1 Integrity  Service  Excellence Autonomy Challenges From an AFRL Perspective 7 August 2014 Kris Kearns AFRL Portfolio Lead for Autonomy Research Human Effectiveness Directorate (711HPW/RH) Air Force Research Laboratory

Flow of Talk What I mean by “Autonomy” Autonomy Problem Space Technical Challenges With brief intro to AFRL technologies AFRL Strategy and Enduring Problem Areas

3 AutomationAutonomy Automation and Autonomy The system functions with no/little human operator involvement; however, the system performance is limited to the specific actions it has been designed to do. Typically these are well-defined tasks that have predetermined responses (i.e., simple rule-based responses. Systems which have a set of intelligence- based capabilities that allow it to respond to situations that were not pre- programmed or anticipated in the design (i.e., decision-based responses). Autonomous systems have a degree of self-government and self-directed behavior (with the human’s proxy for decisions).

4 Autonomous Systems and Technologies Cut Across Domains Cyber – systems handle massive, distributed, and data/information- intensive tasks Aircraft – systems operate in complex environment needing to synchronize space and mission mgmt Weapons – systems that coordinate mission execution Space – once launched systems must operate “on their own” in a harsh environment

5 ―Manpower efficiencies ―Rapid response ―24/7 presence ―Harsh environments ―New mission requirements …….. Across Operational Domains Decentralization, Uncertainly, Complexity…Military Power in the 21 st Century will be defined by our ability to adapt – adaptation is THE underlying foundation of autonomous technology Key AF Challenges Addressed by Autonomy

6 Today’s Unmanned Systems Challenge Unmanned Air Vehicle Leadership Admin & Overhead PilotsSensors Ops MaintMission Coord Processing, Exploitation, Dissemination (PED) Full Motion Video Signal Intelligence Maint Pilots Sensor Ops Maintenance DoD “Unmanned Vehicles” are Unmanned in Name Only...

Getting Beyond the One-to-One Paradigm One Operator for One Ground Control Station One Ground Control Station to One Platform One INT data stream to One “Processing, Exploitation, Dissemination” Cell

8 UAS Autonomy & Teaming UAS Autonomy & Teaming: Key Goals Expand the available action space and decision space Operate in contested and denied environments Increase coordination between assets React faster than the opponents decision cycle Develop and demonstrate the control and autonomy technologies required to enable robust, adaptive, and coordinated combat operations by heterogeneous, mixed teams of air assets Cooperative ISR challenge is to provide ISR as an off-board “service” without the need to directly control the UAS team Future is Tactical Battle Manager (TBM) for multi-vehicle combat operations, supporting team mission execution in contested and denied environments

9 Advanced Interfaces for Multi-UAV Control Developing interface technologies to optimize human performance (increased decision-making, decreased stress, etc) Findings: Performance was significantly improved for 8 of the 12 task types when the timeline display was present. Operators also reported lower perceived cognitive workload with the timeline tool.

10 Balancing Operator Involvement w/ Automation Developing Human-in-the-Loop Testbeds  Objectively and subjectively measure human performance  Physiological (Eye tracking, ECG, voice analysis)  Subjective (Situational Awareness, Trust, Usability)  Mission Performance … to ensure an optimized human-machine team MULTI-UAV TESTBED Findings: Task performance was significantly better when Levels of Automation were similar across tasks, compared to when they differed. ANALYST TESTBED

11 Human State Measurement & Assessment Developing measurement techniques for stress, workload, attention. Correlating human cognitive tasks to performance Long Term vision: Providing the machine data about the human’s state so the machine can aid mission performance Human State Sensing foundational for humans and machines to work as a team

Autonomous System Certification Tomorrow, Decision-Making Systems State-Space Explosion Unpredictable Environments Human-Machine Communication Tomorrow, Decision-Making Systems State-Space Explosion Unpredictable Environments Human-Machine Communication Future, Learning Systems Emergent Behavior Complex, unpredictable Environments Future, Learning Systems Emergent Behavior Complex, unpredictable Environments complexity GAP TODAY: Missing V&V Tools to enable Fielding of Autonomous Systems GAP TODAY: Missing V&V Tools to enable Fielding of Autonomous Systems

13 Trust & Certification Trust & Certification: Key Challenges Insufficient tools to V&V highly complex, software-intensive systems Adaptive/learning systems and uncertain environments yield “near infinite state” systems System composition results in potentially hazardous emergent behavior Engaging a national team of expertise across DoD, NASA, NSF, DoT, etc. to develop new software certification methods, enabling greater degrees of trust in highly complex, software intensive autonomous systems “Design for Certification” asks how: – to supplement test with formal verification – to automate test case generation / reduction (“Non-Statistical DoE for Software”) Formal definition and verification of rqmts & designs to reduce implementation errors and cost in early stages

14 UAS Airspace Integration UAS Airspace Integration: Capability Progression  Sensor, vehicle control algorithms, and pilot interface development and flight test  Common Airborne Sense and Avoid system, scalable to Group 3-5  Terminal Area Operations for safe, efficient ground and terminal operations  Onboard sensors such as radar, EO/IR, TCAS, and ADS-B will enable detection of both cooperative and non-cooperative aircraft, providing protection in all classes of airspace.  The ABSAA system will provide autonomous maneuvering or Pilot-In/On-The-Loop capability as operations dictate.  Key to success is exhibiting pilot-like behavior that allows seamless integration into normal flight operations

