a receding horizon genetic algorithm for dynamic multi-target assignment and tracking
DESCRIPTION
A receding horizon genetic algorithm for dynamic multi-target assignment and tracking. A case study on the optimal positioning of tug vessels along the northern Norwegian coast. Robin T. Bye, Assoc. Prof. Dept. of Technology and Nautical Sciences Ålesund University College (ÅUC) - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/1.jpg)
A receding horizon genetic algorithm for dynamic multi-target assignment and trackingA case study on the optimal positioning of tug vessels along the northern Norwegian coast
Robin T. Bye, Assoc. Prof.Dept. of Technology and Nautical Sciences
Ålesund University College (ÅUC)Norway
![Page 2: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/2.jpg)
Robin T. Bye, Ålesund University College 2
Introduction
• Multiple agents are to be (a) assigned and (b) track multiple moving targets in a dynamic environment
• (a) Target assignment/resource allocation:– which agents shall track which targets?
• (b) Collective tracking/positioning:– how should the agents move to increase net
tracking performance or minimise cost?
ICEC, Valencia, 25.10.2010
![Page 3: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/3.jpg)
Robin T. Bye, Ålesund University College 3
Introduction cont’d
• Tracking performance:– how to define a cost measure?
• Dynamic environment:– how can agents respond to• targets changing their trajectories?• new targets appearing and/or targets disappearing?• variable external conditions?
ICEC, Valencia, 25.10.2010
![Page 4: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/4.jpg)
Robin T. Bye, Ålesund University College 4
Case study: Positioning of tugs
• Norwegian Coastal Administration (NCA)– runs a Vessel Traffic Services (VTS) centre in Vardø– monitors ship traffic off northern Norwegian coast with
the automatic identification system (AIS)– commands a fleet of patrolling tug vessels
• Patrolling tug vessels (=agents)– must stop drifting oil tankers (=targets) or other ships
and tow them to safety before grounding– are instructed by NCA to go to “good” positions that
(hopefully) reduce the risk of drift grounding accidents
ICEC, Valencia, 25.10.2010
![Page 5: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/5.jpg)
Robin T. Bye, Ålesund University College 5
Automatic identification system (AIS)• Ships required to use AIS by law• Real-time VHF radio transmission to VTS centres• Static info: ID, destination, cargo, size, etc.• Dynamic info: Speed, position, heading, etc.• Enables prediction of future state of ships (e.g.,
position, speed, rate of turn)
ICEC, Valencia, 25.10.2010
![Page 6: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/6.jpg)
Robin T. Bye, Ålesund University College 6
Dynamical risk models of NCA• Risk-based decision support tools• Based on static information
– type of ships, cargo, crew, nationality, etc.– geography, e.g., known dangerous waters
• … and dynamic information– Ships’ position, direction, speed, etc.– weather conditions, e.g., wind, currents, waves, etc.
ICEC, Valencia, 25.10.2010
![Page 7: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/7.jpg)
Robin T. Bye, Ålesund University College 7
Dynamical risk models of NCA
Courtesy NCA
ICEC, Valencia, 25.10.2010
![Page 8: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/8.jpg)
Robin T. Bye, Ålesund University College 8
Dynamical risk models of NCA
Courtesy NCA
ICEC, Valencia, 25.10.2010
![Page 9: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/9.jpg)
Robin T. Bye, Ålesund University College 9
Motivation
• Today: Human operator makes decisions based on dynamical risk models
• Limitation: Requires small number of tankers and tugs to be manageable by human operator
• Oil/gas development in northern waters will increase traffic in years to come
How should a fleet of tugs move to reduce risk of accidents?
• Algorithm needed for optimising tug positioning
ICEC, Valencia, 25.10.2010
![Page 10: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/10.jpg)
Robin T. Bye, Ålesund University College 10
Oil tanker traffic
• Traffic: Along corridors
• Tugs: Near shore• We can approximate
corridors by parallel lines
Courtesy NCA
ICEC, Valencia, 25.10.2010
![Page 11: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/11.jpg)
Robin T. Bye, Ålesund University College 11ICEC, Valencia, 25.10.2010
Problem description• Lines of motion
for 3 oil tankers (white) and 2 patrol tugs (black)
• Predicted drift paths at future points in time
• How should tugs move?
![Page 12: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/12.jpg)
Robin T. Bye, Ålesund University College 12
Example scenario
ICEC, Valencia, 25.10.2010
![Page 13: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/13.jpg)
Robin T. Bye, Ålesund University College 13
Scenario explanation
• Crosspoint: Where drift trajectory of a tanker crosses patrol line of tugs
• Typical drift time: 8-12 hours before crossing of patrol line entering high-risk zone
• White circles: Predicted crosspoints of drift trajectories of 6 oil tankers
• Prediction horizon Th=24 hours ahead• Black circles: Suboptimal trajectories of 3 tugs
How to optimise tug trajectories?
