Timeline-based Planning and Execution: Theory and Practice - PLATINUm - A Novel framework for PL anning and A cting with TI meli N es under U ncertainty Alessandro Umbrico National Research Council of Italy (ISTC-CNR)
Outline p General Introduction to PLATINUm n History, general motivations and objectives p PLATINUm Representation Capabilities n Temporal Uncertainty, Components and Resolvers p PLATINUm Deliberative Capabilities n Pseudo-controllability aware planning and hierarchical approach p PLATINUm Executive Capabilities n Closed-loop control approach and controllability issues p PLATINUm in Action n Human-Robot Collaboration in realistic manufacturing scenarios 1
GENERAL INTRODUCTION TO PLATINUM 2
A Brief History of PLATINUm Formalization of Timeline-based Approach with Temporal Uncertainty and Resources [Cialdea et al. 2016] + [Umbrico et al. 2018] PLATINUm HSTS APSI-TRF APSI-GOAC EPSL PLATINUm + Resources [Muscettola et al. 1994] [Cesta et al. 2008] [Fratini et al. 2011] [Umbrico et al. 2015] [Umbrico et al. 2017] [Umbrico et al. 2018] 3
Motivations and Objectives p Several timeline-based systems successfully applied in practice n E.g., EUROPA2 , ASPEN , IxTeT , APSI-TRF p Lack of uniform formal interpretation of the main concepts n E.g., different interpretation of timelines, domain rules, plans and solutions p Lack of a uniform approach to planning and execution with timelines n E.g., different approaches to solving and modeling problems with timelines p Lack of representation of uncertainty and uncontrollable dynamics 4
Framework Capabilities p A software framework capable of dealing with planning and execution of timelines under temporal uncertainty n Comply with the formalization proposed in [Cialdea et al. 2016] p Synthesize timeline-based plans with some desired controllability properties n E.g., pseudo-controllability p Execute timelines by dealing with the dynamics of the uncontrollable features of the environment n The controllability problem [Morris, Muscettola and Vidal 2001] 5
Architectural Overview of the Framework Executive Planner Monitor Clock Dispatcher Strategy Solver Heuristics Executive Plan Database Manager Deliberative Executive Representation Plan Database Domain Component Resolver Temporal Database Parameter Database 6
A Layered Architecture for PLATINUm p The Representation Layer is responsible for providing the basic functionalities needed to manage timeline-based plans n Encapsulate data structures and algorithms needed to build valid timelines p The Deliberative Layer is responsible for solving planning problems by synthesizing timeline-based solution plans n Encapsulate heuristics, strategies and algorithms needed to build plans p The Executive Layer is responsible for executing timelines by scheduling flexible tokens over time n Encapsulate dispatching and monitoring algorithms to dynamically adapt timelines during execution, according to the received feedbacks 7
GOING DEEP INTO REPRESENTATION CAPABILITIES 8
Plan Database Overall Structure 9
Plan Data Representation and Management p Temporal information is managed through Temporal Networks n Framework enabling temporal inference and consistency checking [Dechter et al. 1991] p Simple Temporal Network with Uncertainty (STNU) to manage uncontrollable durations p Controllability check [Morris, Muscettola and Vidal 2001] p A “standard” CSP solver is encapsulated to manage variable assignment and constraint propagation n Choco CSP solver 10
Resolvers and Components p Domain components are data structures that model the features of a planning domain that must be controlled over time n Each feature has its own constraints that must be satisfied to generate valid timelines i.e., temporal behaviors without flaws p Resolvers represent specialized algorithms capable of detecting flaws and computing possible solutions n Each resolver encapsulates the logic for handling a particular type of flaw p PLATINUm provides a set of ready to use components and resolvers representing the typical features that compose a timeline-based planning domain 11
State Variables p Components that comply with the proposed formalization n Encapsulate values, durations, controllability tags and transition constraints p Resolvers are provided to synthesize timelines n Schedule state variable tokens n Synthesize complete sequences of tokens enforcing transition constraints 12
Discrete and Reservoir Resources p Components encapsulate resource constraints and resource events according to the tokens of the timelines p Resolvers provide the logic for detecting and solving peaks n Compute pessimistic and optimistic resource profiles n Compute peak solutions through Minimal Critical Sets (MCSs) p Planning & Scheduling integration 13
