SlideShare a Scribd company logo
1 of 26
Download to read offline
University of Luxembourg
Multilingual. Personalized. Connected.
Improving Pheromone Communication for UAV Swarm Mobility Management
Daniel H. Stolfi1
Matthias R. Brust1
Grégoire Danoy1,2
Pascal Bouvry1,2
13th
International Conference on Computational Collective Intelligence – ICCCI 2021
September 29th – October 1st, 2021
1
SnT - Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg
2
FSTM/DCS, University of Luxembourg, Luxembourg
TABLE OF CONTENTS
1 INTRODUCTION
2 PHEROMONE BASED MOBILITY
3 OPTIMISATION ALGORITHM
4 EXPERIMENTAL RESULTS AND CONCLUSIONS
TABLE OF CONTENTS
1 INTRODUCTION
2 PHEROMONE BASED MOBILITY
3 OPTIMISATION ALGORITHM
4 EXPERIMENTAL RESULTS AND CONCLUSIONS
1/19
UAV: UNMANNED AERIAL VEHICLE
UAVs, also known as drones, can be fixed wings or multi-rotors.
They are usually equipped with:
I Video (infrared) cameras
I Radio communication devices
I Sensors (pollution, radiation, etc.)
I Actuators
Advantages
I Explore different areas
I High speed
I Excellent communication capabilities
Disadvantages
I Reduced flight time
I Cannot carry larger payloads
Photo by Daniel H. Stolfi Source: indiamart.com
2/19
UAV – APPLICATIONS
UAVs are widely used in many applications:
Goods transportation
Road traffic surveillance
Fire fighting
Environmental monitoring
Wildfire monitoring
Farming
Architecture surveillance
Internet delivery
Homeland security
To herd a flock of birds away from an airport (!)
Surveillance systems
Source: procurious.com
Photo by Tyler Casey on unsplash.com
3/19
TABLE OF CONTENTS
1 INTRODUCTION
2 PHEROMONE BASED MOBILITY
3 OPTIMISATION ALGORITHM
4 EXPERIMENTAL RESULTS AND CONCLUSIONS
4/19
SURVEILLANCE APPROACH
Our approach to surveillance missions comprises:
Multi-swarms of Unmanned Aerial Vehicles
Unpredictable trajectories
Maximising area coverage
Maximising intruder detections
Pheromone based mobility
Mobility models analysed:
CROMM (Chaotic Rössler Mobility Model) → Pure chaotic
CACOC (Chaotic Ant Colony Optimisation for Coverage) → CROMM + Pheromones
CACOC+ → Parameterised version of CACOC
5/19
CROMM1
Pure chaotic mobility
1
M. Rosalie, G. Danoy, S. Chaumette, and P. Bouvry. “Chaos-enhanced mobility models for multilevel swarms of UAVs”. In: Swarm and Evol. Comput. 41.November 2017 (2018), pp. 36–48.
6/19
CACOC MOBILITY MODEL2
Pheromone trails
2
M. Rosalie, G. Danoy, S. Chaumette, and P. Bouvry. “Chaos-enhanced mobility models for multilevel swarms of UAVs”. In: Swarm and Evol. Comput. 41.November 2017 (2018), pp. 36–48.
7/19
CACOC+ MOBILITY MODEL3
TABLE: Parameters of CACOC+.
Parameter Units Range
Pheromone amount (τa) % [1 − 100]
Pheromone radius (τr ) cells [0.5 − 2.5]
Pheromone scan depth (τd ) cells [1 − 10]
Each UAV in the swarm
has to know about
the pheromone trails in
the neighbourhood
3
D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UAV Swarms”. In: 2020 IEEE 17th Annual Consumer Communications &
Networking Conference (CCNC). IEEE, 2020, pp. 1–6.
8/19
PHEROMONE SHARING
(a) Full pheromone map (b) UAV1’s known map (c) UAV2’s known map
