Timeline-based Planning and Execution: Theory and Practice - - - PowerPoint PPT Presentation
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
Alessandro Umbrico National Research Council of Italy (ISTC-CNR)
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
2
3
HSTS
[Muscettola et al. 1994]
APSI-TRF
[Cesta et al. 2008]
APSI-GOAC
[Fratini et al. 2011]
EPSL
[Umbrico et al. 2015]
PLATINUm
[Umbrico et al. 2017]
Formalization of Timeline-based Approach with Temporal Uncertainty and Resources
[Cialdea et al. 2016] + [Umbrico et al. 2018]
PLATINUm + Resources
[Umbrico et al. 2018]
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
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
Deliberative
Planner Strategy Solver Heuristics
Representation
Plan Database Domain Component Resolver Temporal Database Parameter Database
Executive
Executive Monitor Clock Dispatcher Executive Plan Database Manager
6
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
8
9
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
p Domain components are data structures that model the features
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
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
constraints
12
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
n Compute peak solutions through
Minimal Critical Sets (MCSs)
p Planning & Scheduling integration
13
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
15
16
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
p Analyze synchronization rules
to extract dependencies among state variables and their values
n Extract a hierarchy if possible n Domain-independent heuristics
p Leverage the extracted
hierarchy to evaluate flaws and decide which flaw to solve next
n Support flaw decision point
18
Functional variables
SVA SVB SVC
Primitive variables
SVD SVE
SVA SVB SVC SVD SVE
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
20
21
22
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
p Extract start/end execution
dependencies by analyzing temporal relations of a plan
n Dynamically generate a
execution dependency graph
p Manage token transitions
according to their controllability properties
n Different controllability properties
entail different dispatching policies
waiting in-execution c executed c
controllable
waiting in-execution c executed u
partially controllable
waiting starting c in-execution u executed u
uncontrollable
24
Deliberative
buffered planned
Failure Manager Executive
Dispatcher Monitor
failure executed re-planning
System/ROS-based Simulator
send command feedback feedback send command
25
26
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
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
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
Robot’s motion tasks Human’s assigned tasks
30
Verify the capabilities of an integrated task and motion planning control to improve the efficiency of HRC assembly processes
31
257 225 195 171 169 172 0% 10% 20% 30% 40% 50% 60% 70% 80% 50 100 150 200 250 300 1 2 3 4 5 6 7 Execution TIme [s] Execution Time [s] Saved Time [%] Robot Allocated Task [%]
Planning can reduce the duration of HRC processes and realize effective and safe collaborations between human operators and robots [Pellegrinelli et al. CIRP Annals 2017]
32
p HRC is particularly suited to show the capabilities of PLATINUm
p Temporal uncertainty and hierarchical problem modeling and solving
p The FourByThree research project has shown the capability of
PLATINUm to synthesize flexible and adaptable behaviors of a robot acting in the real-world
p Download PLATINUm from GitHub:
https://github.com/pstlab/PLATINUm
33
34
p A knowledge engineering environment aimed at supporting the
design and development of timeline-based applications
n Round-trip-engineering to support both graphical and programming user
interface to model timeline-based domains
n Available as plugin for the Eclipse IDE n https://ugilio.github.io/keen/
p Integrated with PLATINUm
n Launch platinum-based planners on designed timeline-based domains n Launch platinum-based executive to simulate execution of synthesized
plans
35
p PLATINUm is an open framework which can be “easily” extended
to introduce new representation features and solving capabilities
n Discrete and Reservoir Resource management has been recently
introduced [Umbrico et al. ICAPS 2018]
p Future works
n Investigate new heuristics and new search strategies n Integrate dynamic controllability checking algorithms n Comparison with other state of the art timeline-based and hybrid planners
p EUROPA [Barreiro et al., 2012], CHIMP [Stock et al., 2015], FAPE [Dvorak et al.,
2014]
36
37
PLATINUm – PLanning and Acting with TImeliNes under Uncertainty
Available on GitHub https://github.com/pstlab/PLATINUm