The Plan Database p Encapsulating all the domain components and configurations n Composite design pattern n Provide a public interface to domain features and data p Leverage internal components to detect planning goals n Planning goal solutions computed through synchronization rules n Apply expansion or unification 14
GOING DEEP INTO DELIBERATIVE CAPABILITIES 15
Detailed Structure of a PLATINUm Planner 16
Pseudo-controllability Aware Solving p General plan refinement search procedure n Iteratively refine an initial partial plan by solving flaws, until a valid plan without flaws is found n Search decision point : which partial plan to select for search space expansion n Flaw decision point : which flaw to solve for plan refinement p Pseudo-controllability check as a special flaw of the plan n Verify if the flexible durations of the uncontrollable tokens have been modified with respect to the domain specification n Pseudo-controllability is a necessary but not sufficient condition for dynamic controllability 17
Hierarchical Flaw Selection Heuristics p Analyze synchronization rules Functional variables SV A to extract dependencies among state variables and their values SV B SV C n Extract a hierarchy if possible n Domain-independent heuristics Primitive variables p Leverage the extracted SV D SV E hierarchy to evaluate flaws and decide which flaw to solve next SV B SV D SV A n Support flaw decision point SV C SV E 18
Search & Build Plan Synthesis p Search phase aims at constraining temporal behaviors as much as possible n Interleave planning and scheduling decisions by reasoning on flaws n Constraint state variables behaviors according to synchronization rules and resource constraints - generated behaviors are not timelines yet p Build phase aims at finalizing timelines by enforcing semantics defined by the formalization n Synthesize valid timelines according to the constrained behaviors of state variables generated by the search phase n Backtrack by jumping-back to the search phase in case of failures 19
Defining and Using a PLATINUm Planner 20
GOING DEEP INTO EXECUTIVE CAPABILITIES 21
Detailed Structure of a PLATINUm Executive 22
Closed-loop Execution of Timeline-based Plans p A PLATINUm executive consists of a closed-loop control process which iteratively fix flexible timelines over time p A Dispatcher actually executes the timelines of a plan by sending commands to a physical system n It is responsible for deciding the start of the execution of the tokens that compose the timelines of a plan p A Monitor handles execution feedbacks to verify whether the plan complies with the observed status of the environment or not n It is responsible for propagating information about the actual duration of uncontrollable tokens 23
Executing Timelines under Temporal Uncertainty p Extract start/end execution dependencies by analyzing uncontrollable partially temporal relations of a plan controllable controllable waiting n Dynamically generate a waiting waiting c execution dependency graph c starting c in-execution u p Manage token transitions in-execution in-execution according to their c u u controllability properties executed executed executed n Different controllability properties entail different dispatching policies 24
Closed-loop Control Architecture buffered re-planning Deliberative planned failure executed Executive Failure Manager Dispatcher Monitor send command feedback feedback send command System/ROS-based Simulator 25
HUMAN-ROBOT COLLABORATION CASE STUDY 26
The FourByThree Research Project p Horizon 2020 research project n Call FoF-06-2014 “Symbiotic Human-Robot Collaboration for safe and dynamic multimodal manufacturing systems” n Coordinated by FUNDACION TEKNIKER (Spain) n http://fourbythree.eu/ 27
Objectives of the Project p Develop a new generation of modular industrial robotic solutions that are suitable for efficient task execution in collaboration with humans in a safe way and are easy to use and program n Vision : A system integrator (or end-user) can create its own custom robot according to their application needs (“kit” of hardware and software components) p Real-world Pilot case studies to test Human-Robot Collaboration n ALFA , WOLL, STODT, PREMIUM 28
ALFA: A Collaborative Assembly Case Study p Investment Casting process n Dies are assembled and disassembled manually n Some operations need human dexterity n Others can be done by a robot p Re-design the process by taking into account an HRC perspective n Hierarchical process description n Three levels: Supervision , Coordination , Implementation 29
Recommend
More recommend