ICEC, Valencia, 25.10.2010
![Page 14: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/14.jpg)
Robin T. Bye, Ålesund University College 14
Method
• Examine a finite number of potential patrol trajectories and evaluate a cost function for each
• Use a genetic algorithm to find good solutions in reasonable time
• Use receding horizon control to incorporate a dynamic environment and update trajectories
• Plan trajectories 24 hours ahead but only execute first hour, then replan and repeat
ICEC, Valencia, 25.10.2010
![Page 15: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/15.jpg)
Robin T. Bye, Ålesund University College 15
Genetic algorithm (GA)
• Employs the usual GA scheme:1. Define cost function, chromosome encoding and
set GA parameters, e.g., mutation, selection 2. Generate an initial population of chromosomes3. Evaluate a cost for each chromosome4. Select mates based on a selection parameter5. Perform mating6. Perform mutation based on a mutation parameter7. Repeat from Step 3 until desired cost level reached
ICEC, Valencia, 25.10.2010
![Page 16: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/16.jpg)
Robin T. Bye, Ålesund University College 16
Some GA features
• Population size: Number of chromosomes• Selection: Fraction of chromosomes to keep
for survival and reproduction• Mating: Combination of extrapolation and
crossover, single crossover point• Mutation rate: Fraction of genes mutated at
every iteration
ICEC, Valencia, 25.10.2010
![Page 17: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/17.jpg)
Robin T. Bye, Ålesund University College 17
Cost function
• Sum of distances between all crosspoints and nearest patrol points (positions of tugs)– only care about nearest tug that can save tanker
• Define ytp as pth tug’s patrol point at time t
• Define ytc as cth tanker’s cross point at time t
• Consider No oil tankers and Np patrol tugs
Function of time t and chromosome Ci:
ICEC, Valencia, 25.10.2010
![Page 18: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/18.jpg)
Robin T. Bye, Ålesund University College 18
Cost function cont’d
cost
nearest patrol point
cross point
ICEC, Valencia, 25.10.2010
![Page 19: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/19.jpg)
Robin T. Bye, Ålesund University College 19
Chromosome encoding
• Contains possible set of Np control trajectories:
• Each control trajectory u1p,…,uTh
p is a sequence of control inputs with values between -1 (max speed south) and +1 (max speed north)
• Sequence of patrol points for tug p at time t from difference equation (ts is sample time):
ICEC, Valencia, 25.10.2010
![Page 20: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/20.jpg)
Robin T. Bye, Ålesund University College 20
Receding horizon genetic algorithm (RGHA)
• Scenario changes over time:– Winds, ocean currents, wave heights, etc.– Tanker positions, speeds, directions, etc.
• Must reevaluate solution found by GA regularly receding horizon control:1. Calculate (sub)optimal set of trajectories with duration
Th (24 hours, say) into the future2. Execute only first part (1 hour, say) of trajectories 3. Repeat from Step 1 given new and predicted
information
ICEC, Valencia, 25.10.2010
![Page 21: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/21.jpg)
Robin T. Bye, Ålesund University College 21
Simulationstudy
ICEC, Valencia, 25.10.2010
![Page 22: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/22.jpg)
Robin T. Bye, Ålesund University College 22
Simulation example, td=0 hours
ICEC, Valencia, 25.10.2010
![Page 23: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/23.jpg)
Robin T. Bye, Ålesund University College 23
Simulation example, td=10 hours
ICEC, Valencia, 25.10.2010
![Page 24: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/24.jpg)
Robin T. Bye, Ålesund University College 24
Simulation example, td=25 hours
ICEC, Valencia, 25.10.2010
![Page 25: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/25.jpg)
Robin T. Bye, Ålesund University College 25
Results
• Mean cost– Static strategy: 2361– RHGA: 808– Performance improvement: 65.8%
• Standard deviation– Static strategy: 985– RHGA: 292– Improvement: 70.4%
ICEC, Valencia, 25.10.2010
![Page 26: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/26.jpg)
Robin T. Bye, Ålesund University College 26
Conclusions
• The RHGA is able to simultaneously perform multi-target allocation and tracking in a dynamic environment
• The choice of cost function gives good tracking with target allocation “for free” (need no logic)
• The RHGA provides good prevention against possible drift accidents by accounting for the predicted future environment
ICEC, Valencia, 25.10.2010
![Page 27: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/27.jpg)
Robin T. Bye, Ålesund University College 27
Future directions
• Comparison with other algorithms• Extend/change cost function– punish movement/velocity changes (save fuel)– vary risk factor (weight) of tankers– use a set of various max speeds for tankers/tugs
• Incorporate boundary conditions• Add noise and nonlinearities• Extend to 2D and 3D• Test with other/faster systems
ICEC, Valencia, 25.10.2010
![Page 28: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/28.jpg)
Robin T. Bye, Ålesund University College 28
Questions?
ÅUC campus
Robin T. Bye, [email protected] Møre project, www.virtualmore.orgÅlesund University College, www.hials.no
ICEC, Valencia, 25.10.2010
![Page 29: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/29.jpg)
Robin T. Bye, Ålesund University College 29
Results
ICEC, Valencia, 25.10.2010
![Page 30: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/30.jpg)
Robin T. Bye, Ålesund University College 30
Simulation example, td=0 hours
ICEC, Valencia, 25.10.2010
![Page 31: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/31.jpg)
Robin T. Bye, Ålesund University College 31
Simulation example, td=5 hours
ICEC, Valencia, 25.10.2010
![Page 32: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/32.jpg)
Robin T. Bye, Ålesund University College 32
Simulation example, td=10 hours
ICEC, Valencia, 25.10.2010
![Page 33: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/33.jpg)
Robin T. Bye, Ålesund University College 33
Simulation example, td=15 hours
ICEC, Valencia, 25.10.2010
![Page 34: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/34.jpg)
Robin T. Bye, Ålesund University College 34
Simulation example, td=20 hours
ICEC, Valencia, 25.10.2010
![Page 35: A receding horizon genetic algorithm for dynamic multi-target assignment and tracking](https://reader035.vdocuments.net/reader035/viewer/2022062310/56816364550346895dd438d6/html5/thumbnails/35.jpg)
Robin T. Bye, Ålesund University College 35
Simulation example, td=25 hours
ICEC, Valencia, 25.10.2010