Ground Processing Optimization Using Artificial Intelligence Techniques
Status: Completed
Start Date: 2013-05-23
End Date: 2013-11-23
Description: Kennedy Space Center (KSC) has the most complex, enormous, difficult, diverse, distributed, and unique set of integrated scheduling problems in the world and it is only getting more difficult as ground resources need to be shared by different organizations. KSC's scheduling problem is decomposed into many individual but coordinated scheduling problems, each with its own unique set of resources, tasks, constraints, ground rules, and scheduling techniques, resulting in different scheduling processes for each of the individual applications. Stottler Henke's existing Aurora intelligent planning and scheduling system development framework was specifically designed for KSC ground operations scheduling and to be highly adaptable to different domains and has already proven to be adaptable by its successful applications in many dozens of widely varying domains (including multiple KSC scheduling domains). In every domain where a comparison was performed, Aurora always generated more optimal schedules. The proposed vision is to develop one scheduling tool that SMEs in wildly different KSC areas can adapt to create automated scheduling software for different scheduling applications. New capabilities need to be added to address the new KSC realities and to make the adaptation process more SME-friendly. Initially the Intelligent Operations Scheduling System (IOSS) would be fielded in a small number of vehicle and payload processing applications. Later SMEs could adapt IOSS themselves. Eventually, IOSS-based automatic scheduling systems might constitute the majority of schedule decision making at KSC. These separate IOSS scheduling applications could automatically interact, providing automated coordination capabilities. These applications will also be able to interoperate with legacy scheduling systems. Ultimately, by automating, replacing, or interfacing to every scheduling function or system, extreme synergies of coordination and manpower savings would result.
Benefits: The most direct targets for transition of this proposed effort are the large number of various payload and vehicle processing scheduling applications at KSC. By showing its ability to create high-quality schedules with greatly reduced manpower, IOSS will clearly illustrate its advantages over the status quo. Because it will be possible for SMEs to customize the eventual IOSS themselves to their own scheduling applications, a large number of intelligent scheduling applications can be quickly developed. As more are fielded, additional synergies will be created by the cooperative interactions between IOSS-based intelligent scheduling applications and each other. Capabilities to easily interface and interact cooperatively and in a peer-to-peer manner with legacy scheduling systems will also provide additional cooperative synergies. There is a potential to automate the majority of scheduling decision-making at KSC with a corresponding massive savings in highly skilled manpower. An additional, nearby target is the CCAFS, which has nearly identical scheduling problems. Beyond KSC, NASA has a large number of difficult scheduling problems that IOSS could be readily adapted to. Major IOSS successes at KSC will facilitate entry into other NASA markets.
On the commercial side, Stottler Henke already sells Aurora and associated customization services to private companies. Commercial product and service sales related to Aurora have already resulted in over $4 million in revenue. IOSS improvements can be readily incorporated into Aurora and sold through existing sales channels. Most importantly, by providing an SME customization capability, IOSS will be removing one of the most significant current constraints on Aurora sales—the need for Stottler Henke's involvement in 90% of the customization projects. An SME-customizable version of Aurora would be applicable to orders of magnitude more customers. And by requiring far less of our time, it would allow us to sell the product for far less. Current Aurora customers tend to be aerospace manufacturers, partly due to our early conversion of Boeing's 787 Dreamliner production line to being an Aurora customer. Companies like Learjet and Bombardier quickly followed suit as well as some of Boeing's suppliers. Other customers tend to have high-value applications both requiring a high-quality solution and justifying the relatively high price. An IOSS-enhanced version of Aurora would presumably tend to have a similar diverse base of customer but the lower cost should greatly increase the number of potential customers.
On the commercial side, Stottler Henke already sells Aurora and associated customization services to private companies. Commercial product and service sales related to Aurora have already resulted in over $4 million in revenue. IOSS improvements can be readily incorporated into Aurora and sold through existing sales channels. Most importantly, by providing an SME customization capability, IOSS will be removing one of the most significant current constraints on Aurora sales—the need for Stottler Henke's involvement in 90% of the customization projects. An SME-customizable version of Aurora would be applicable to orders of magnitude more customers. And by requiring far less of our time, it would allow us to sell the product for far less. Current Aurora customers tend to be aerospace manufacturers, partly due to our early conversion of Boeing's 787 Dreamliner production line to being an Aurora customer. Companies like Learjet and Bombardier quickly followed suit as well as some of Boeing's suppliers. Other customers tend to have high-value applications both requiring a high-quality solution and justifying the relatively high price. An IOSS-enhanced version of Aurora would presumably tend to have a similar diverse base of customer but the lower cost should greatly increase the number of potential customers.
Lead Organization: Stottler Henke Associates, Inc.