SBIR-STTR Award

The Autoloader is a decision support tool designed to allow loadmasters to efficiently create tie-down patterns while also increasing the safety and reliability of the patterns. The tool will be built with Unity3D. There are several benefits to using Unity 3D. This will allow us to take advantage of the 3D rendering to create a display that accurately represents the cargo area of an aircraft, while using color, sizing, and rendered text to provide understandable real-time feedback about the quality of the tie-down pattern. Additionally, Unity3D provides an Augmented Reality framework we can use to allow the loadmaster to add items to the library of cargo types by using a tablets camera and touch screen. Finally, Unity3D supports a wide variety of platforms, allowing us to develop for Android as well as enabling commercialization efforts on other platforms, including IOS and Web Clients. Autoloader uses a mixed-initiative Genetic Algorithm to generate tie-down patterns for a fixed configuration of cargo in a variety of aircraft. The Genetic Algorithm is inspired by neuro-evolutionary research and automated architectural design. The algorithm uses a hierarchical representation of the tie-down pattern. The evolutionary process uses separate cross-over and mutation operations applied to the high-level overall cargo configuration and the low-level pattern used for each individual cargo pattern. Reasonable initial configurations are created to increase the efficiency of the search process. The algorithm will allow the system to develop complete tie-down patterns or use a mixed-initiative approach to work with the loadmaster to complete a partially specified pattern. The system is designed to find a pattern that meets all safety constraints, while minimizing the number of tie-downs used. Additionally, the system will return the safest possible result if no fully valid solution exists.

Benefit:
We envision three paths towards commercializing this product outside of direct contract with the Navy. The first path is a direct commercialization of the project to the air cargo industry. Many of the issues that affect the Navy also affect the major air cargo freight companies. These freight companies ship only cargo and account for over half of cargo shipped via aircraft. Despite environmental and fuel cost concerns, the air cargo industry is expected to exceed $100 Billion in revenue and continue to grow at a rate of 4% for the next 20 years. Given these numbers, this is obviously a profitable industry and a tool that can improve safety and efficiency could be extremely well received. The second source of commercialization is architecture and construction. The algorithm selected for optimizing the tie-down pattern was inspired by evolutionary algorithms used to design buildings by adding or removing structural elements. Given this pedigree, the algorithm could be returned to developing structures. Architecture and construction have been going through a transition to take advantage of digital tools. This transition has led to new tools such as parametric design tools that allow architects to explore whole classes of buildings. This transition has also led to new workflows such as Building Information Modeling (BIM). In this workflow, instead of generating separate terrain, structural, electrical, and plumbing designs, there is a single integrated digital model of a facility representing the physical and functional characteristics of a building. The extensive use of digital models for the standard workflow allows significant opportunities for tools that can perform validation and optimization of designs. AutoDesk is one of the leading sellers of software to support BIM. Autodesk had a revenue in 2019 of $2.57 Billion, a 24.95% increase from the previous year. Much of this increase can be traced to increased subscriptions to Revit, their BIM Software. Revit has an active plugin market. This market and a large user base provide a convenient way to market and deliver a new product with minimal investment and with the potential for significant profit. The final path for commercialization is enhancing existing in-house commercial products. Aurora performs resource scheduling in a variety of domains. Stottler Henke has received $37M in follow on funding from Aurora-related contracts. Much of this work is related to manufacturing and communications. These domains often involve problems optimizing how multiple resources interact. While we have existing heuristics that perform well, the algorithms developed for Autoloader could significantly improve the effectiveness and quality of the solutions provided by Aurora. These improvements could see new development contracts with existing customers as well as the opportunity to attract new clients.

Keywords:
Optimization, Optimization, Genetic Algorithms, Mixed Initiative Planning, Augmented Reality, decision support

Managing cargo loading for U.S. Navy and Marine Corps aircraft is a challenging task, requiring an understanding of elements such as aircraft limitations, aircraft center of gravity, cargo space dimensions, and tie-down procedures to name a few. These elements differ across aircraft and are documented in lengthy Cargo Loading Guides (CLGs). The primary objective of this SBIR topic is to develop apps that run on the Marine Air-Ground Tablet (MAGTAB) and assist aircrew in completing their loadmaster duties, helping to ensure that cargo is stowed efficiently and meets loading requirements specified in the CLGs. We propose to develop AutoLoader, which runs on a MAGTAB and performs calculations and provides feedback for efficient and effective cargo loading. The AutoLoader software has three primary requirements: First, enable the development of a 3D model of cargo placement and tie-down patterns. Second, evaluate the safety of the placement and tie-downs based on the information in the CLGs. Third, generate a complete solution, or finish a partial solution, to a specified cargo loading problem. By meeting these requirements, AutoLoader improves on existing processes by automating calculations, providing actionable feedback, and searching for optimizations to enable more efficient and effective cargo loading.

Benefit:
We envision both transition and commercialization opportunities for AutoLoader. The primary opportunity is direct transition into use by the U.S. Navy and Marine Corps during the Phase II Option. NAVAIR PMA-261 H-53 Heavy Lift Helicopters is the sponsor of this SBIR topic. If the Phase II effort is successful, PMA-261 would lead the effort to transition the AutoLoader software into operational use. Additionally, PMA-275 V-22 Joint Program Office has demonstrated an interest in the results of this SBIR topic. The Phase I work included the CH-53 and V-22 aircraft to engage both program offices. Commercialization opportunities include other branches of the DoD and the air cargo industry. First, both the Air Force and Army have similar aircraft and similar loading problems. To engage with these possible customers, during Phase II we will model and demonstrate two additional platforms in AutoLoader: the C-130 and the CH-47. Second, air cargo freight companies ship only cargo and account for over half of cargo shipped via aircraft. The air cargo industry is expected to exceed $100 billion in revenue and continue to grow at a rate of 4% for the next 20 years. During Phase I, we used criteria around problem similarity and revenue to identify the air cargo companies to focus our commercialization efforts on during Phase II.

Keywords:
Mixed Initiative Planning, 3-D Modeling, Augmented Reality, UNITY, Genetic Algorithms, decision support, Optimization