FIGURE: Pheromone Sharing
9/19
COMMUNICATION SCENARIOS
Radio link subject to interferences
Maximum communication range
Shorter data packets could
reduce. . .
I packet loss probability
I energy consumption
Could we keep good coverage rates by
optimising the parameters of CACOC+?
FIGURE: Four scenarios simulated using ARGoS
10/19
COMMUNICATION SCENARIOS
Radio link subject to interferences
Maximum communication range
Shorter data packets could
reduce. . .
I packet loss probability
I energy consumption
Could we keep good coverage rates by
optimising the parameters of CACOC+?
FIGURE: Four scenarios simulated using ARGoS
10/19
TABLE OF CONTENTS
1 INTRODUCTION
2 PHEROMONE BASED MOBILITY
3 OPTIMISATION ALGORITHM
4 EXPERIMENTAL RESULTS AND CONCLUSIONS
11/19
OPTIMISATION ALGORITHM: GA
GAs are efficient method for solving combinatorial optimisation problems
Simulates processes present in evolution
Operators:
I Binary tournament
I Uniform crossover
I Mutation for integers values
I Best individual in offspring replaces the worst individual in population
Problem representation:
Fitness function:
~
x = {τa1
, τr1
, τd1
, . . . , τaN
, τrN
, τdN
}
F(~
x) = # of explored cells
# of cells in the scenario
N ∈ {2, 4, 6} is the number of UAVs in the swarm
12/19
EVALUATION: ARGOS SIMULATOR
FIGURE: ARGoS Simulator
Simulation of UAV’s dynamics
Realistic communication layer
10-metre radio range
Simulated packet loss rates
1000 evaluations per GA run
360 runs in total
10 equivalent days of computing
time (reduced by parallel
evaluations/runs)
13/19
EVALUATION: ARGOS SIMULATOR
FIGURE: ARGoS Simulator
Simulation of UAV’s dynamics
Realistic communication layer
10-metre radio range
Simulated packet loss rates
1000 evaluations per GA run
360 runs in total
10 equivalent days of computing
time (reduced by parallel
evaluations/runs)
13/19
TABLE OF CONTENTS
1 INTRODUCTION
2 PHEROMONE BASED MOBILITY
3 OPTIMISATION ALGORITHM
4 EXPERIMENTAL RESULTS AND CONCLUSIONS
14/19
OPTIMISATION RESULTS
Case Study Scenario
Fitness Friedman
Rank
Wilcoxon
p-value
Avg. SD. Max.
2 UAVs
CACOC+ 0.524 0.005 0.538 2.50 0.365
CACOC+.10 0.523 0.006 0.535 2.10 0.325
CACOC+.05 0.525 0.006 0.535 2.68 0.802
CACOC+.00 0.526 0.007 0.539 2.72 —
4 UAVs
CACOC+ 0.769 0.006 0.780 2.28 0.087
CACOC+.10 0.771 0.007 0.788 2.70 0.640
CACOC+.05 0.769 0.005 0.782 2.22 0.120
CACOC+.00 0.772 0.006 0.786 2.80 —
6 UAVs
CACOC+ 0.885 0.005 0.895 2.48 0.246
CACOC+.10 0.887 0.004 0.897 2.70 —
CACOC+.05 0.885 0.004 0.893 2.52 0.133
CACOC+.00 0.884 0.006 0.896 2.30 0.058
Fitness values of each optimisation run for each case study and scenario.
15/19
OPTIMISATION RESULTS
Case Study Scenario
Fitness Friedman
Rank
Wilcoxon
p-value
Avg. SD. Max.
2 UAVs
CACOC+ 0.524 0.005 0.538 2.50 0.365
CACOC+.10 0.523 0.006 0.535 2.10 0.325
CACOC+.05 0.525 0.006 0.535 2.68 0.802
CACOC+.00 0.526 0.007 0.539 2.72 —
4 UAVs
CACOC+ 0.769 0.006 0.780 2.28 0.087
CACOC+.10 0.771 0.007 0.788 2.70 0.640
CACOC+.05 0.769 0.005 0.782 2.22 0.120
CACOC+.00 0.772 0.006 0.786 2.80 —
6 UAVs
CACOC+ 0.885 0.005 0.895 2.48 0.246
CACOC+.10 0.887 0.004 0.897 2.70 —
