Connected and Autonomous Technology Evaluation Center (CAVTEC) Overview. TennSMART Spring Meeting April 9 th, 2019

Transcription

1 Connected and Autonomous Technology Evaluation Center (CAVTEC) Overview TennSMART Spring Meeting April 9 th, 2019

2

3

4

5 Location Location Location Tennessee s Portal to Aerospace & Defense Technologies

6 Mach 4 Wind Tunnel one of the largest in academia World Class Facilities for Advanced Graduate Research Mach 3 Wind Tunnel Mach 3 wind tunnel Propulsion Research Facility with Afterburning Jet Engine Space Environments Vacuum Chamber

7 Hypersonics Enabling TN to be the National Epicenter for Hypersonic R&D Dr. John Schmisseur H.H. Arnold Chair AIAA Fellow AFRL Fellow 23 year career with the AFRL

8

9 Credit: NASA/Pat Rawlings, SAIC

10 Integrated Systems and Test Engineering Leveraging Legacy Strengths Risk Management for Complex Industrial Settings Train Flight Test & Research Test & Certify Autonomous Vehicles to Disruptively Shape the Future

11

12

13 The Next Phase

14 SYSTEM SAFETY: The cars must be engineered to respond safely to software malfunctions, near crashes, loss of traction and other risks. Carmakers should get outside validation of their safety systems and prove their cars can operate safely even when technology problems are encountered. CERTIFICATION: Any software updates or new driverless features must be submitted to the N.H.T.S.A. Verification & Validation for AV Safety VALIDATION: Automakers need to develop testing and validation methods that account for the wide range of technologies used in driverless cars. Their tests should include simulation, test track and on-road testing.

15 The Challenge to Testing Autonomous Vehicle Safety Congressional Testimony Importantly, it is not enough to simply propose or develop testing methods. The methods need to be validated rigorously, objectively, and independently both to assess their statistical soundness, relation to existing safety and performance standards, and engineering and social considerations and to build confidence in the methods among diverse stakeholders. Concerted and immediate effort should be made to develop sound and feasible testing methods and to develop those methods into a regulatory framework that balances the need for development and deployment of the technology with appropriate levels of safety at each stage of exposure. Nidhi Kalra Challenges and Approaches to Realizing Autonomous Vehicle Safety CT-463 Testimony submitted to the House Energy and Commerce Committee, Subcommittee on Digital Commerce and Consumer Protection on February 14, 2017.

16 The Challenge to Testing Autonomous Vehicle Safety Congressional Testimony Importantly, it is not enough to simply propose or develop testing methods. The methods need to be validated rigorously, objectively, and independently both to assess their statistical soundness, relation to existing safety and performance standards, and engineering and social considerations and to build confidence in the methods among diverse stakeholders. Concerted and immediate effort should be made to develop sound and feasible testing methods and to develop those methods into a regulatory framework that balances the need for development and deployment of the technology with appropriate levels of safety at each stage of exposure. Nidhi Kalra Challenges and Approaches to Realizing Autonomous Vehicle Safety CT-463 Testimony submitted to the House Energy and Commerce Committee, Subcommittee on Digital Commerce and Consumer Protection on February 14, 2017.

17 The Challenge to Testing Autonomous Vehicle Safety Congressional Testimony Importantly, it is not enough to simply propose or develop testing methods. The methods need to be validated rigorously, objectively, and independently both to assess their statistical soundness, relation to existing safety and performance standards, and engineering and social considerations and to build confidence in the methods among diverse stakeholders. Concerted and immediate effort should be made to develop sound and feasible testing methods and to develop those methods into a regulatory framework that balances the need for development and deployment of the technology with appropriate levels of safety at each stage of exposure. Nidhi Kalra Challenges and Approaches to Realizing Autonomous Vehicle Safety CT-463 Testimony submitted to the House Energy and Commerce Committee, Subcommittee on Digital Commerce and Consumer Protection on February 14, 2017.

18 The Challenge to Testing Autonomous Vehicle Safety Congressional Testimony Importantly, it is not enough to simply propose or develop testing methods. The methods need to be validated rigorously, objectively, and independently both to assess their statistical soundness, relation to existing safety and performance standards, and engineering and social considerations and to build confidence in the methods among diverse stakeholders. Concerted and immediate effort should be made to develop sound and feasible testing methods and to develop those methods into a regulatory framework that balances the need for development and deployment of the technology with appropriate levels of safety at each stage of exposure. Nidhi Kalra Challenges and Approaches to Realizing Autonomous Vehicle Safety CT-463 Testimony submitted to the House Energy and Commerce Committee, Subcommittee on Digital Commerce and Consumer Protection on February 14, 2017.

