Codes

Here you can find our codes:

 

  • Multi-objective analysis of Parkinson data

The codes for multi-objective analysis can be downloaded here. 

 

 

  • DrivingSwarm framework

To use the DrivingSwarm framework, go to https://github.com/ovgu-FINken/driving_swarm_infrastructure

If you use our framework, please use the following reference: Sebastian Mai, Nele Traichel and Sanaz Mostaghim, Driving Swarm: A Swarm Robotics Framework for Intelligent Navigation in a Self-organised World, International Conference on Robotics and Automation (ICRA), May 23-27, 2022, Philadelphia (PA), USA

 

  • Multi-Modal Multi-Objective Codes

You can have access to our codes from recent research: 

1) Related to Modified Crowding Distance and Mutation for Multimodal Multi-Objective Optimization and The effects of Crowding Distance and Mutation in Multimodal and Multi-objective Optimization Problems: 

  • Mahrokh Javadi, Heiner Zille and Sanaz Mostaghim
  • The effects of Crowding Distance and Mutation in Multimodal and Multi-objective Optimization Problems
  •  In: Gaspar-Cunha A., Periaux J., Giannakoglou K.C., Gauger N.R., Quagliarella D., Greiner D. (eds) Advances in Evolutionary and Deterministic Methods for Design, Optimization and Control in Engineering and Sciences. Computational Methods in Applied Sciences, vol 55. Springer, Cham., pp. 115-130, 2021 --> https://link.springer.com/chapter/10.1007/978-3-030-57422-2_8

Source Code: Download

 2) Related to the work in Javadi M, and Mostaghim S., Using neighbourhood-based Density Measures for Multimodal Multi-Objective Optimization, EMO 2021

Source Code: Download

 

  • Scalable Many-Objective Pathfinding Benchmark Suite

Jens Weise and Sanaz Mostaghim

The software creates instances of the proposed Many-Objective Pathfinding Benchmark Suite. Also, we provide true Pareto-fronts and sets. Download here.

 

  • Framework for modelling multi-objective multi-agent pathfinding with vehicle models

This algorithm is capable of optimizing a set of trajectories for multiple robots with multiple objectives. The output of the algorithm is a Pareto-front and the coressponding Pareto-set of plans for a given navigation scenario. In the framework we implemented three objectives: The mean path length, the mean travel time and the maximum risk for all agents. In addition, we defined serveral environments, which can be used for benchmarking the algorithm.

  • Sebastian Mai and Sanaz Mostaghim 
  • Modelling Pathfinding for Swarm Robotics
  • In: Dorigo M. et al. (eds) Swarm Intelligence. ANTS 2020. Lecture Notes in Computer Science, vol 12421. Springer, Cham. 2020. https://doi.org/10.1007/978-3-030-60376-2_15 

 The source code is available on github: https://github.com/ovgu-FINken/MOMAPF-VM

 

  • Weighted Optimization Framework (WOF):

This algorithm uses weight variables and problem transformation to tacke large-scale multi-objective optimisation problems. The code is written in Matlab for the PlatEMO framework version 2.5 (or newer). This is the latest version of WOF which implements several improvements compared to the original publication. It includes several transformation functions, grouping mechanisms and other parameters to choose. This version further enables you to choose the internal optimiser between NSGA-II, NSGA-III, SMPSO and MOEA/D. There is also a randomised version included. WOF is based on the following publications:

1) Heiner Zille, "Large-scale Multi-objective Optimisation: New Approaches and a Classification of the State-of-the-Art", PhD Thesis, Otto von Guericke University Magdeburg, 2019, http://dx.doi.org/10.25673/32063 (Download)

2) Heiner Zille and Sanaz Mostaghim, "Comparison Study of Large-scale Optimisation Techniques on the LSMOP Benchmark Functions", IEEE Symposium Series on Computational Intelligence (SSCI), IEEE, Honolulu, Hawaii, November 2017 --> Link to IEEE Xplore Digital Library  (Download)

3) Heiner Zille, Hisao Ishibuchi, Sanaz Mostaghim and Yusuke Nojima, "A Framework for Large-scale Multi-objective Optimization based on Problem Transformation", IEEE Transactions on Evolutionary Computation, Vol. 22, Issue 2, pp. 260-275, April 2018  --> Link to IEEE Xplore Digital Library (Download) (Supplement Material)