CACOC+.05 0.885 0.004 0.893 2.52 0.133
CACOC+.00 0.884 0.006 0.896 2.30 0.058
Fitness values of each optimisation run for each case study and scenario.
15/19
OPTIMISATION RESULTS
Case Study 2 UAV 4 UAV 6 UAV
CROMM 13.3% 43.5% 52.2%
CACOC 46.5% 71.0% 85.8%
CACOC.10 46.5% 68.7% 85.8%
CACOC.05 46.5% 71.6% 84.2%
CACOC.00 38.8% 70.2% 80.0%
CACOC+ 53.8% 78.0% 89.5%
CACOC+.10 53.5% 78.8% 89.7%
CACOC+.05 53.5% 78.2% 89.3%
CACOC+.00 53.9% 78.6% 89.6%
Coverage values
16/19
OPTIMISATION RESULTS
Case Study 2 UAV 4 UAV 6 UAV
CROMM 13.3% 43.5% 52.2%
CACOC 46.5% 71.0% 85.8%
CACOC.10 46.5% 68.7% 85.8%
CACOC.05 46.5% 71.6% 84.2%
CACOC.00 38.8% 70.2% 80.0%
CACOC+ 53.8% 78.0% 89.5%
CACOC+.10 53.5% 78.8% 89.7%
CACOC+.05 53.5% 78.2% 89.3%
CACOC+.00 53.9% 78.6% 89.6%
Coverage values
16/19
INTERFERENCES AND PACKET LOSS
(a) 2 UAVs (b) 4 UAVs (c) 6 UAVs
FIGURE: Area Coverage vs. Packet Loss Probability
17/19
INTERFERENCES AND PACKET LOSS
(a) 2 UAVs (b) 4 UAVs (c) 6 UAVs
FIGURE: Area Coverage vs. Packet Loss Probability
17/19
CONCLUSIONS AND FUTURE WORK
Conclusions
CACOC+ improved CACOC and CROMM in all scenarios
CACOC+ adapted the UAVs’ behaviour to deal with an incomplete
pheromone map
CACOC performance degraded with the reduction of the transmitted data
CROMM (pure chaotic) cannot compete with pheromone-based mobility
Future Work
Include more UAVs in the study
Use a specific parameter for each UAV
Alternative collision avoidance algorithm
Validation of trajectories using real drones
18/19
QUESTIONS?
Daniel H. Stolfi
daniel.stolfi@uni.lu
https://hunted.gforge.uni.lu/
https://pcog.uni.lu/
https://wwwen.uni.lu/snt/
https://wwwen.uni.lu/
Improving Pheromone Communication for UAV Swarm Mobility Management
Daniel H. Stolfi1, Matthias R. Brust1, Grégoire Danoy1,2, and Pascal Bouvry1,2
1 SnT - Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg
2 FSTM/DCS, University of Luxembourg, Luxembourg
References:
M. Rosalie, G. Danoy, S. Chaumette, and P. Bouvry. “Chaos-enhanced mobility models for multilevel swarms of UAVs”. In: Swarm and Evol. Comput. 41.November 2017 (2018),
pp. 36–48
D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UAV Swarms”. In: 2020 IEEE 17th Annual
Consumer Communications & Networking Conference (CCNC). IEEE, 2020, pp. 1–6
D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “Optimizing the Performance of an Unpredictable UAV Swarm for Intruder Detection”. In: Optimization and Learning. Cham:
Springer International Publishing, 2020, pp. 37–48
D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “Competitive Evolution of a UAV Swarm for Improving Intruder Detection Rates”. In: 2020 IEEE International Parallel and Distributed
Processing Symposium Workshops (IPDPSW). IEEE, May 2020, pp. 528–535
This work relates to Department of Navy award N62909-18-1-2176 issued by the Office of Naval Research. The United States Government has a royalty-free
license throughout the world in all copyrightable material contained herein. This work is partially funded by the joint research programme UL/SnT-ILNAS
on Digital Trust for Smart-ICT.
19/19

