CyberPhysical Software Agents Vincenzo Liberatore V Liberatore Cyberphysical

Cyber-Physical Software Agents Vincenzo Liberatore V. Liberatore Cyberphysical software

Cyberphysical Systems Computing in the physical world l Components l – Sensors, actuators – Controllers – Networks V. Liberatore Cyberphysical software 2

Cyberphysical Systems: Examples l l l l Enables Industrial automation [BL 04] Distributed instrumentation [ACRKNL 03] Unmanned vehicles [LNB 03] Home robotics [NNL 02] Distributed virtual environments [LCCK 05] Power distribution [P 05] Building structure control [SLT 05] V. Liberatore Cyberphysical software 3

Cyberphysical Systems l Merge cyber- and physical- worlds – Networked control and tele-epistemology [G 01] l Sensor networks – Not necessarily wireless or energy constrained – One component of sense-actuator networks V. Liberatore Cyberphysical software 4

Programming Cyberphysical Systems V. Liberatore Cyberphysical software 5

Objectives and Challenges l Objectives – Remote supervision and programming – Adaptive and evolvable – Security and safety l Challenges: decouple control from – Long-haul network delay, losses – Lack of network Quality-of-Service provisioning – Precise environment modeling V. Liberatore Cyberphysical software 6

Vision (1): Agent-based l Basic properties – Autonomous, mobile – Adaptable, flexible, reactive – Knowledgeable, goal-oriented, learning – Collaborative – Persistent l Agents for cyber-physical systems – Aggregation into task-oriented teams – Evolvable l V. Liberatore Re-programmability, reconfiguration, extensibility Cyberphysical software 7

Vision (2): Supervision l Coarse-grained high-level – Directions – Troubleshooting – Reprogramming Autonomous systems Tele-operation Supervision V. Liberatore Cyberphysical software 8

Advantages of Supervisory Control l Utilize autonomous capabilities of robot – Less work for the Supervisor l Makes control with delay feasible – Higher Level commands translated into many smaller ones l Still V. Liberatore the same safe robots Cyberphysical software 9

Achieving Generic Control l Want the same program to powerfully represent unknown, high level commands – Completely generic GUI – Adapts to commands and attributes of robot l Utilizes a small code stub on the robot – Uses modern day windows controls l Works on robots that communicate IP, regardless of OS and programming V. Liberatore Cyberphysical software 10

This talk l Progress – Agent-oriented platform l Agent-Communication l Dynamically load functionality l Mobility l Virtual containment l Resource Discovery l Experience l Future work – Application-oriented middleware l E. g. , Scheduling of mobility – AI (knowledge, planning, learning) – Security V. Liberatore Cyberphysical software 12

Agent Communication l Supervisor invokes robotic functionality – Passes parameters using dynamic GUI l Robot communicates with Supervisor – Returns values for display – Notifies supervisor of properties – Able to ask supervisor for assistance l V. Liberatore Priority may cause emergency handling Cyberphysical software 13

Dynamically Load Functionality l Currently, robot must be fully represented l Supervisor interacts with Virtual Robot – Middleman we can inject code into – Interfaces provide access to robotic attributes l Ability to add new behavior that uses existent functionality and properties – Added to proxy means that they appear as robotic functionality to supervisor V. Liberatore Cyberphysical software 14

Dynamically Load Functionality Believes that the robot it is Supervisorimplements GUI controlling both foo() and bar() function Reports foo() loaded that calls upstream foo() Exposes a function foo() V. Liberatore Cyberphysical software 15

Dynamically Load Functionality l Powerful ability to “reprogram” robot – Doesn’t require actual robotic modification – Send across canned functionality – Reprogram to deal with unknown environment l May wrap up functionality again and again, abstracting away the lower layers l Applies to multiple-robot scenarios – Dynamically reorganize groups of robots V. Liberatore Cyberphysical software 16

Dynamically Load Functionality Invokes a bar() command Invokes foo() Invokes more_foo() Invokes yet_foo_again() twice Executes yet_foo_again() twice V. Liberatore Cyberphysical software 17

