Robotics group team selected for finalists in the 1st Prize of the “2019 International High School Competition for Brain-Inspired Computing” in China.” 1st Prize”
University of Minho team of graduate students –Weronika Wojtak, Flora Ferreira and Paulo Vicente – PhD Programs in Mathematics and Electronic Engineering and Computers – is among the teams selected for the 2019 International Collegiate Competition 1st Prize for Brain-inspired Computing ‘in China — http://contest.cbicr.org/en/ .
The work is in the area of Cognitive Neuroscience Inspired Robotics, with the theme “Learning Sequences with Time Constraints” and is carried out in partnership by the CMAT and ALGORITMI Centers, with the students being guided by Professors Wolfram Erlhagen (CMAT) and Estela Bicho (ALGORITMI).
200 teams competed. Results can be found here http://contest.cbicr.org/en/index.php?catid=4
The ability to gain sensitivity to ordinal and temporal regularities in many of our sequential activities is critical to our adaptive behavior in an inherently dynamic environment. In this context, we present a neuro-computational model, based on Dynamic Neuronal Fields, that implements neuroplausable processing mechanisms that support efficient acquisition and flexible reproduction of time-constrained complex sequences – What to do? And When to do ?. The model was tested on different real-world robotics experiments – e.g. learning a musical sequence, learning joint representations and learning object construction sequences. First, the robot acquires knowledge about the ordinal and temporal aspects of sequential tasks in a demonstration learning paradigm – with few demonstrations – and then remembers memory information, taking into account potential speed constraints. Providing robots with the ability to efficiently learn complex sequences with time constraints greatly improves the smoothness and fluency of human-robot interactions.