Autonomy - NASA...Autonomy Breakout Summary from NASA Aero-Propulsion Control Technology Roadmap...
Transcript of Autonomy - NASA...Autonomy Breakout Summary from NASA Aero-Propulsion Control Technology Roadmap...
AutonomyBreakout Summary from
NASA Aero-Propulsion Control Technology Roadmap Development Workshop
August 18-19, 2016, Cleveland, Ohio
Jonathan [email protected]
Intelligent Control and Autonomy BranchNASA Glenn Research Center
AutonomyNASA Aero-Propulsion Control Technology Roadmap Development WorkshopAugust 18, 2016
National Aeronautics and Space Administration
www.nasa.gov
Strategic Thrust 6: Assured Autonomy for Aviation Transformation
The objective of Strategic Thrust 6 is to enable autonomous systems that employ highly intelligent machines to maximize the benefits of aviation to society. - NASA Aeronautics Strategic Implementation Plan, 2015
National Aeronautics and Space Administration
www.nasa.gov
Outcomes, Benefits, and Capabilities2015 2025 2035
Out
com
es Introduction of aviation systems withbounded autonomy, capable of
carrying out function-level goals
Introduction of aviation systems with flexible autonomy based on earned
levels of trust, capable of carrying out mission-level goals
Introduction of distributed collaborative aviation systems with
assured autonomy, capable of carrying out policy-level goals
Ben
efits
• Efficiency and NAS capacity• Increased robustness and resilience in
operations• Enhanced vehicle performance• Initial UAS applications benefits
• Increased NASA system flexibility,efficiency and capacity
• Prognostic safety• New vehicles designed to leverage
autonomy• Reduced costs at all levels• Multi-vehicle UAS applications benefits
• Extreme flexibility and adaptability for large-scale systems, with extreme levels of reliability and recovery from disturbances
• Advanced prognostic safety• Further reduced costs at all levels
Cap
abili
ties/
NAS
A O
utpu
ts
• Advanced prescribed automation and initial goal-directed and adaptive automation
• Initial world views from local sensors and limited data exchange
• Applied to aviation system components and small-scale systems.
• Predominantly human-supervised; higher levels of machine independence under carefully controlled conditions
• Mission-level goal-directed adaptive automation
• Large-scale detailed world views using advanced sensors and networks
• Applied to large-scale integrated systems
• Human/machine teams with many levels of control, depending on specific situations; extensive machine-based learning
• Campaign-level goal-directed adaptive automation, embeddedwithin all system elements
• Adaptive collaboration based on extensive shared world views
• Highly distributed large-scale collaborative systems that constitute integral parts of larger systems they support
• Human/machine teams, with humans primarily specifying strategic goals; many systems self-protect and self-heal
National Aeronautics and Space Administration
www.nasa.gov
1A. Develop machine intelligence design methods that are robust to system failures and system integrity threats
3A. Develop methods and guidelines for assigning roles to humans and increasingly autonomous systems in realistic operating conditions
4A. Develop methods to evaluate the viability & impacts (e.g., societal, economic, technological) of increasingly autonomous aerospace vehicles & operations
1B. Develop technologies to support machine sensation, perception, and low-level cognition
1E. Develop technologies to support machine reasoning and decision making
1H. Develop technologies to support collaboration between autonomous systems
1F. Develop design methods for adaptive/non-deterministic machine intelligence
1C. Develop machine intelligence design methods for unforeseen events in complex environments
1G. Develop technologies for self-healing systems
2A. Develop methods for characterizing the behavior of increasingly autonomous and collaborative systems
2B. Develop methods and standards for assuring trustworthiness of increasingly autonomous systems
2C. Develop certification methods for safe deployment of increasingly autonomous systems
2D. Develop methods and standards for maintaining real-time trustworthiness of increasingly autonomous systems in complex environments
3D. Develop methods and technologies to support teaming between humans and increasingly autonomous systems in normal and non-normal operations
3E. Develop methods to determine which human capabilities remain necessary / add value to the aviation system
3B. Develop framework for introducing increasingly autonomous systems that matches role and authority with earned levels of trust
3C. Develop technologies to enable real-time situation understanding between human operators and increasingly autonomous systems
4E. Identify infrastructure to support flexible, large-scale, cooperative autonomous systems
4H. Select, develop, and implement applications of autonomy that enable adaptive, collaborative aerospace operations on a system-wide scale
4B. Select, develop, and implement applications of autonomy that are compatible with existing systems
4F. Select, develop, and implement applications of autonomy that enable flexible, large-scale aerospace vehicle cooperation
5A. Develop metrics, methods and capabilities to assess feasibility, safety, resilience, robustness, trust, performance, and human interactions with increasingly autonomous systems
2E. Develop methods and standards for maintaining real-time trustworthiness of adaptive/non-deterministic collaborative systems
1D. Develop technologies to support system-state management and optimization
4G. Identify infrastructure to support adaptive, system-wide collaborative autonomous systems
Technologies and Methods for
Design of Complex
Autonomous Systems
Assurance, Verification, and
Validation of Autonomous
Systems
Human-Autonomy Teaming in Complex Aviation Systems
Implementation and Integration of Autonomous Airspace and
Vehicle Systems
Testing and Evaluation of Autonomous
Systems
Strategic Thrust 6 Research ChallengesIntroduction of aviation systems with bounded autonomy, capable of carrying out function-
