This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
|
teaching:mfe:ia [2016/03/14 15:58] mdorigo [Automatic fitness function definition in evolutionary robotics] |
teaching:mfe:ia [2016/03/14 16:01] mdorigo [Collective Decision Making with Heterogeneous Agents] |
||
|---|---|---|---|
| Line 263: | Line 263: | ||
| - | |||
| - | ===== Collective Decision Making with Heterogeneous Agents ===== | ||
| - | |||
| - | Swarm robotics is an interesting approach to the coordination of hundreds of robots as it promotes the realization of systems which are scalable, robust and flexible. | ||
| - | The master thesis will study how to provide a swarm system with the cognitive capability of collective decision making. | ||
| - | Each agent has partial knowledge of the available alternatives and of their quality estimate, however the swarm, as a whole, is able to decide for the best option. Recently, numerous works have studied strategies and algorithms to implement this process in distributed systems (often taking inspiration from biology, e.g., bees or cockroaches behaviour). One of the common characteristic of these works is that all the agents of the swarm has the same behaviour. In the Master Thesis project, the student will study how heterogeneity influences the global outcome. We will consider heterogeneity both in the individual behaviour (for instance, robots can estimate different option characteristics) and in the interaction network. | ||
| - | |||
| - | In practice, the student is supposed to (i) model the collective decision making problem | ||
| - | (ii) design and implement multi-agents simulations, and (iii) analyse and discuss the obtained | ||
| - | results. Depending on the student skills and preferences, the work can focus more on theoretical | ||
| - | aspects, thus favouring the modelling and analysis of the problem, or can be more practical, | ||
| - | thus centring the thesis on the multi-agent implementation part. Possibly, a more practical | ||
| - | thesis could result (depending on the student skills) in the implementation of a real world | ||
| - | demonstrator with a swarm of up to 100 robots. | ||
| - | |||
| - | * Contacts : [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo]] and Andreagiovanni Reina (IRIDIA) | ||
| Line 390: | Line 374: | ||
| - | ===== Evolution of Modular Controllers for Simulated and Real Robots ===== | + | ===== Design of a holonomic drive system ===== |
| - | The goal of this master thesis is investigating how modularity in a robot controller can influence the quality of the behaviours obtained through artificial evolution. | + | Unlike a differential drive system, a holonomic drive system has the advantage of being able to move in any direction at a given instant. The goal of this master thesis is to design and evaluate the performance of a holonomic drive system. The drive system will be assembled from a combination of off-the-shelf components and 3D printed parts. In order to evaluate the drive system, close loop controllers need to be designed and evaluated in C/C++. |
| - | Similarly to the nervous system that can be divided in central and peripheral, the project will study a modular architecture for neural network controllers. The peripheral modules encode the information coming from the sensory subsytems or going to the motor apparatus. The central system encodes the behavioural rules that map sensations to actions. The project will study methods to develop the peripheral modules by maximising the information transfer from the sensory input and to the motor output, on the basis of measures derived from Information Theory. | + | |
| - | The project will involve experimental activities with both simulated and real robots, and will investigate both individual and collective behaviours. | + | |
| - | Required skills: The candidates should be acquainted with C/C++ programming and have a working knowledge of the English language. | + | Required skills: The candidates should have some experience with programming in C/C++, and some experience with 3D modelling (preferably Solidworks). The candidates should be able to use basic kinematics to solve simple physics problems, and have a working knowledge of the English language. |
| - | * Contact: [[http://iridia.ulb.ac.be/~vtrianni|Vito Trianni]], Marco Dorigo (IRIDIA) | + | * Contact: [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo]] (IRIDIA) |