Lecture notes and reading material
Preliminary lecture notes will be available in PDF format before the class (usually Monday evening) while definitive lecture notes will be available only after the class has been held, in a timely fashion (usually, at latest a couple of days after the lecture).
Lecture notes will be complemented by possible reading material listed on the syllabus and further pointers, all available on the student area. Due to copyright issues, electronic copies of the material are only available to EPFL students officially enrolled in this course. Students interested in downloading this material can do so from the student area by logging in using with their GASPAR account.
Week 1
TOPIC
Course organization (credits, workload, logistics) and content overview. Introduction to Swarm Intelligence (SI) and key principles, natural and artificial examples. Foraging, trail laying/following mechanisms. Open-space, multi-source foraging experiments: biological data and microscopic models. From real to virtual ants: Ant System (AS), the first combinatorial optimization algorithm based on ant trail/following principles. Application to a classical operational research problem: the Traveling Salesperson Problem (TSP).
READING
Primary Literature:
- Bonabeau E., Dorigo M., and Theraulaz G., âSwarm Intelligence: From Natural to Artificial Systemsâ, SantaFe Studies in the Sciences of Complexity, Oxford University Press, 1999, Ch. 1 (pp.1-23) and Ch. 2 (pp. 25-36 and 39-56).
Secondary Literature:
- Martinoli A., âCollective Complexity out of Individual Simplicityâ. Invited book review on âSwarm Intelligence: From Natural to Artificial Systemsâ, by Bonabeau E., Dorigo M., and Theraulaz G. Artificial Life, Vol. 7, No. 3, pp. 315-319, 2001.
- Beni G., âFrom Swarm Intelligence to Swarm Roboticsâ. In Ćahin E. and Spears W., editors, Proc. of the SAB 2004 Workshop on Swarm Robotics, Santa Monica, CA, USA, July, 2004. Lecture Notes in Computer Science (2005), Vol. 3342, pp. 1-9.
Week 2
TOPIC
From AS to Ant Colony Optimization (ACO). Ant-based algorithms (ABC, Ant-Net) applied to routing in telecommunication networks.
READING
Primary:
- Bonabeau E., Dorigo M., and Theraulaz G., âSwarm Intelligence: From Natural to Artificial Systemsâ, Santa Fe Studies in the Sciences of Complexity, Oxford University Press, 1999, Ch. 2 (pp. 80-107).
Secondary:
- Dorigo M. and Stuetzle T., âAnt Colony Optimizationâ, MIT Press, 2004, Ch. 2 (pp. 25-46).
Week 3
TOPIC
Introduction to mobile robotics: basic concepts centered around the differential drive vehicle used in the course (e-puck) and the high-fidelity, open-source robotic simulator (Webots). Introduction to control architecture for mobile robots with special focus on reactive control architectures.
READING
Primary:
- Michel O., âWebots: Professional Mobile Robot Simulationâ. Int. J. of Advanced Robotic Systems, 1: 39-42, 2004.
- Mondada F., Bonani M., Raemy X., Pugh J., Cianci C., Klaptocz A., Magnenat S., Zufferey J.-C., Floreano D., Martinoli A., âThe e-puck, a Robot Designed for Education in Engineeringâ. Proc. of the 9th Conference on Autonomous Robot Systems and Competitions, May 2009, Castelo Branco, Portugal, Vol.1, pp. 59-65.
- Siegwart R. and Nourbakhsh I. R., âIntroduction to Autonomous Mobile Robotsâ, MIT Press, 2004, Ch. 4 (pp. 89-98).
Secondary:
- Brooks R., âA Robust Layered Control System for a Mobile Robotâ. IEEE Trans. on Robotics and Automation, 2(1): 14-23, 1986.
- Arkin R. C., âMotor Schema Based Mobile Robot Navigationâ. Int. J. of Robotics Research, 8(4): 92-112, 1989.
Week 4
TOPIC
Localization methods in mobile robotics: positioning systems, odometry-based and feature-based localization. Sources of localization uncertainties and corresponding handling methods for mobile robots.
READING
- Siegwart R. and Nourbakhsh I. R., âIntroduction to Autonomous Mobile Robotsâ, MIT Press, 2004, Ch. 3 (pp. 47-53), Ch. 4 (pp. 145-154).