More Related Content

Similar to Improving Pheromone Communication for UAV Swarm Mobility Management

Risk assessment of mined areas using
Risk assessment of mined areas usingRisk assessment of mined areas using
Risk assessment of mined areas using
ijaia
 
Sampling based positioning of unmanned aerial vehicles as communication relay...
Sampling based positioning of unmanned aerial vehicles as communication relay...Sampling based positioning of unmanned aerial vehicles as communication relay...
Sampling based positioning of unmanned aerial vehicles as communication relay...
Inkonova AB
 
anaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURES
anaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURESanaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURES
anaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURES
Nathaniel A. ADEWOLE
 
Visual victim detection and quadrotor-swarm coordination control in search an...
Visual victim detection and quadrotor-swarm coordination control in search an...Visual victim detection and quadrotor-swarm coordination control in search an...
Visual victim detection and quadrotor-swarm coordination control in search an...
IJECEIAES
 

Similar to Improving Pheromone Communication for UAV Swarm Mobility Management (20)

ICRA 2013 talk 2
ICRA 2013 talk 2ICRA 2013 talk 2
ICRA 2013 talk 2
 
Drones and the Internet of Things: realising the potential of airborne comput...
Drones and the Internet of Things: realising the potential of airborne comput...Drones and the Internet of Things: realising the potential of airborne comput...
Drones and the Internet of Things: realising the potential of airborne comput...
 
IRJET- Drone Delivery System
IRJET- Drone Delivery SystemIRJET- Drone Delivery System
IRJET- Drone Delivery System
 
Risk assessment of mined areas using
Risk assessment of mined areas usingRisk assessment of mined areas using
Risk assessment of mined areas using
 
Sampling based positioning of unmanned aerial vehicles as communication relay...
Sampling based positioning of unmanned aerial vehicles as communication relay...Sampling based positioning of unmanned aerial vehicles as communication relay...
Sampling based positioning of unmanned aerial vehicles as communication relay...
 
IRJET - Drone Delivery System: A Review
IRJET - Drone Delivery System: A ReviewIRJET - Drone Delivery System: A Review
IRJET - Drone Delivery System: A Review
 
NVIDIA GTC 2018 Presentation
NVIDIA GTC 2018 PresentationNVIDIA GTC 2018 Presentation
NVIDIA GTC 2018 Presentation
 
SPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADS
SPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADSSPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADS
SPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADS
 
SPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADS
SPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADSSPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADS
SPOT-THE-CAMEL: COMPUTER VISION FOR SAFER ROADS
 
Creating a buzz
Creating a buzzCreating a buzz
Creating a buzz
 
Creating a buzz
Creating a buzzCreating a buzz
Creating a buzz
 
Ijetr021108
Ijetr021108Ijetr021108
Ijetr021108
 
Ijetr021108
Ijetr021108Ijetr021108
Ijetr021108
 
anaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURES
anaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURESanaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURES
anaFLY01-05: A MULTIPURPOSE QUADCOPTER WITH DUALITY FEATURES
 
Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...
Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...
Haptic Virtual Fixtures to Assist Endonasal Micro Robotic Surgery through Vir...
 
Visual victim detection and quadrotor-swarm coordination control in search an...
Visual victim detection and quadrotor-swarm coordination control in search an...Visual victim detection and quadrotor-swarm coordination control in search an...
Visual victim detection and quadrotor-swarm coordination control in search an...
 
