SBIR-STTR Award

GreenSight (GS) proposes Modular Autonomous Capability for Landing on Uncooperative Vehicles (MACLUV), a modular system for enabling a wide range of VTOL unmanned aircraft to land and takeoff autonomously from moving non cooperative targets. GS, GSs PI and consultants have industry leading experience across multiple decades developing various autonomous landing, recovery and takeoff systems for both cooperative and uncooperative landing scenarios on USVs, wires, ground vehicles, docking stations and drone charging hives. GSs MACLUV approach uses a combination of reinforcement learning coupled with stereo vision and 3D reconstruction to reliably and precisely plan and execute a landing trajectory to a user specified landing location on the non cooperative target. GS has both the software experience to execute this project as well as commercialized hardware systems to build a low SWaPC system that can be easily integrated with existing and future VTOL SUAS which require this capability.

Benefit:
The proposed MACLUV system fills a large unfilled niche for a variety of commercial and military applications. There currently does not exist a commercial product in any form able to fill the required specifications. We see extensive tactical and commercial CONOPs involving a wide variety of offensive, logistics, surveillance, rescue and onboard service missions well beyond the Navys initial interest and missions. We intend to pursue commercialization, leveraging our existing hardware and payload systems as building blocks, offering MACLUV as a hardware module for inclusion both on GSs own VTOL SUAS as well as for existing and in-development third party SUAS. By expanding the use cases for unmanned aircraft for what are often very dangerous missions (even for commercial ones), our system will increase safety by removing pilots from harms way, and allow for critical supplies to be delivered in higher risk conditions that would be considered too dangerous for a manned mission. We anticipate a very large commercial market for this technology, to be quantified in detail during Phase II.

Keywords:
Sensors, Sensors, Artificial Intelligence/Machine Learning, Autonomous Landing, surveillance, Non-cooperative, Unmanned Systems, AI/ML

GreenSight (GS) proposes Modular Autonomous Capability for Landing on Uncooperative Vehicles (MACLUV), a modular system enabling a wide range of VTOL unmanned aircraft to land and take off autonomously from moving non-cooperative targets. GS has industry-leading experience across multiple decades developing various autonomous landing, recovery, and takeoff systems for both cooperative and uncooperative landing scenarios on USVs, wires, ground vehicles, docking stations, and drone charging hives. GSs MACLUV approach uses a combination of reinforcement learning coupled with stereo vision and 3D reconstruction to reliably and precisely plan and execute a landing trajectory to a user-specified landing location on the non-cooperative target. GS has both the software experience to execute this project and commercialized hardware systems to build a low SWaPC system that can be easily integrated with existing and future VTOL SUAS that require this capability.

Benefit:
The proposed MACLUV system fills a sizeable niche for a variety of commercial and military applications. A commercial product in any form currently does not exist that can fulfill the required specifications. We see extensive tactical and commercial CONOPs involving a wide variety of offensive, logistics, surveillance, rescue, and onboard service missions well beyond the Navys initial interest and missions. We intend to pursue commercialization, leveraging our existing hardware and payload systems as building blocks, offering MACLUV as a hardware module for inclusion on GSs own VTOL SUAS and existing and in-development third-party SUAS. By expanding the use cases for unmanned aircraft for what are often very dangerous missions (even for commercial ones), our system will increase safety by removing pilots from harms way and allow for critical supplies to be delivered in higher-risk conditions that would be considered too dangerous for a manned mission. We anticipate a very large commercial market for this technology, which will be quantified in detail during Phase II, for transition to Phase III.

Keywords:
Artificial Intelligence/Machine Learning, Sensors, surveillance, Non-cooperative, AI/ML, Autonomous Landing, Unmanned Systems