Week 5
TOPIC
Localization methods in mobile robotics: uncertainties in wheel-based odometry, Kalman filters for 2D localization. Collective movements in natural societies; focus on flocking phenomena. Collective movements in artificial systems: Reynolds’ virtual agents (Boids).
READING
- Siegwart R. and Nourbakhsh I. R., âIntroduction to Autonomous Mobile Robotsâ, MIT Press, 2004, Ch. 5 (pp. 181-200).
- Maybeck P. S. âStochastic Models, Estimation, and Controlâ, Academic press, 1979, Ch. 1 (pp.1-16).
- Reynolds C. W. âFlocks, Herds, and Schools: A Distributed Behavioral Model, in Computer Graphicsâ, Proc. of SIGGRAPH ’87, 21(4), pp. 25-34, 1987.
Secondary:
- Siegwart R. and Nourbakhsh I. R., âIntroduction to Autonomous Mobile Robotsâ, MIT Press, 2004, Ch. 5 (212-214; 227-244).
Week 6
TOPIC
Experiments with multi-robot systems on flocking and formation (behavior-based). Graph-based distributed control for spatial consensus (rendez-vous, formation).
READING
Primary:
- Fredslund J. and MatariÄ M. J., “A General, Local Algorithm for Robot Formations”, IEEE Transactions on Robotics and Automation,, special issue on Advances in Multi-Robot Systems, Vol. 18, p.5, pp. 837-846, 2002.
- Gowal S., âA Framework for Graph-Based Distributed Rendezvous of Nonholonomic Multi-Robot Systemsâ, EPFL Thesis no. 5845, Ch. 6 and 7 (pp. 49-60), 2013.
- Falconi R., Gowal S., and Martinoli A., âGraph-Based Distributed Control of Non-Holonomic Vehicles Endowed with Local Positioning Information Engaged in Escorting Missionsâ. Proc. of the 2010 IEEE Int. Conf. on Robotics and Automation, May 2010, Anchorage, AK, U.S.A., pp. 3207-3214.
Secondary
- Balch T. and Arkin T. C., âBehavior-Based Formation Control for Multirobot Teamsâ. IEEE Trans. on Robotics and Automation, 1998, Vol. 14, No. 6, pp. 926-939.
- Pugh J., Raemy X., Favre C., Falconi R., and Martinoli A., âA Fast On-Board Relative Positioning Module for Multi-Robot Systemsâ. Special issue on Mechatronics in Multi-Robot Systems, Chow M.-Y., Chiaverini S., Kitts C., editors, IEEE Trans. on Mechatronics, 14(2): 151-162, 2009.
- Ren W., Beard R. W., and Atkins E. M., âA Survey of Consensus Problems in Multi-Agent Coordinationâ, Proc. of the 2005 American Control conference, pp. 1859-1864, 2005.
Week 7
TOPIC
Introduction to multi-level modeling techniques (underlying methodological framework, levels, assumptions, principles); linear example; calibration of model parameters.
Primary
- Lerman K., Martinoli A., and Galstyan A., âA Review of Probabilistic Macroscopic Models for Swarm Robotic Systemsâ. In Sahin E. and Spears W., editors, Proc. of the SAB 2004 Workshop on Swarm Robotics, July 2004, Santa Monica, CA, USA. Lecture Notes in Computer Science (2005), Vol. 3342, pp. 143-152.
- Martinoli A., Easton K., and Agassounon W., âModeling of Swarm Robotic Systems: A Case Study in Collaborative Distributed Manipulationâ. Special Issue on Experimental Robotics, Siciliano B., editor, Int. Journal of Robotics Research, Vol. 23, No. 4, pp. 415-436, 2004.
Secondary
- Correll N. and Martinoli A., âCollective Inspection of Regular Structures using a Swarm of Miniature Robotsâ. In Ang Jr., M.H. and Khatib, O., editors, Proc. of the Ninth Int. Symp. Experimental Robotics, June 2004, Singapore. Springer Tracts in Advanced Robotics (2006), Vol. 21, pp. 375â385.
Week 8
TOPIC
Challenging multi-level modeling case studies (distributed seed assembly and collaborative stick-pulling). Combined modeling and machine-learning methods for control optimization; diversity and specialization metrics.
Primary
- Agassounon W., Martinoli A., and Easton K., âMacroscopic Modeling of Aggregation Experiments using Embodied Agents in Teams of Constant and Time-Varying Sizesâ. Autonomous Robots, special issue on Swarm Robotics, Dorigo M. and Sahin E., editors, 17(2-3): 163-192, 2004.
