The U.S. Department of Transportation (U.S. DOT), John A. Volpe National Transportation Systems Center (Volpe Center), Cambridge, MA, is conducting market research to identify Universities and companies within a 25 mile radius of Arlington, VA for research and develop of artificial intelligence applications using open source software to automate vehicle operations, provide secure storage of Government furnished platforms, and has exterior on-site space to conduct research testing.
The dynamic and rapid advancement in, and ad hoc application of, machine learning in vehicle platforms (i.e. cars, trucks, boats, unmanned aerial systems (UAS) requires the U.S. DOT/Volpe Center and other Federal partners to quickly assess usage that individuals may attempt that could present unsafe conditions on roadways, waterways, and airspace. The Volpe Center is researching various platform’s capability and susceptibility to be modified to operate autonomously in an unsafe manner, as well the monitoring the advancement of artificial intelligence/machine learning that can be applied to these platforms.
The Contractor must have the level of expertise in artificial intelligence (AI)/machine learning for object recognition and its application to operate unmanned and autonomous vehicle platforms, particularly Class 1 and Class 2 aerial systems. This effort has three primary tasks, (1) providing work/storage/test space within 25 miles of Arlington VA to allow Government engineers quick access in response to Government questions/investigation involving autonomous aerial systems and cars, (3) providing an exterior on-site facility where autonomous aerial platforms and cars can be safely and securely operated for testing, and (4) developing the ability through the use of open source code of a Contractor design and build racing drone size quadcopter with COTS parts to safely fly autonomously outside avoiding obstacles, locating targets. The contractor facility must be located within 25 miles of Arlington, VA.
The Contractor shall be able to provide space and material in an unclassified equipped laboratory and allow Government engineers access to work with Contractor personnel, researching advancement in object recognition for autonomous vehicles and repair/fabrication of these platforms. The period of performance of this effort is 12 months. The amount of time the Government would need to use the laboratory facility will not exceed 20% over the period of the contract, whereas the storage requirement will be for 100% of the time over the period of the contract. For Government engineers using the laboratory, the Contractor shall provide:
- Up to two work bench areas with standard electronic test equipment (computer/software, power supplies, multimeter, soldering equipment, and similar material) used in the maintenance/repair/building of conventional and autonomous aerial vehicles
• 3D printer capable of producing the type and quantity of parts to replace small components of autonomous vehicles
• Laser milling machine.
The contractor shall be able to design and build a racing drone sized quadcopter using commercial off-the-shelf (COTS) components and open source code, OpenCV and Python preferred. The contractor shall be able to then train the quadcopter using AI/machine learning to fly autonomously around objects and land on a designated targets. The contractor shall provide the software code and designs when completed.
Solicitation Number: 6913G6-19-SN-1001
Deadline for submissions: 17 January 2019
Responsible Agency: Department of Transportation