Control of aircraft from the base station using eog siganl transmission
Control of aircraft from the base station using eog siganl transmissionControl of aircraft from the base station using eog siganl transmission
Control of aircraft from the base station using eog siganl transmission
 
Control of aircraft from the base station using eog siganl transmission
Control of aircraft from the base station using eog siganl transmissionControl of aircraft from the base station using eog siganl transmission
Control of aircraft from the base station using eog siganl transmission
 
Properties and Impact of Vicinity in Mobile Opportunistic Networks
Properties and Impact of Vicinity in Mobile Opportunistic NetworksProperties and Impact of Vicinity in Mobile Opportunistic Networks
Properties and Impact of Vicinity in Mobile Opportunistic Networks
 
OW2con'14 - Xlcloud, 3D rendering in the cloud
OW2con'14 - Xlcloud, 3D rendering in the cloudOW2con'14 - Xlcloud, 3D rendering in the cloud
OW2con'14 - Xlcloud, 3D rendering in the cloud
 

More from Daniel H. Stolfi

More from Daniel H. Stolfi (12)

Optimising Autonomous Robot Swarm Parameters for Stable Formation Design
Optimising Autonomous Robot Swarm Parameters for Stable Formation DesignOptimising Autonomous Robot Swarm Parameters for Stable Formation Design
Optimising Autonomous Robot Swarm Parameters for Stable Formation Design
 
Ocupación de Aparcamientos y Predicción
Ocupación de Aparcamientos y PredicciónOcupación de Aparcamientos y Predicción
Ocupación de Aparcamientos y Predicción
 
Bio-inspired Computing and Smart Mobility
Bio-inspired Computing and Smart MobilityBio-inspired Computing and Smart Mobility
Bio-inspired Computing and Smart Mobility
 
Computing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms
Computing New Optimized Routes for GPS Navigators Using Evolutionary AlgorithmsComputing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms
Computing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms
 
Predicting Car Park Occupancy Rates in Smart Cities
Predicting Car Park Occupancy Rates in Smart CitiesPredicting Car Park Occupancy Rates in Smart Cities
Predicting Car Park Occupancy Rates in Smart Cities
 
Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S...
Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S...Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S...
Fine Tuning of Traffic in Our Cities with Smart Panels: The Quito City Case S...
 
An Evolutionary Algorithm to Generate Real Urban Traffic Flows
An Evolutionary Algorithm to Generate Real Urban Traffic FlowsAn Evolutionary Algorithm to Generate Real Urban Traffic Flows
An Evolutionary Algorithm to Generate Real Urban Traffic Flows
 
Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel...
Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel...Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel...
Smart Mobility Policies with Evolutionary Algorithms: The Adapting Info Panel...
 
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...
Un Algoritmo Evolutivo para la Reducción de Tiempos de Viaje y Emisiones Util...
 
Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)
Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)
Eco-friendly Reduction of Travel Times in European Smart Cities (GECCO'14)
 
Reducing Gas Emissions in Smart Cities by Using the Red Swarm Architecture (C...
Reducing Gas Emissions in Smart Cities by Using the Red Swarm Architecture (C...Reducing Gas Emissions in Smart Cities by Using the Red Swarm Architecture (C...
Reducing Gas Emissions in Smart Cities by Using the Red Swarm Architecture (C...
 
Red Swarm: Smart Mobility in Cities with EAs (GECCO'13)
Red Swarm: Smart Mobility in Cities with EAs (GECCO'13)Red Swarm: Smart Mobility in Cities with EAs (GECCO'13)
Red Swarm: Smart Mobility in Cities with EAs (GECCO'13)
 

Recently uploaded

Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Sérgio Sacani
 
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
Lokesh Kothari
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
Areesha Ahmad
 

Recently uploaded (20)

Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
Vip profile Call Girls In Lonavala 9748763073 For Genuine Sex Service At Just...
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
American Type Culture Collection (ATCC).pptx
American Type Culture Collection (ATCC).pptxAmerican Type Culture Collection (ATCC).pptx
American Type Culture Collection (ATCC).pptx
 
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts ServiceJustdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
Justdial Call Girls In Indirapuram, Ghaziabad, 8800357707 Escorts Service
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
Clean In Place(CIP).pptx .
Clean In Place(CIP).pptx                 .Clean In Place(CIP).pptx                 .
Clean In Place(CIP).pptx .
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
 
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICESAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
 
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
 
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
Feature-aligned N-BEATS with Sinkhorn divergence (ICLR '24)
 