- Li L., Martinoli A., and Abu-Mostafa Y., âLearning and Measuring Specialization in Collaborative Swarm Systemsâ. Special issue on Mathematics and Algorithms of Social Insects, Balch T. and Anderson C., editors, Adaptive Behavior, 12, No. 3-4, pp. 199-212, 2004.
Secondary
- Martinoli A., Ijspeert A. J., and Gambardella L. M., âA Probabilistic Model for Understanding and Comparing Collective Aggregation Mechanismsâ. In Floreano D., Mondada F., and Nicoud J.-D., editors, of the Fifth Europ. Conf. on Artificial Life, September 1999, Lausanne, Switzerland. Lectures Notes in Artificial Intelligence (1999), Vol. 1674, pp. 575â584.
Week 9
TOPIC
Introduction to machine-learning techniques and metaheuristic optimization: terminology and classification. Particle Swarm Optimization (PSO): algorithm and performances on benchmark functions. Application of metaheuristic methods to automatic control design and optimization of single-robot systems.
Primary
- Eberhart R. C. and Kennedy J., âA New Optimizer using Particle Swarm Theoryâ. of the Sixth IEEE Int. Symp. Micro Machine and Human Science, Nagoya, Japan, 1995, pp. 39â43.
- Shi, Y. H., Eberhart, R. C. âA Modified Particle Swarm Optimizerâ of the IEEE International Conference on Evolutionary Computation, Anchorage, Alaska, May 1998, pp. 69-73.
- Poli R., Kennedy J., and Blackwell T., âParticle Swarm Optimization: An Overviewâ. Swarm Intelligence Journal, 1(1): 33-57, 2007.
- Pugh J., Zhang Y., and Martinoli A., âParticle Swarm Optimization for Unsupervised Robotic Learningâ. of the Second IEEE Symp. on Swarm Intelligence, Pasadena, CA, USA, June 2005, pp. 92-99.
- Engelbrecht A. P., âParticle Swarm Optimization: Where Does it Belong?â of the Third IEEE Symp. on Swarm Intelligence, Indianapolis, IN, USA, May 2006, pp. 48-54.
Secondary
- Floreano D. and Mondada F., âEvolution of Homing Navigation in a Real Mobile Robotâ, IEEE Trans. on System, Man, and Cybernetics: Part B, 26(3): 396-407, 1996.
- Lipson, H., Pollack J. B., âAutomatic Design and Manufacture of Artificial Lifeformsâ, Nature, 406: 974-978, 2000.
- Bongard J., Zykov V., Lipson H. (2006), âResilient Machines Through Continuous Self-Modelingâ, Science 314. no. 5802, pp. 1118 â 1121.
Week 10
TOPIC
Noisy and expensive optimization problems; noise-resistant algorithms. Application of machine-learning techniques to automatic control design and optimization of multi-robot systems. Specific issues for automatic control design and optimization in distributed systems (e.g., credit assignment problem).
Primary
- Pugh J. and Martinoli A., âDistributed Scalable Multi-Robot Learning using Particle Swarm Optimizationâ. Swarm Intelligence Journal, 3(3): 203-222, 2009.
- Di Mario E. and Martinoli A., âDistributed Particle Swarm Optimization for Limited Time Adaptation with Real Robotsâ. Chirikjian G. and Hsieh A., editors, Special issue on Distributed Robotics, Robotica, 32(2): 193-208,
- Di Mario E., Navarro I., and Martinoli A., âAnalysis of Fitness Noise in Particle Swarm Optimization: From Robotic Learning to Benchmark Functionsâ. of the 2014 IEEE Congress on Evolutionary Computation, July 2014, Beijing, China, pp. 2785-2792.
- Di Mario E., Navarro I., and Martinoli A., âA Distributed Noise-Resistant Particle Swarm Optimization Algorithm for High-Dimensional Multi-Robot Learningâ, of the 2015 IEEE International Conference on Robotics and Automation, May 2015, pp. 5970â5976.
Secondary
- C. Chen, J. Lin, E. YĂŒcesan, and S. E. Chick, âSimulation Budget Allocation for Further Enhancing the Efficiency of Ordinal Optimization,â Discrete Event Dynamic Systems: Theory and Applications, pp. 251â270, 2000.