19 Lessons Learned from Aerospace Systems How do we ensure safe and proper operation of human-rated autonomous vehicles?

20 Aircraft Dynamics 101

21

22 Maybe it is Rocket Science After All Feed-forward Neural Networks are loosely analogous to the human brain, with data moving through layers of nodes V ( ) W x 1 ( ) y 1 x 2 x N1 ( ) N 1 N 3 ( ) N 2 y 2 y N3

23

24 Challenges of Testing Autonomous Systems Traditional methods do not apply to adaptive control or neural networks Certification must be based on new mathematical proofs, rigorous simulation and focused testing & evaluation

25 Environment (e.g. roadways, traffic) Hazards & Anomalies Path Plan + + Effectors (e.g. steering, accelerator) (Mathematical Model) Autonomy & Control Logic Safety Monitor System Sensors (e.g. GPS, LIDAR) _ + Verification & Validation for AV Safety The Science of Autonomy Vehicle Data

26 UTSI's Technology Alignment Aerospace T&E to CAV Learning from the History of Automation in the Aviation Workforce The aviation industry developed technological were doing, yet they remained responsible for taking solutions to help airline pilots manage factors such over when the automated systems reached the limits as high workload, distractions, and abnormal of their operating domains or malfunctioned. Pilots situations. Innovation at that time eventually led to were also encouraged to use automation to the the introduction of autopilot, a cost. It became harder exclusion of manual flight controls, potentially for pilots to understand what the automated systems degrading manual flight skills. UTSI s decades of aerospace sciences expertise safely certifying Human-Rated Systems for NASA/DoD/FAA aligns with US DOT s policy to leverage aerospace lessons learned. 26

27 Objective Develop a Research, Test, and Evaluation Center for safety certification to expeditiously field Connected and Autonomous Vehicle (CAV) Technology. Vehicle To Vehicle V2V Vehicle To IoT V2X On Board Systems V2I Vehicle To Infrastructure

28 Vision: Connecting Science & Systems UTSI/SIRC bring new insight to the automotive research via NASA/DOD/FAA technology agnostic approach. Constrained Systems Test Unconstrained Ops Subsystem Test Lab Reduce Technical Risk Early Research Repeatable Technical Processes Infrastructure foundation in place to build out a TN CAV Tech Center Range Capability in Tennessee

29 UTSI and Surrounding Area Infrastructure Ready for a Tennessee CAV Tech Center

30 C L A S S R O O M S

31 O F F I C E S

32 O P E R AT I O N S C E N T E R

33 D ATA A N D A N A LY S I S C E N T E R

34 Potential CAVTEC HQ G & H Wings G and H Wings provide room for 33 CAVTEC Residents/Clients Dedicated Rooms for Ops Center, Innovation Center, Data & Analyses, IT/SIMS Legend Available Requires repurposing 34

35 C AV W O R K B AY S

36 More than 35 miles of roads and 3,300 acres on UTSI/USAF CAVTEC Range Land 2.2 mi. 36

37 N E A R LY $ 5 5 M I N E X I S T I N G I N F R A S T R U C T U R E + I N T E L L E C T U A L C A P I T A L I N : T R A N S P O R T A T I O N R E S E A R C H & E N G R H U M A N - R A T E D S Y S T E M S T E S T & E V A L A E R O S P A C E A U T O N O M Y D A T A S C I E N C E S C E N T U R I E S O F D E E P S M E P R I C E L E S S

38 Possible CAVTEC Testing UTSI Campus Isolated and Co-mingling with Manned Automobiles 1.8 miles Suburban Streets & Intersections 38

39 Possible CAV Testing of Configurable Rural, Suburban and Urban scenarios Camp Forrest, Arnold AFB Unused roads on either side of Wattendorf Highway Rural, Suburban, Urban Configurable Streets & Intersections ~3,086 acres ~1.5 miles 39

40 Available CAV Maturity Testing in City of Tullahoma Approved via Microcell Network prior to CAV release to Major TN Cities ~8 Microcell Tower Locations 40

41 CAVTEC Growth Potential on UTSI Nominal UTSI Boundary CAVTEC Phased Expansion - Phase 1 CAVTEC Integration & Maintenance Facility (at CAVTEC approval) - Phase 2 CAVTEC Free Play and on-ramp (ASAP with client investment & earnings) Phase 3 CAVTEC Conference Center and potential on-campus test facility growth area Crockett s Cove Cabins

42 Where we are today License Outgrant between Arnold AFB and UTSI for Camp Forrest and UTSI Roads approved 8 March. Edge Computing Environment Research Test setup in process with test planned 24 April UTSI Facility modifications and new construction in planning Camp Forrest Range Prep coordination in work with USAF 42

43 CAVTEC Leading the Nation to Safely Field CAV Technologies