This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision | Next revision Both sides next revision | ||
|
teaching:mfe:ia [2016/03/11 11:46] stuetzle [Optimising Ant Colony Algorithms for Performance] |
teaching:mfe:ia [2016/03/14 15:58] mdorigo [Automatic fitness function definition in evolutionary robotics] |
||
|---|---|---|---|
| Line 381: | Line 381: | ||
| - | ===== Automatic fitness function definition in evolutionary robotics ===== | + | ===== Development of remote monitoring software for intelligent structures ===== |
| - | Evolutionary robotics is a fascinating approach to the design of robot controllers that takes inspiration from natural evolution. | + | S-blocks are dynamically reconfigurable blocks used for autonomous construction applications. When two or more S-blocks are assembled they are capable of communicating with each other over a near field communication (NFC) wireless interface. The goal of this master thesis is to develop software to monitor (and control) the blocks in an intelligent structure remotely over the auxiliary Zigbee-based wireless interface. As only one block in the structure is fitted with this wireless interface, it is required that the other blocks communicate with the PC, via routing messages through the block-to-block NFC interfaces. This will require the software on the S-Blocks to be enhanced to use preemptive task swapping, to allow multiple blocks to communicate with each other simultaneously. |
| - | In order to obtain a robot that is able to perform a desired task, the evolutionary robotics approach considers a population of robots that evolves in time. Each robot is characterized by a genotype that defines somehow its behavior. Each robot is evaluated according to a fitness function that measures the ability of the robot to perform the desired task. Robots with a low fitness are eliminated. Robots with a high fitness remain in the population and generate offsprings -- e.g., robots with a similar genotype obtained via mutation and/or cross-over. Through this process, generation by generation, the evolutionary robotics approach is able to obtain robots that present higher and higher fitness and that are therefore able to perform the desired task more and more effectively. | + | Required skills: The candidates should understand low level computer concepts such as: interrupts, timers, and registers, have some experience with C/C++ programming, and have a working knowledge of the English language. |
| - | + | ||
| - | One of the main open problems in evolutionary robotics is that the definition of an appropriate fitness function is a very complex, labor-intensive, and time-consuming activity that requires the attention of an expert researcher. | + | |
| - | + | ||
| - | The goal of this master thesis is to devise an automatic method to define a fitness function in order to obtain a robot that is able to perform a desired task. This automatic method will be based on machine learning and metaheuristic algorithms. In particular, it will draw ideas from the fields of reinforcement learning and of on-line adaptation of parameters in optimization algorithms. | + | |
| - | + | ||
| - | Required skills: The candidates should be acquainted with C/C++ programming and have a working knowledge of the English language. | + | |
| - | * Contact: [[http://iridia.ulb.ac.be/~mbiro|Mauro Birattari]], Marco Dorigo, Vito Trianni (IRIDIA) | + | * Contact: [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo]] (IRIDIA) |