Simulating Uninhabited Combat Aircraft in Hostile ... - Philippe Morignot
Mission. â¢Stand-alone UCAV. â¢Recce UCAVs. â¢Strike UCAVs. F .E .B .A . Pop-up threat ... Choosing a single proposal for each UCAV and a feasible attack time ...
Simulating Uninhabited Combat Aircraft in Hostile Environments (Part II) P. Morignot, J.-C. Poncet, J. Baltié, P. Fabiani, E. Bensana, J.-L. Farges, B. Patin
2005 EURO SPRING SIW
Motivation • Less dangerous situations for pilots. • Uninhabited Combat Aircraft Vehicles (UCAVs) have been studied for 10 years. • French initiative over the last years, funded by the Délégation Générale pour l’Armement (the French DARPA).
2005 EURO SPRING SIW
Mission
F.E.B.A.
Split
•Stand-alone UCAV •Recce UCAVs •Strike UCAVs
Pop-up threat area
Attack
2005 EURO SPRING SIW
Goals • • • •
Simulation of the ground and air environment. Pseudo real-time. Reasoning under time stress. Collaboration among UCAVs.
2005 EURO SPRING SIW
Software Architecture Time out, Imposed waypoints
Plan
Plan (from now on)
Plan (from now on)
Long-Term Ps, Long Term Pk, location, time
Long-Term Observe
Format
Short-Term Ps < threashold Short-Term location out of a zone Navigation Point, etc...
System functions
Contingency Plan
Formatted plan (from now on)
Act
Reactive Level
Preempt Observe & Compare
Decisional Level
Compare
Prepare
2005 EURO SPRING SIW
Collaboration Model Choosing a single proposal for each UCAV and a feasible attack time and a feasible attack mode for each objective treated by maximising global efficiency of attack and package survival probability UCAV 1 enumerating a set of proposals taking into account topology and own resources
plan
UCAV n enumerating a set of proposals taking into account topology and own resources
Proposal: •Sequence of attacked objectives •Minimum and maximum time between objectives •Available weapons •Survival probability
2005 EURO SPRING SIW
Planner Implementation
2005 EURO SPRING SIW
Conclusion • Work in progress (end in April 2006). – First simulation of the main components using Petri nets [Morignot et al. 04]. – Software architecture (reactive, decisional levels, system functions). – Planner : • Collaboration by propositions • Anytime property
– Integration tested on scenarios of increasing difficulty.
• Future research directions: – More experiments (first demo planned in September, 2005). – High Level Architecture (HLA) for pseudo real-time simulation. – Porting the models on 3 small real aircraft.
interaction constraints by selecting a single proposition by agent. Optionally .... Pi,k; minimization of the dual variables β, µi,k and κi,k) has to be searched for, ...
Graphical Environments : X/Motif, basics of ILOG VIEWS .... Consultant in optimization. Scheduling the test campaign of L'OREAL products (ILOG SCHEDULER).
which includes the available sensori-motor control loops of the robotic agent. ... has been proposed for intelligent transportation systems, such as automated cars in ... for later computing the detailed voltage to give to electrical effectors (e.g.
Feb 8, 2012 - Constraint Satisfaction Problems (CSPs). ⢠UML / OCL. ⢠Principles for using ... Cost f: Constraint Satisfaction and Optimization Problem (CSOP).
people (end users and care takers) very intuitively in a domestic setting. Keywords. .... impairments, such as those in an early stage of the Alzheimer's disease. ... another partner in the project, the robot is able to plan his path through the hous
Mar 28, 2011 - with an A.I. task planner, to represent these scenarios in a high level language and to ... there are many scenarios which would have to be manually written in real ..... 01/08/2008-03/08/2008, Munich, Germany. [21] V. Vidal, H.
operations, vehicle subsystems, and the MMS of other UCAV. .... Download ..... enough fuel to finish the mission are checked. It ...... cdc03/cdc03b_ros_rmm.pdf ...
Turing test (see Introduction section) on the long term. Unfortunately, A.I. is often only considered as a library of algorithms, in which Robotics researchers dig as ...
Jul 8, 2013 - Constraint programming is one paradigm for ... The variables involved in constraint C k. ⢠R ..... optimization to compute; And (ii) the optimum.
its name (âCarâ class), an internal class (âDriverEmotionâ) and its possible motion (âMotionâ class, with sub-classes ..... http://code.google.com/p/swoop/.
reified constraints without any extension; 3) it opens up constraint propa- ... global store, and specify optimization procedures such as Branch-and-Bound. In.
Apr 29, 2016 - April 29, 2016. Seminar VEH08, VEDECOM. 4 f. 1 f. 2 ⦠f n g. 1 g. 2 ⦠g l. State. Goals ? ⦠... Universal quantifications? ⢠Qualification problem .... Using (forward) search in a plan space (A. Barrett). ⢠Using evolutionnar
follow a path of timed waypoints provided by a C2 interface. ..... RAM on a virtual machine. .... ity in CP is the CSP solver CHOCO (Prud'homme, Fages,.
Jun 26, 2018 - constraint optimization problem. ⢠Search for a path (timed waypoints in a topological map) for multiple coordinated agents, while optimizing a ...
Oct 25, 2013 - Example: for the sudoku game, a coarse evaluation of the number of combinations is (8!) ..... http://afpc.greyc.fr/web/. P. Morignot - Softshake'13.
Example (1/3). ⢠Sudoku: P. Morignot - Softshake'14. 4 ... Example: for the sudoku game, a coarse evaluation of the number of ..... http://afpc.greyc.fr/web/.
Feb 18, 2015 - February 18, 2015. Planning Domain Definition Language: problem. LifeWare ... (:goal (and. (ON L C) (ON C P) (ON P Q) (ON Q M) (ON M B).
function, tests are conducted on a single Sun Blade. 1500 computer. ... 100. Time (s). E fficien cy no attack. 1 target. 2 targets. 3 targets. 4 targets. Fig. 7.
intelligent vehicles, as a function of V2V communication (for the ego vehicle to ..... ware [10] suggests that V2V communication and dynamic path-finding ...
