business's technology is currently at an acceptable maturity level to immediately execute the prototype development, testing, and system integration required in Phase II.

Required Substantiation Components

Offerors must submit a structured technical package within the proposal (typically matching the Department of Defense Volume 2 Technical Guidance) that clearly defines the current technological baseline. Offerors must explicitly demonstrate that they possess the intellectual property rights or native ownership of the algorithmic baselines being brought forward. This foundational proof cannot be purely conceptual or marketing-driven; it must contain raw technical and analytical validation.

To satisfy the specific constraints of an automated enterprise-data-to-robotic-execution pipeline, the documentation must provide evidence across three core domains:

Ingestion & Semantic Interpretation Capability: Documentation showing the mature capability of existing code blocks or analytical tools to ingest engineering files (such as 3D CAD models, STEP files, or legacy 2D PDFs) and systematically isolate geometric structures, dimensional annotations, and textual production notes. Standardized Data Architecture: Evidence of a functional relational schema, database template, or centralized data graph structure utilized by the software to catalog and bind extracted dimensions directly to spatial CAD nodes. Kinematic & Simulation Mechanics: Proof that the small business has successfully compiled algorithms capable of reading logical manufacturing sequences and converting them into multi-axis spatial motions or automated path-planning trajectories within a virtual modeling sandbox.

Acceptable Forms of Evidence

The Air Force will evaluate the proposal based on empirical data rather than speculative milestones. Offerors should supply a combination of the following documentation types to conclusively prove feasibility:

Technical Reports and White Papers: Comprehensive white papers detailing the results, architectural limitations, and developmental conclusions of previous internally funded research or non-SBIR commercial software deployments. These reports must highlight how previous iterations successfully managed multi-format document exceptions. Empirical Test and Measurement Data: Quantitative performance charts indicating the precision and accuracy of the software's semantic parsing or extraction engines. This includes specific metrics on Optical Character Recognition (OCR) error rates, geometric normalization latency, or vector parsing precision. Prototype Design Schematics and Software Architecture Models: Logic flow charts, structural class diagrams, API data contract definitions, and interface maps illustrating how data progresses from raw enterprise packages into a centralized repository, and ultimately into automated motion commands. Simulation Benchmarks and Run-Time Measurements: Time-study records, compute logs, or comparative tables tracking the computational time required to automatically generate path trajectories relative to manual offline programming configurations. This data should ideally record baseline path-generation cycle times to validate the scaling potential of the optimization engine. Defined Prototype Success Criteria: Clear operational boundaries, algorithmic tolerances, and pass/fail thresholds under which previous internal iterations achieved successful outcomes. Offerors must list the specific file sizes, component geometric complexities, and degree of nesting variations that their software baseline has successfully parsed without human intervention.

Failure to provide rigorous, quantitative proof of a functioning software baseline that bridges data ingestion with basic path computation will result in a determination of technical non-conformance, rendering the proposal ineligible for a Direct-to-Phase-II award.

Phase II

Phase II Expected Outcomes and Technical Framework The Phase II effort represents a major research, development, and engineering push aimed at transitioning the foundational software baseline into a hardened, production-ready enterprise platform. The overarching objective is to eliminate the manual overhead, human parsing errors, and rigid programming loops that bottleneck modern aerospace manufacturing lines. By the conclusion of the Period of Performance, the recipient must deliver a mature, well-defined software ecosystem capable of directly translating raw engineering intent into optimized, collision-free multi-axis robotic paths. The final system must demonstrate operational viability and full structural traceability back to the originating digital assets.Operating Parameters & Use Cases The software suite must maintain operational viability across highly dynamic industrial settings. Phase II development must satisfy the following baseline parameters and specific deployment use cases: Ingestion of Heterogeneous Artifacts: The ingestion system must process and map multi-vendor file formats natively without relying on manual pre-formatting or external template modifications. This includes parsing geometric data types (e.g., STEP, IGES) alongside flat text and visual annotations (e.g., drawings, PDF specification sheets, text-based process blocks).Use Case 1: Rapid Line Reconfiguration: The primary manufacturing usecase is the rapid setup of robotic tasks for modular or short-run components, specifically targeting complex structure profiles typical of autonomous collaborative platforms (ACPs) or unmanned aircraft structures. Use Case 2: Multi-Vendor Kinematic Adaptation: The trajectory engine must adapt logical tasks to varied multi-axis robotic hardware platforms (e.g., varied serial arms paired with mobile transport carts or tracked bases). The software must abstract the path calculations from specific OEM programming semantics, allowing uniform execution across distinct vendor controllers. Technical Goals & Functional Requirements The software platform must be architected as a modular, cohesive system organized across clear functional layers: Engineering Intent Processing and Graphing: The system must isolate complex design specifications—such as Geometric Dimensioning and Tolerancing (GD&T) callouts, fastener tolerances, and localized surface processing sequences—from raw documents and compile them into a relational schema or centralized data architecture. This framework must programmatically bind quantitative quality boundaries directly to the respective spatial locations on the 3D target geometry. Autonomous Path & Sequence Generation: Using the compiled structural schema, the planning block must calculate the sequence of activities independently. It must automatically optimize physical tracking angles, sensor stand-off distances, and surface normal orientations without traditional waypoint scripting or manual joystick teaching. No-Code Operator Interface: To support floor personnel who lack advanced programming backgrounds, the platform must include an intuitive, no-code graphical layer. This dashboard must visually highlight the automatically derived inspection points, outline the planned tool paths, and provide a human-in-the-loop review portal to allow manual modifications or explicit process validation before runtime deployment. The culmination of this project will be a software platform has reached a Technology Readiness Level (TRL) of 6/7, fully capable of driving multi-vendor industrial manipulators directly from enterprise data packages.

Phase III

The contractor will pursue commercialization of the technology, targeting government program offices, commercial industrial base stakeholders. and dual use industrial customers.

Keywords: Autonomous Path PlanningTechnical Data Package (TDP)Automated InspectionEnterprise Data IngestionSemantic Feature ExtractionDigital Manufacturing

Technology areas: Air Platform, Materials, Weapons

Focus areas: Advanced Computing and Software, Advanced Infrastructure & Advanced Manufacturing, Hypersonics, Space Technology, Sustainment & Logistics, Trusted AI and Autonomy

ITAR: Applies

CMMC level: Level 2 (Self)