Resource Discovery l Plug-and-play – Add new resources on the fly – Example: USB l l l Plug in a USB camera on a USB port But now we want: on a network, with arbitrary units Example – Locate a robot on the network V. Liberatore Cyberphysical software 19

Jini l Operations – Discover, Join, Look-up, Use l Programming – Include a library – Use functions l Fault-tolerance – Leases l Join only last for a certain time period l Renew the lease – Multiple look-up servers – Java. Spaces l Distributed shared memory l Courtesy of Sun Microsystems URL: www. jini. org V. Liberatore Cyberphysical software 20

Middleware l Between application and transport – Libraries to provide advanced functionality – Hide communication l Applications – – – l Resource Discovery Remote Procedure Calls Security Interoperability (e. g. , since Real-Time Corba) Scheduling, resource management, performance analysis Multicast Software development – Simpler, faster – State-of-the-art functionality l Middleware over IP – Wealth of libraries for IP – Critical advantage of the Internet Protocol V. Liberatore Cyberphysical software 21

Agent Mobility l Mobility – Software component stops execution on host A – Resume execution from same state on host B l Benefits – Adapt to changes of physical topology l E. g. , if a unit moves and triggers functionality hand-off – Anticipate planned disconnections – Dynamic re-programmability by agent dispatching V. Liberatore Cyberphysical software 22

Agent teams Virtual Robots: The Core GUI, interface Thin-legacy layer On-board controllers V. Liberatore Cyberphysical software 26

Hierarchical organization Relationship: Virtual inclusion Chain of command V. Liberatore Cyberphysical software 27

Virtual Containment l Analogy – A robotic platoon “contains” individual robot – Not necessarily in terms of ontology l Application – Task-oriented teams – Layering V. Liberatore Cyberphysical software 28

Upstream Communication l Report state upstream – Sensory data collection l Appeals for assistance – Minimal demands of directions from human or intelligent systems High-level directions l Triggered only by difficult or unexpected events l – Improves safety and reliability V. Liberatore Cyberphysical software 29

Hierarchical organization Relationship: Virtual inclusion Upstream communication V. Liberatore Cyberphysical software 30

Experience Parameter (range) Robot id Go!!! Methods V. Liberatore Cyberphysical software Task-space: Fluid dynamics 31

Demo l Objective – Close lever l Operations – Remote command – Robotic manipulator l Procedure – Break complex Close lever command (Close. Lever) into progressively simpler instructions multiple invocations of Move. To(x, y, z) multiple invocations of Go. To(x, y, z) V. Liberatore Cyberphysical software 32

Example Open/Close Agent-based software Move. To RPCS Virtual Supervisor V. Liberatore Cyberphysical software 33

Other topics l Security – Encrypt communication – Authentication and Authorization – Standard Java libraires l Fault-tolerance – Look-up with soft-state – Checkpoint in Java. Spaces l Advanced functionality with little incremental cost – Demonstrate importance of software re-use with state-of-the-art middleware V. Liberatore Cyberphysical software 34

Related Research V. Liberatore Cyberphysical software 35

Play-Back Buffers l Playback – Smooths out network non-determinism l Playback buffers integrated with – Sampling (adaptive T) – Control (expiration times, performance metrics) l Packet losses – Reverts to open loop plant (contingency control) V. Liberatore Cyberphysical software 36

Bandwidth Allocation l Definition – Multiple sense-and-respond flows – Contention for network bandwidth l Desiderata – Stability and performance of control systems l Must account for physics – Efficiency and fairness – Fully distributed, asynchronous, and scalable – Dynamic and selfreconfigurable V. Liberatore Cyberphysical software 37

Problem Formulation l Define a utility fn U(r) that is – Monotonically increasing – Strictly concave – Defined for r ≥ rmin l Optimization V. Liberatore formulation Cyberphysical software 38

Conclusions Remote supervision of robotic manipulation l Compliant control l – Local encapsulation – Gentle, compliant, tolerant to network vagaries l Agent-based software – Hierarchical Demonstration l Future work: middleware, AI, security l V. Liberatore Cyberphysical software 39

To Learn More http: //home. case. edu/~vxl 11/Net. Bots/ vl@case. edu V. Liberatore Cyberphysical software 40