Improving Pheromone Communication for UAV Swarm Mobility Management

  • 1. University of Luxembourg Multilingual. Personalized. Connected. Improving Pheromone Communication for UAV Swarm Mobility Management Daniel H. Stolfi1 Matthias R. Brust1 Grégoire Danoy1,2 Pascal Bouvry1,2 13th International Conference on Computational Collective Intelligence – ICCCI 2021 September 29th – October 1st, 2021 1 SnT - Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg 2 FSTM/DCS, University of Luxembourg, Luxembourg
  • 2. TABLE OF CONTENTS 1 INTRODUCTION 2 PHEROMONE BASED MOBILITY 3 OPTIMISATION ALGORITHM 4 EXPERIMENTAL RESULTS AND CONCLUSIONS
  • 3. TABLE OF CONTENTS 1 INTRODUCTION 2 PHEROMONE BASED MOBILITY 3 OPTIMISATION ALGORITHM 4 EXPERIMENTAL RESULTS AND CONCLUSIONS 1/19
  • 4. UAV: UNMANNED AERIAL VEHICLE UAVs, also known as drones, can be fixed wings or multi-rotors. They are usually equipped with: I Video (infrared) cameras I Radio communication devices I Sensors (pollution, radiation, etc.) I Actuators Advantages I Explore different areas I High speed I Excellent communication capabilities Disadvantages I Reduced flight time I Cannot carry larger payloads Photo by Daniel H. Stolfi Source: indiamart.com 2/19
  • 5. UAV – APPLICATIONS UAVs are widely used in many applications: Goods transportation Road traffic surveillance Fire fighting Environmental monitoring Wildfire monitoring Farming Architecture surveillance Internet delivery Homeland security To herd a flock of birds away from an airport (!) Surveillance systems Source: procurious.com Photo by Tyler Casey on unsplash.com 3/19
  • 6. TABLE OF CONTENTS 1 INTRODUCTION 2 PHEROMONE BASED MOBILITY 3 OPTIMISATION ALGORITHM 4 EXPERIMENTAL RESULTS AND CONCLUSIONS 4/19
  • 7. SURVEILLANCE APPROACH Our approach to surveillance missions comprises: Multi-swarms of Unmanned Aerial Vehicles Unpredictable trajectories Maximising area coverage Maximising intruder detections Pheromone based mobility Mobility models analysed: CROMM (Chaotic Rössler Mobility Model) → Pure chaotic CACOC (Chaotic Ant Colony Optimisation for Coverage) → CROMM + Pheromones CACOC+ → Parameterised version of CACOC 5/19
  • 8. CROMM1 Pure chaotic mobility 1 M. Rosalie, G. Danoy, S. Chaumette, and P. Bouvry. “Chaos-enhanced mobility models for multilevel swarms of UAVs”. In: Swarm and Evol. Comput. 41.November 2017 (2018), pp. 36–48. 6/19
  • 9. CACOC MOBILITY MODEL2 Pheromone trails 2 M. Rosalie, G. Danoy, S. Chaumette, and P. Bouvry. “Chaos-enhanced mobility models for multilevel swarms of UAVs”. In: Swarm and Evol. Comput. 41.November 2017 (2018), pp. 36–48. 7/19
  • 10. CACOC+ MOBILITY MODEL3 TABLE: Parameters of CACOC+. Parameter Units Range Pheromone amount (τa) % [1 − 100] Pheromone radius (τr ) cells [0.5 − 2.5] Pheromone scan depth (τd ) cells [1 − 10] Each UAV in the swarm has to know about the pheromone trails in the neighbourhood 3 D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UAV Swarms”. In: 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC). IEEE, 2020, pp. 1–6. 8/19
  • 11. PHEROMONE SHARING (a) Full pheromone map (b) UAV1’s known map (c) UAV2’s known map FIGURE: Pheromone Sharing 9/19