- Di Mario E., Navarro I., and Martinoli A., âDistributed Particle Swarm Optimization using Optimal Computing Budget Allocation for Multi-Robot Learning,â in IEEE Congress on Evolutionary Computation, 2015, pp. 566â572.
Week 11
TOPIC
Division of labor and task-allocation mechanisms: threshold-based algorithms and market-based algorithms; comparison between threshold-based and market-based algorithms.
READING
Primary
- Stentz A., Dias M. B., âA free market architecture for coordinating multiple robotsâ. Technical report CMU-RI-TR-99-42, Robotics Institute, Carnegie Mellon University, December 1999.
- Bonabeau E., Dorigo M., and Theraulaz G., âSwarm Intelligence: From Natural to Artificial Systemsâ, SantaFe Studies in the Sciences of Complexity, Oxford University Press, 1999, pp. 109-139 (Chapter 3).
- Kalra N. and Martinoli A., âA Comparative Study between Threshold-Based and Market-Based Task Allocationâ. Proc. of the Eight Int. Symp. on Distributed Autonomous Robotic Systems, July 2006, Minneapolis/St. Paul, MN, U.S.A. Distributed Autonomous Robotic Systems 7 (2006), pp. 91â102.
Secondary
- Dias M. B., Zlot R., Kalra N., and Stentz A., âMarket-Based Multirobot Coordination: A Survey and Analysisâ. IEEE Proceedings, 94(7): 1257-1270, 2006.
- Agassounon W. and Martinoli A., âEfficiency and Robustness of Threshold-Based Distributed Allocation Algorithms in Multi-Agent Systemsâ. of the First ACM Int. Joint Conf. on Autonomous Agents and Multi-Agent Systems, July 2002, Bologna, Italy, pp. 1090â1097.
Week 12
TOPIC
Division of labor and task-allocation mechanisms (continuation).
READING
Same as Week 11
Week 13
TOPIC
Distributed environmental sensing using static wireless sensor networks.
READING
Primary
- Culler D., Estrin D., and Srivastava M., âGuest Editors’ Introduction: Overview of Sensor Networksâ. IEEE Computer, Vol. 37, No. 8, pp.41-49, 2004.
- Barrenetxea G., Ingelrest F., Schaefer G. and Vetterli M., âThe Hitchhiker’s Guide to Successful Wireless Sensor Network Deploymentsâ. Proc. of the 6th ACM Conference on Embedded Networked Sensor Systems (SenSys 2008). Raleigh, NC, USA, 5-7 November 2008.
- Prorok A., Cianci C. M., and Martinoli A., âTowards Optimally Efficient Field Estimation with Threshold-Based Pruning in Real Robotic Sensor Networksâ. Proc. of the 2010 IEEE Int. Conf. on Robotics and Automation, May 2010, Anchorage, AK, U.S.A, pp. 5453-5459.
- Evans W. C., Bahr A., and Martinoli A., âEvaluating Efficient Data Collection Algorithms for Environmental Sensor Networksâ. Proc. of the Tenth Int. Symp. on Distributed Autonomous Robotic Systems, November 2010, Lausanne, Switzerland; Springer Tracts in Advanced Robotics (2013), Vol. 83, pp. 77-90.
Secondary
- Evans W. C., Bahr A., and Martinoli A., âDistributed Spatiotemporal Suppression for Environmental Data Collection in Real-World Sensor Networksâ. of the 2013 IEEE Int. Conf. on Distributed Computing in Sensor Systems, May 2013, Boston, U.S.A., pp. 70-79.
Week 14
TOPIC
Distributed environmental sensing using robotic sensor networks. General take home messages of the course. Discussion about student feedback for the course.
READING
Primary
- Marjovi A., Arfire A., and Martinoli A., âExtending Urban Air Pollution Maps beyond the Coverage of a Mobile Sensor Network: Data Sources, Methods, and Performance Evaluation,â Proc. of the Int. Conf. on Embedded Wireless Systems and Networks, February 2017, Uppsala, Sweden, pp. 12-23.
- Arfire A., Marjovi A., and Martinoli A., âMitigating slow dynamics of low-cost chemical sensors for mobile air quality monitoring sensor networks,â Proc. of the Int. Conf. on Embedded Wireless Systems and Networks, February 2016, Graz, Austria, pp. 159-167.