Detailed Programme

Evolutionary Robotics

The EvoROBOT track focusses on evolutionary robotics: the application of evolutionary computation techniques to automatically design the controllers and/or hardware of autonomous robots, real or simulated. This is by nature a multi-faceted field that combines approaches from other fields such as neuro-evolution, evolutionary design, artificial life, robotics, et cetera.

We seek high quality contributions dealing with state-of-the-art research in the area of evolutionary robotics.

Topics include but are not limited to:


Accepted papers will appear in the proceedings of EvoStar, published in a volume of the Springer Lecture Notes in Computer Science, which will be available at the Conference.Submissions must be original and not published elsewhere. The submissions will be peer reviewed by at least three members of the program committee. The authors of accepted papers will have to improve their paper on the basis of the reviewers comments and will be asked to send a camera ready version of their manuscripts. At least one author of each accepted work has to register for the conference and attend the conference and present the work.The reviewing process will be double-blind, please omit information about the authors in the submitted paper.

Submission Details

Submissions must be original and not published elsewhere. They will be peer reviewed by members of the program committee. The reviewing process will be double-blind, so please omit information about the authors in the submitted paper.

Submit your manuscript in Springer LNCS format.

Please provide up to five keywords in your Abstract

Page limit: 12 pages to http://myreview.csregistry.org/evoapps14/.


Submission deadline: 1 November 2013 11 November 2013
Notification: 06 January 2014
Camera ready: 01 February 2014
EvoROBOT: 23-25 April 2014


Further information on the conference and co-located events can be
found in: http://www.evostar.org

Programme Committee

EvoROBOT Programme

Thurs 0930-1110 EvoROBOT & EvoHOT
Chair: Giovanni Squillero
Speeding up Online Evolution of Robotic Controllers with Macro-neurons     Fernando Silva, Luís Correia, Anders Christensen
In this paper, we introduce a novel approach to the online evolution of robotic controllers. We propose accelerating and scaling online evolution to more complex tasks by giving the evolutionary process direct access to behavioural building blocks prespecified in the neural architecture as \emph{macro-neurons}. During task execution, both the structure and the parameters of macro-neurons and of the entire neural network are under evolutionary control. We perform a series of simulation-based experiments in which an e-puck-like robot must learn to solve a deceptive and dynamic phototaxis task with three light sources. We show that: (i) evolution is able to progressively \emph{complexify} controllers by using the behavioural building blocks as a substrate, (ii) macro-neurons, either evolved or preprogrammed, enable a significant reduction in the adaptation time and the synthesis of high performing solutions, and (iii) evolution is able to inhibit the execution of detrimental task-unrelated behaviours and adapt non-optimised macro-neurons.

HyperNEAT versus RL PoWER for Online Gait Learning in Modular Robots   Massimiliano D'Angelo, Berend Weel, A.E. Eiben 
This paper addresses a principal problem of in vivo evolution of modular multi-cellular robots, where robot `babies' can be produced with arbitrary shapes and sizes. In such a system we need a generic learning mechanism that enables newborn morphologies to obtain a suitable gait quickly after `birth'. In this study we investigate and compare the reinforcement learning method RL PoWeR with HyperNEAT. We conduct simulation experiments using robot morphologies with different size and complexity. The experiments give insights into the differences in solution quality and algorithm efficiency, suggesting that reinforcement learning is the preferred option for this online learning problem.

Diagnostic Test Generation for Statistical Bug Localization using Evolutionary Computation     Marco Gaudesi, Maksim Jenihhin, Jaan Raik, Ernesto Sanchez, Giovanni Squillero, Valentin Tihomirov, Raimund Ubar
Verification is increasingly becoming a bottleneck in the process of designing electronic circuits. While there exists a wide range of verification tools that assist in detecting occurrences of design errors, or bugs, there is a lack of solutions for accurately pin-pointing the root causes of these errors. Statistical bug localization has proven to be an approach that scales up to large designs and is widely utilized both in debugging hardware and software. However, the accuracy of statistical localization is highly dependent on the diagnostic quality of the test stimuli. In this paper we formulate diagnostic test set generation as a task for an evolutionary algorithm and propose dedicated fitness functions that closely correlate with the bug localization capabilities of statistical approaches. We perform experiments on the register-transfer level design of the Plasma microprocessor implementing µGP (MicroGP) for evolutionary test pattern generation and the zamiaCAD tool’s bug localization infrastructure for fitness evaluation. As a result, the diagnostic resolution of the tests is significantly improved.