  • 12. COMMUNICATION SCENARIOS Radio link subject to interferences Maximum communication range Shorter data packets could reduce. . . I packet loss probability I energy consumption Could we keep good coverage rates by optimising the parameters of CACOC+? FIGURE: Four scenarios simulated using ARGoS 10/19
  • 13. COMMUNICATION SCENARIOS Radio link subject to interferences Maximum communication range Shorter data packets could reduce. . . I packet loss probability I energy consumption Could we keep good coverage rates by optimising the parameters of CACOC+? FIGURE: Four scenarios simulated using ARGoS 10/19
  • 14. TABLE OF CONTENTS 1 INTRODUCTION 2 PHEROMONE BASED MOBILITY 3 OPTIMISATION ALGORITHM 4 EXPERIMENTAL RESULTS AND CONCLUSIONS 11/19
  • 15. OPTIMISATION ALGORITHM: GA GAs are efficient method for solving combinatorial optimisation problems Simulates processes present in evolution Operators: I Binary tournament I Uniform crossover I Mutation for integers values I Best individual in offspring replaces the worst individual in population Problem representation: Fitness function: ~ x = {τa1 , τr1 , τd1 , . . . , τaN , τrN , τdN } F(~ x) = # of explored cells # of cells in the scenario N ∈ {2, 4, 6} is the number of UAVs in the swarm 12/19
  • 16. EVALUATION: ARGOS SIMULATOR FIGURE: ARGoS Simulator Simulation of UAV’s dynamics Realistic communication layer 10-metre radio range Simulated packet loss rates 1000 evaluations per GA run 360 runs in total 10 equivalent days of computing time (reduced by parallel evaluations/runs) 13/19
  • 17. EVALUATION: ARGOS SIMULATOR FIGURE: ARGoS Simulator Simulation of UAV’s dynamics Realistic communication layer 10-metre radio range Simulated packet loss rates 1000 evaluations per GA run 360 runs in total 10 equivalent days of computing time (reduced by parallel evaluations/runs) 13/19
  • 18. TABLE OF CONTENTS 1 INTRODUCTION 2 PHEROMONE BASED MOBILITY 3 OPTIMISATION ALGORITHM 4 EXPERIMENTAL RESULTS AND CONCLUSIONS 14/19
  • 19. OPTIMISATION RESULTS Case Study Scenario Fitness Friedman Rank Wilcoxon p-value Avg. SD. Max. 2 UAVs CACOC+ 0.524 0.005 0.538 2.50 0.365 CACOC+.10 0.523 0.006 0.535 2.10 0.325 CACOC+.05 0.525 0.006 0.535 2.68 0.802 CACOC+.00 0.526 0.007 0.539 2.72 — 4 UAVs CACOC+ 0.769 0.006 0.780 2.28 0.087 CACOC+.10 0.771 0.007 0.788 2.70 0.640 CACOC+.05 0.769 0.005 0.782 2.22 0.120 CACOC+.00 0.772 0.006 0.786 2.80 — 6 UAVs CACOC+ 0.885 0.005 0.895 2.48 0.246 CACOC+.10 0.887 0.004 0.897 2.70 — CACOC+.05 0.885 0.004 0.893 2.52 0.133 CACOC+.00 0.884 0.006 0.896 2.30 0.058 Fitness values of each optimisation run for each case study and scenario. 15/19
  • 20. OPTIMISATION RESULTS Case Study Scenario Fitness Friedman Rank Wilcoxon p-value Avg. SD. Max. 2 UAVs CACOC+ 0.524 0.005 0.538 2.50 0.365 CACOC+.10 0.523 0.006 0.535 2.10 0.325 CACOC+.05 0.525 0.006 0.535 2.68 0.802 CACOC+.00 0.526 0.007 0.539 2.72 — 4 UAVs CACOC+ 0.769 0.006 0.780 2.28 0.087 CACOC+.10 0.771 0.007 0.788 2.70 0.640 CACOC+.05 0.769 0.005 0.782 2.22 0.120 CACOC+.00 0.772 0.006 0.786 2.80 — 6 UAVs CACOC+ 0.885 0.005 0.895 2.48 0.246 CACOC+.10 0.887 0.004 0.897 2.70 — CACOC+.05 0.885 0.004 0.893 2.52 0.133 CACOC+.00 0.884 0.006 0.896 2.30 0.058 Fitness values of each optimisation run for each case study and scenario. 15/19
