MPA for the SUO Planning and Decision Aid

MPA for the SUO Planning and Decision Aid David E. Wilkins SRI International Artificial Intelligence Center email: wilkins@ai. sri. com URL: http: //www. ai. sri. com/~wilkins June 1999 SRI International

Long-term Contributions of PDA to the Soldier • Shared plan representations cognizant of miltary principles, doctrine, SOPs and TTPs. Makes possible: • Doctrinally correct plan usable by everyone. • Fast generation of multiple distinct COAs, including ones the commander may not have considered. • Support commander creativity through human guidance. • Uniformly high plan quality, even during high-stress crises. • Continuous analysis of the plan using multiple metrics. • Monitor plan execution and respond quickly to events, helping the commander modify the plan appropriately. • Provide relevant information to other echelons, allowing fast communication while preserving bandwidth SRI International

Multiagent Planning Architecture (MPA) • Agent-based framework (efficiency and modularity) • Enable interoperation of diverse planning technologies – plan generation, scheduling, temporal reasoning, evaluation, . . . • Provide a shared plan representation • Provide organizational structure, control strategies, and communication protocols, wrappers • Develop planning and metaplanning agents specifically for collaborative planning and scheduling • Support dynamic, event-driven reconfiguration of planning organization and strategies at runtime SRI International

MPA Components Planning Cells - organizational units for agents: – Planning Agent (PA), Meta Planning Agent (Meta-PA) – Planning-Cell Managers Shared plan model and representation – based on extenstions to Act formalism Communication Protocols Transport Level: robust, reuse existing technology Content Level: high-level performatives Plan Server - central repository for plans and related information Process Management - extensible set of reactive control policies for implementing problem-solving strategies Support- documentation of each agent’s I/O, Wrappers for individual technologies SRI International

Communication • Messages use KQML-like performatives: – communication performatives – plan performatives • MPA wrappers and libraries for: – message passing – multithreaded processing – tracing and logging of messages • Communication substrates: – KQML (Lockheed-Martin and UMBC) – ILU (Xerox PARC) – OAA (SRI International) SRI International

Examples of MPA messages Requesting solutions from the meta-PCM: (: evaluate : content (: multiple-solve : task “air-superiority” : advice-contexts ((“yuma” (: ingress-at-yuma : deny-air-picture)) (“yuma-sf” (: ingress-at-yuma : ingress-2 -at-san-francisco : breach-at-two-places))))) Retrieving the plan from the plan server: (: ask-all : content (: query-plan : task “air-superiority” : plan “plan-yuma-sf” : view : ascii) SRI International

MPA Plan Server • Central repository for planning information • Hierarchical model of plans (plans, tasks, and action networks) • Answers queries about the plan, providing multiple views • Supports a broad range of plan management capabilities Annotations - declarations of high-level attributes of plans, planning process Product Annotation: pedigree, flaws, plan quality, resource status Process Annotation: time spent on plan components, current status Triggers - rules used to notify cell agents of planning events Example: trigger notifies PCM of overutilized resource annotation, PCM reacts by changing planning strategy SRI International

MPA Applied to ACP • Validate MPA by integrating several systems in DARPA Planning Initiative (TIE 97 -1): INSPECT (ISI) OPIS (CMU) Advisable Planner (SRI) SIPE-2 (SRI) APAT (ISX) ACS (UMass) Process Panel (AIAI -UEdin) VISAGE (MAYA) • Domain is Air Campaign Planning – – – thousands of objects, several thousand nodes in each plan down to support mission level (must allocate supporting resources) air superiority objective only targets grouped into networks which depend on other networks network effectiveness is modeled quantitatively SRI International

TIE 97 -1 Architecture MPA Planning Agents Meta Planning-Cell Manager (PRS) Advisable Planner (SIPE-2) Scheduler (OPIS) Planning-Cell Manager (PRS) Process Monitor APAT GUI Plan Viewer MPA Agent Evaluation Toolkit ACS VISAGE Plan Server Cue: ACT 2 (TEST (ready unit 1)) ACT 1 Cue: Answer query Annotations Triggers Inspect SRI International

TIE 97 -1 Demonstrations DARPA • May 98 - ARPI Workshop, Monterey CA • Feb 98 - DARPA, Arlington VA • Dec 97 - JFACC PMR, San Pedro CA • Nov 97 - ARPI Workshop, San Francisco CA SRI International Increasing Capabilities • Sept 98 - EFX 98, Ft. Walton Beach FL