level goals
Introduction of distributed collaborative aviation systems with assured autonomy, capable of carrying out policy-level goals
Introduction of aviation systems with flexible autonomy based on earned levels of trust, capable of carrying out mission-level goals
2025 20352015
4D. Assess candidate technology development and transition paths for the future of aviation autonomy
5B. Test, evaluate & demonstrate selected small-scale applications of autonomy
5C. Test, evaluate and demonstrate selected flexible, cooperative applications of autonomy to support large-scale operations
5D. Test, evaluate and demonstrate selected adaptive, collaborative applications of autonomy to support system-wide operations
ResearchThemes
4C. Develop framework for co-development of policies, standards, and regulations with development and deployment of increasingly autonomous systems
National Aeronautics and Space Administration
www.nasa.gov
On-Going Work at NASA• Essentially all ARMD autonomy work is related to the
airspace (air traffic management, etc.), not vehicle-related• AAVP and TACP sponsored a vehicle-centric autonomy team
that classified vehicle technologies into three areas: vehicle-only, airspace-related, and either/bothVehicle as an Isolated System
Vehicle by design
• Design for performance• Active (intelligent) control for
lightweight wing structural integrity and wing shaping
• Enable vertical/short takeoff & landing access
• Production• Rapid manufacturing, inspection
• Operation in nominal and off-nominal conditions
• Stability & control; avoid loss of control• Damage, environment (ice, etc…)
• Heath/Maintenance• Self health management• Condition-based maintenance
Vehicle as part of Airspace System
Airspace architecture connection by design
• Flight Operations (within rules)• Guidance • Navigation• Communication• Separation
Overlap – Mutual Interests
Gray Zone
• Flight Management• Trajectory Based Ops, Continuous
Descent Approach, etc.• Avoiding ice-prone, contrail-prone
air, etc.
• Aircraft State of Awareness• Data for self • Data communicated, as system of
systems
• Spacing• Spacing to avoid wake vortex • Formation flight (close proximity
possibly)
National Aeronautics and Space Administration
www.nasa.gov
Report Out from Breakout Session Discussion
National Aeronautics and Space Administration
www.nasa.gov
Break-out Session Participants
• Jonathan Litt NASA• Donald Simon NASA• Gary Hunter NASA• Paul Nelson NASA• Jerry Welch NASA• Milos Ilak United Technologies Research Center• Jerry Ding United Technologies Research Center• Bruce Wood Pratt & Whitney• Laurel Frediani Sporian Microsystems, Inc.• Scott Waun General Electric Aviation
National Aeronautics and Space Administration
www.nasa.gov
Discussion led to following potential areas for NASA to focus on in terms on developing vehicle related technologies for more autonomous operation of air vehicles in the airspace:
• Micro-weather and UAS–propulsion systems are not capable of responding to micro-weather events or downwash from overhead helicopters
• Imposing conditions on propulsion system to handle these situations• Economics of achieving assured autonomy in civilian applications without having to go through military
first• Safety as size increases• Real-time situational awareness
• More sensors to recognize engine state• Information must be unambiguous
• Automate lower level tasks so single pilot can focus on more demanding tasks• Autonomy to allow aircraft to get additional performance• Teamed autonomous systems
• What information is required for situational awareness on the ground• Propulsion Mission Product for NASA ARMD Autonomy Roadmap
• Lots of effort would go to vehicle, with little spent on engine in each relevant mission product. This would allow an engine interface and capability to be used by multiple other mission products
• Coordination between vehicle and propulsion system• Adapting to mission• Data need to be converted into actionable knowledge for the pilot/monitor on the ground• Communication between airframe and engine• Protection against bad information
Specific Topics to Address
National Aeronautics and Space Administration
www.nasa.gov
Broad areas and natural groupings
• Efficiency• Performance • Economics• Adaptability/Resiliency• Safety• Certification
These topics were grouped into broad areas and then further grouped into two Specific technology areas
National Aeronautics and Space Administration
www.nasa.gov
Brief Description:Introduction of autonomous systems provides the opportunity to integrate flight and propulsion control, and to use internal knowledge to optimize operations.
• Engine state awareness• Integrated Flight and Propulsion Control for performance• Adaptation to changing conditions• Standard interfaces for internal communication
Relevance to GoalsAddresses Thrusts 3 and 4. New designs that account for enhanced integration and internal communication, ability to anticipate maneuvers, and control optimized for every situation, will help realize N+3 engine goals beyond what is achievable through engine and vehicle design alone.
Efficiency and Performance/Economics
National Aeronautics and Space Administration
www.nasa.gov
Brief Description: Autonomous systems will introduce new and unique safety challenges that are not being addressed today. Significantly greater overall internal connectedness enables greater capability but adds complexity and opportunity for security breaches.• Engine state awareness• Integrated Flight and Propulsion Control for safety• Adaptation to unforeseen circumstances / Resilience• Data need to be converted to actionable knowledge• Information needs to be unambiguous and secure• No pilot in the loop means machine must perform human functions• New data flow paths and interconnections. What aspects must the certification address?Relevance to Goals:Addresses Thrusts 1 and 5. Resilience to unusual events and guaranteed robust algorithms will maintain safety at least at current levels in a vastly denser airspace.
Safety/Certification