  • 21. OPTIMISATION RESULTS Case Study 2 UAV 4 UAV 6 UAV CROMM 13.3% 43.5% 52.2% CACOC 46.5% 71.0% 85.8% CACOC.10 46.5% 68.7% 85.8% CACOC.05 46.5% 71.6% 84.2% CACOC.00 38.8% 70.2% 80.0% CACOC+ 53.8% 78.0% 89.5% CACOC+.10 53.5% 78.8% 89.7% CACOC+.05 53.5% 78.2% 89.3% CACOC+.00 53.9% 78.6% 89.6% Coverage values 16/19
  • 22. OPTIMISATION RESULTS Case Study 2 UAV 4 UAV 6 UAV CROMM 13.3% 43.5% 52.2% CACOC 46.5% 71.0% 85.8% CACOC.10 46.5% 68.7% 85.8% CACOC.05 46.5% 71.6% 84.2% CACOC.00 38.8% 70.2% 80.0% CACOC+ 53.8% 78.0% 89.5% CACOC+.10 53.5% 78.8% 89.7% CACOC+.05 53.5% 78.2% 89.3% CACOC+.00 53.9% 78.6% 89.6% Coverage values 16/19
  • 23. INTERFERENCES AND PACKET LOSS (a) 2 UAVs (b) 4 UAVs (c) 6 UAVs FIGURE: Area Coverage vs. Packet Loss Probability 17/19
  • 24. INTERFERENCES AND PACKET LOSS (a) 2 UAVs (b) 4 UAVs (c) 6 UAVs FIGURE: Area Coverage vs. Packet Loss Probability 17/19
  • 25. CONCLUSIONS AND FUTURE WORK Conclusions CACOC+ improved CACOC and CROMM in all scenarios CACOC+ adapted the UAVs’ behaviour to deal with an incomplete pheromone map CACOC performance degraded with the reduction of the transmitted data CROMM (pure chaotic) cannot compete with pheromone-based mobility Future Work Include more UAVs in the study Use a specific parameter for each UAV Alternative collision avoidance algorithm Validation of trajectories using real drones 18/19
  • 26. QUESTIONS? Daniel H. Stolfi daniel.stolfi@uni.lu https://hunted.gforge.uni.lu/ https://pcog.uni.lu/ https://wwwen.uni.lu/snt/ https://wwwen.uni.lu/ Improving Pheromone Communication for UAV Swarm Mobility Management Daniel H. Stolfi1, Matthias R. Brust1, Grégoire Danoy1,2, and Pascal Bouvry1,2 1 SnT - Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg 2 FSTM/DCS, University of Luxembourg, Luxembourg References: M. Rosalie, G. Danoy, S. Chaumette, and P. Bouvry. “Chaos-enhanced mobility models for multilevel swarms of UAVs”. In: Swarm and Evol. Comput. 41.November 2017 (2018), pp. 36–48 D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “A Cooperative Coevolutionary Approach to Maximise Surveillance Coverage of UAV Swarms”. In: 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC). IEEE, 2020, pp. 1–6 D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “Optimizing the Performance of an Unpredictable UAV Swarm for Intruder Detection”. In: Optimization and Learning. Cham: Springer International Publishing, 2020, pp. 37–48 D. H. Stolfi, M. R. Brust, G. Danoy, and P. Bouvry. “Competitive Evolution of a UAV Swarm for Improving Intruder Detection Rates”. In: 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, May 2020, pp. 528–535 This work relates to Department of Navy award N62909-18-1-2176 issued by the Office of Naval Research. The United States Government has a royalty-free license throughout the world in all copyrightable material contained herein. This work is partially funded by the joint research programme UL/SnT-ILNAS on Digital Trust for Smart-ICT. 19/19