Non-Technical Challenges (Culture) “Drones” –Public perception – right or wrong – complicates acceptance AF Pilot History –A pilot has always been in control of the aircraft General hurdle for All New Technologies –Single failure complicates acceptance of follow-on technologies –How to establish CONOPs/uses

16 Ensure safe and effective systems in unanticipated & dynamic environments AFRL Autonomy Vision & Goals Create actively coordinated teams of multiple machines Ensure operations in complex, contested environment AFRL Autonomy Vision Demonstrate highly effective human-machine teaming Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments

17 Ensure safe and effective systems in unanticipated & dynamic environments AFRL Autonomy Human-Machine Teaming Create actively coordinated teams of multiple machines Ensure operations in complex, contested environment Demonstrate highly effective human-machine teaming Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments

18 Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments Ensure safe and effective systems in unanticipated & dynamic environments AFRL Autonomy Human-Machine Teaming Create actively coordinated teams of multiple machines Ensure operations in complex, contested environment Demonstrate highly effective human-machine teaming Enable & Calibrate trust between human and machines Develop common understanding and shared perception between humans and machines Create an environment for flexible and effective decision making Enable & Calibrate trust between human and machines Develop common understanding and shared perception between humans and machines Create an environment for flexible and effective decision making Transparency Communication Training Sensing Interfaces

19

20

21 AFRL Autonomy Coordinated Teams of Machines Ensure operations in complex, contested environment Demonstrate highly effective human-machine teaming Ensure safe and effective systems in unanticipated & dynamic environments Create actively coordinated teams of multiple machines Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments

22 AFRL Autonomy Coordinated Teams of Machines Ensure operations in complex, contested environment Demonstrate highly effective human-machine teaming Ensure safe and effective systems in unanticipated & dynamic environments Create actively coordinated teams of multiple machines Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments Mature machine intelligence Develop and manage fractionated and composable systems Develop reliable, secure, interoperable communication Mature machine intelligence Develop and manage fractionated and composable systems Develop reliable, secure, interoperable communication Communication Perceive Reasoning Training Sense Act Plan

23 AFRL Autonomy Complex & Contested Environments Demonstrate highly effective human-machine teaming Ensure safe and effective systems in unanticipated & dynamic environments Create actively coordinated teams of multiple machines Ensure operations in complex, contested environment Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments

24 AFRL Autonomy Complex & Contested Environments Demonstrate highly effective human-machine teaming Ensure safe and effective systems in unanticipated & dynamic environments Create actively coordinated teams of multiple machines Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments Ensure operations in complex, contested environment Develop technologies that assure robust system and self- protection capabilities Develop technologies that enable situational understanding of the environment Develop technologies that assure robust system and self- protection capabilities Develop technologies that enable situational understanding of the environment Situational Awareness Self Awareness Self Protection Perception Sense

25 AFRL Autonomy Test & Evaluation, Verification & Validation Create actively coordinated teams of multiple machines Ensure operations in complex, contested environment Demonstrate highly effective human-machine teaming Ensure safe and effective systems in unanticipated & dynamic environments Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments

26 AFRL Autonomy Test & Evaluation, Verification & Validation Create actively coordinated teams of multiple machines Ensure operations in complex, contested environment Demonstrate highly effective human-machine teaming Ensure safe and effective systems in unanticipated & dynamic environments Intelligent machines seamlessly integrated with humans - maximizing mission performance in complex and contested environments Provide assurance for machine intelligence and decision-making in complex, uncertain, and dynamic environments Develop methods to ensure reliability of human-machine communication and interaction Develop rigorous and verifiable architecture systems for data centric autonomous systems Develop methodology to V&V fractionated and composable systems Provide assurance for machine intelligence and decision-making in complex, uncertain, and dynamic environments Develop methods to ensure reliability of human-machine communication and interaction Develop rigorous and verifiable architecture systems for data centric autonomous systems Develop methodology to V&V fractionated and composable systems Standards Precedence Structured Traceable Reusable Composable Evidence

27 Questions

28 AFRL Autonomy Team RH –Mike Patzek, RHCI* –Mark Draper, RHCI –Scott Galster, RHCP –Jeff Graley, RHXM RI –Jerry Dussault, RISB –Rick Metzger, RIS* RQ –Bob Smith, RQCC** –Corey Schumacher, RQCA* –Jake Hinchman, RQCC RV –Scott Erwin, RVSV –Paul Zetocha, RVSV* –Khanh Pham, RVSV RW –Rob Murphey, RWW –Will Curtis, RWWN* –TJ Klausutis, RWW –Ric Wehling, RWWI RY –Raj Malhotra, RYAR* OSR –Tristan Nguyen, RTC Autonomy Research conducted at many of the AFRL Technical Directorates

29 Human-Machine Teaming Technology Challenges Inter-relationship

Testing and Verifying Autonomous Systems Key Questions Will It Make The Correct Decision When Encountering Expected, Unexpected Or Unknown Situations? Types of correct decisions? For safety For mission completion For rational behavior How Trustworthy Is The Information, given its current situational awareness? How Do You Prevent Undesired Emergent Behavior, as systems interact? Key Challenges Insufficient tools to V&V highly complex, software-intensive systems Adaptive/learning systems and uncertain environments yield “near infinite state” systems System composition results in potentially hazardous emergent behavior Ensuring autonomous machines are safe and behave as specified