Source Codes: (Download) (Last Update: 6th April 2020)

 

  • Linear Search Mechanism for Multi- and Many-Objective Optimisation (LCSA):

This algorithm uses linear combination-based transformations of the search space for large-scale multi-objective optimisation. LCSA is based on the following publications:

1) Heiner Zille, "Large-scale Multi-objective Optimisation: New Approaches and a Classification of the State-of-the-Art", PhD Thesis, Otto von Guericke University Magdeburg, 2019, http://dx.doi.org/10.25673/32063 (Download)

2) Heiner Zille and Sanaz Mostaghim, "Linear Search Mechanism for Multi- and Many-Objective Optimisation", 10th International Conference on Evolutionary Multi-Criterion Optimization (EMO 2019), Lecture Notes in Computer Science, vol 11411. Deb K. et al. (eds), Springer, Cham, East Lansing, Michigan, USA, March 2019. https://doi.org/10.1007/978-3-030-12598-1_32  (Download)  

Source Codes: (Download) (Last Update: 6th April 2020)

 

  • Mutation Operators Based on Variable Grouping for Multi-objective Large-scale Optimization (GLMO):

This algorithm uses special mutation operators for large-scale multi-objective optimisation. The code is written in Matlab for the PlatEMO framework version 2.5 (or newer). GLMO is based on the following publications:

1) Heiner Zille, "Large-scale Multi-objective Optimisation: New Approaches and a Classification of the State-of-the-Art", PhD Thesis, Otto von Guericke University Magdeburg, 2019, http://dx.doi.org/10.25673/32063 (Download)

2) Heiner Zille, Hisao Ishibuchi, Sanaz Mostaghim and Yusuke Nojima, "Mutation Operators Based on Variable Grouping for Multi-objective Large-scale Optimization", IEEE Symposium Series on Computational Intelligence (SSCI), IEEE, Athens, Greece, December 2016, https://ieeexplore.ieee.org/document/7850214 (Download)

Source Codes: (Download) (Last Update: 6th April 2020)

 

  • Transfer Strategies from Single- to Multi-objective Grouping Mechanisms:

Paper: Frederick Sander, Heiner Zille and Sanaz Mostaghim Transfer Strategies from Single- to Multi-objective Grouping Mechanisms, In the Proceedings of the ACM Genetic and Evolutionary Computation Conference (GECCO), Pages 729-736, Kyoto, July 2018 --> Link

Downloads:
- Article
- Supplement Material
- Sourcecode written in Matlab 

 

  • Open Loop Search for General Video Game Playing

Paper: Diego Perez, Jens Dieskau, Martin Hünermund and Sanaz Mostaghim, Simon Lucas, Open Loop Search for General Video Game Playing, In Proceedings of ACM Genetic and Evolutioanry Computation Conference (GECCO 2015), Pages , July 2015 -> Link

Code: https://github.com/xaedes/open-loop-search-for-general-video-game-playing

 

  • Energy-Aware PSO:

Paper: Sanaz Mostaghim, Christoph Steup and Fabian Witt, Energy Aware Particle Swarm Optimization as Search Mechanism for Aerial Micro-robots, IEEE Swarm Intelligence Symposium, IEEE SSCI 2016, December 2016

Code: EA-PSO in MATALB

 

  • Visulaization for many-objective optimization 

Paper: Andy Pryke, Sanaz Mostaghim, Ali Reza Nazemi, Heatmap Visualisation of Population Based Multi Objective Algorithms, In S. Obayashi et al., Evolutionary Multi-Criterion Optimization, 4th International Conference, EMO 2007, Proceedings, pages: 361-375, Springer, LNCS, 4403, 2007

Code: VisPop in R

 

  • Multi-Objective Particle Swarm Optimization

Paper: Sanaz Mostaghim, Jürgen Teich, Strategies for finding good local guides in multi-objective particle swarm optimization, the Proceedings of IEEE Swarm Intelligence Symposium, Indianapolis, USA, April, 2003 -> Link

Code: MO-PSO in c++

 

  • Liquid Swarm: this is an executable file with very easy and user freindly interface to set up different swarms in various relations to each other. More information will be uploaded here. 

Code: LiquidSwarm.exe

 

 

Last Modification: 17.01.2024 - Contact Person: Webmaster