Inside an MPA Planning Cell PA GUI/Advice Manager (AP and PRS) Create a plan Meta-PA Planning-Cell Manager (PRS) Plan Complete Cue: ACT 2 (TEST (ready unit 1)) Cue: ACT 1 Plan One-Level Create a plan Request: Plan ok? Planning-Cell Designator Plan Complete Plan Server (PRS) or PA Temporal Reasoner (Tachyon) Cue: ACT 2 (TEST (ready unit 1)) ACT 1 Cue: Answer query Request Expand Next Level PA (meta-PA) Critic Manager all (SIPE-2) Cue: ACT 2 (TEST (ready unit 1)) Cue: ACT 1 Resource Critic Annotations Triggers PA Temporal Reasoner (OPIS) PA Scheduler (OPIS) OPIS PA Temporal Constraint Critic (SIPE-2) KQML Agent PA (meta-PA) Search Manager one-level (SIPE-2) PA Schedule Critic (new) Message SRI International SIPE-2

MPA PDA Cell Company Commander Create a plan Cell Manager (CPEF) Plan Complete Cue: ACT 2 (TEST (ready unit 1)) Cue: ACT 1 Plan One-Level Cell Designator New Op Order Request: Modify plan Plan Server (PRS) Platoon A PDA Higher Echelon: Cue: ACT 2 (TEST (ready unit 1)) Planner (SIPE-2, O-Plan) ACT 1 Cue: Answer query Cue: ACT 2 (TEST (ready unit 1)) Cue: ACT 1 Resource Critic Annotations Triggers Platoon B PDA Platoon C PDA Terrain Reasoner Fire Control Planner (e. g. ) KQML Agent At WTA Message SRI International

Multiple PDA Cell Configuration Plan Higher Echelon Cell Manager (CPEF) Cue: ACT 2 (TEST (ready unit 1)) Cue: ACT 1 Plan One-Level Plan PDA Cell Manager New Order Cell Manager Plan Server Planner Subordinate PDA Terrain Reasoner Possibly Shared Agents Agent KQML Message Subordinate PDA Logistics Visualization/Comparison SRI International

Opportunities Enabled by MPA • Facilitate collaboration: – agents exchange information and influence each other during planning – can easily explore different degrees of collaboration • Can more easily explore/evaluate: – different organizational units for flexible control policies – different planning styles and strategies – new or alternative technologies SRI International

Backup Slides SRI International

The Problem Support rapid, accurate military decision making in information-rich warfighting environment SRI International

Example MPA Performatives Communication Plan Performative : annotation Insert Delete Ask-All Ask-One : trigger Insert Delete Ask-All Ask-One : update-task Tell Delete : update-plan Tell Delete : query-task Ask-all Ask-One : query-plan Ask-All Ask-One : query-node Ask-All Ask-One : ping Evaluate : pcd Tell Performatives accepted by the Plan Server SRI International

Planning Cells • Hierarchically organized collection of planning agents • Composed dynamially by the Planning-Cell Manager • Planning Cell Designator (PCD) provides registry of agents to fill various roles: Planner: SIPE-2 Scheduler: OPIS • Distribute tasks and PCD to PAs and meta-PAs • Each cell includes a plan server Planning cell: Planning-Cell Manager PA meta-PA PA PA Plan Server meta-PA PA PA SRI International

Planning Cell Manager (PCM) • Persistent agent continuously accepting tasks • Oversees problem-solving within a Planning Cell • Provides a range of problem-solving behaviors and strategies – user-configurable – can adapts strategies in response to runtime activities • PRS-based PCM – PCD and process state encoded in PRS database – strategies encoded in Acts – Example strategy: expand critique by levels • implemented by 14 Acts – small library of different PCMs • various cell configurations, problem-solving strategies SRI International

Meta Planning-Cells • Planning cell composed of a set of planning cells • A Meta-PCM controls and coordinates the cells • Accepts multiple planning requests, including advice • Distributes tasks to available planning cells • Gathers results for possible comparison Meta Planning-Cell: Meta Planning-Cell Manager Planning Cell SRI International

Act Plan Server • PRS-based Plan Server in current MPA applications – builds on reactive control capabilities • grounded in the Act Formalism model for plans Task: problem to be solved, advice, assumptions Action Networks: partial orders of activities, at multiple abstraction levels Plan: linked sets of action networks Nodes: individual activites (goals, actions) • limited persistence, versioning, browsing, and no access control SRI International

MPA Multiple Planning-Cell Configuration task solved Meta Planning. Cell Manager (PRS) Cue: ACT 2 (TEST (ready unit 1)) Cue: ACT 1 Plan One-Level Planning Cell Planning-Cell Manager Search Manager Temporal Reasoner Visualization/Comparison KQML Message request solution to task Planning-Cell Manager Search Manager Critic Manager Shared Agents Agent task solved Plan Server Cue: ACT 2 (TEST (ready unit 1)) ACT 1 Cue: Answer query Annotations Critic Manager Shared Agents Scheduler Simulator Triggers SRI International