no code implementations • 14 Mar 2018 • Eivind Samuelsen, Kyrre Glette
In certain complex optimization tasks, it becomes necessary to use multiple measures to characterize the performance of different algorithms.
no code implementations • 6 Jan 2018 • Justinas Miseikis, Patrick Knobelreiter, Inka Brijacak, Saeed Yahyanejad, Kyrre Glette, Ole Jakob Elle, Jim Torresen
This can be the case when sensors and the robot are calibrated in relation to each other and often the reconfiguration of the system is not possible, or extra manual work is required.
no code implementations • 15 Mar 2018 • Tønnes F. Nygaard, Charles P. Martin, Jim Torresen, Kyrre Glette
This allows active adaptation of morphology to different environments, and enables rapid tests of morphology with a single robot.
Robotics
no code implementations • 21 Dec 2019 • Ulysse Côté-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark, Kyrre Glette, Erik Scheme, François Laviolette, Benoit Gosselin
Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines.
no code implementations • 30 Mar 2020 • Tønnes F. Nygaard, Charles P. Martin, David Howard, Jim Torresen, Kyrre Glette
We find that the evolutionary search finds high-performing and diverse morphology-controller configurations by adapting both control and body to the different properties of the physical environments.
no code implementations • 19 May 2020 • Jørgen Nordmoen, Tønnes Frostad Nygaard, Eivind Samuelsen, Kyrre Glette
Real-valued genotypes together with the variation operators, mutation and crossover, constitute some of the fundamental building blocks of Evolutionary Algorithms.
no code implementations • 11 Jul 2020 • Sondre A. Engebraaten, Jonas Moen, Oleg A. Yakimenko, Kyrre Glette
This repertoire would enable the swarm to transition between behavior trade-offs online, according to the situational requirements.
no code implementations • 5 Aug 2020 • Jørgen Nordmoen, Frank Veenstra, Kai Olav Ellefsen, Kyrre Glette
In this paper we compare a single objective Evolutionary Algorithm with two diversity promoting search algorithms; a Multi-Objective Evolutionary Algorithm and MAP-Elites a Quality Diversity algorithm, for the difficult problem of evolving control and morphology in modular robotics.
no code implementations • 3 May 2022 • Julian Fuhrer, Alejandro Blenkmann, Tor Endestad, Anne-Kristin Solbakk, Kyrre Glette
Here, we propose a method grounded in algorithmic information theory that affords direct statements about responses' similarity by estimating the encoded information through a compression-based scheme.
1 code implementation • 3 Jun 2022 • Alex Szorkovszky, Frank Veenstra, Kyrre Glette
Four CPGs, maximizing different weighted averages of the fitness functions, are then selected from the Pareto front and each is used as a basis for optimizing a filter network.
1 code implementation • 2 May 2023 • Emma Stensby Norstein, Kai Olav Ellefsen, Kyrre Glette
We want to move one step closer to creating simulated environments similar to the diverse real world, where agents can both find solvable tasks, and adapt to them.
1 code implementation • 30 May 2022 • Birk Torpmann-Hagen, Vajira Thambawita, Kyrre Glette, Pål Halvorsen, Michael A. Riegler
Generalizability is seen as one of the major challenges in deep learning, in particular in the domain of medical imaging, where a change of hospital or in imaging routines can lead to a complete failure of a model.
1 code implementation • 27 Jun 2022 • Mia-Katrin Kvalsund, Kyrre Glette, Frank Veenstra
Overall, if these findings translate to other robot systems, our results and issues encountered can help future researchers make a choice of control method when co-optimizing morphology and control.
1 code implementation • 7 Apr 2021 • Emma Hjellbrekke Stensby, Kai Olav Ellefsen, Kyrre Glette
We compare the diversity, fitness and robustness of agents evolving in environments generated by POET to agents evolved in handcrafted curricula of environments.
1 code implementation • 22 Apr 2024 • Jinyue Guo, Anna-Maria Christodoulou, Balint Laczko, Kyrre Glette
Evolutionary Algorithms and Generative Deep Learning have been two of the most powerful tools for sound generation tasks.
1 code implementation • 16 Dec 2019 • Ulysse Côté-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark, Kyrre Glette, Erik Scheme, François Laviolette, Benoit Gosselin
The ability of the dynamic dataset to serve as a benchmark is leveraged to evaluate the impact of different recalibration techniques for long-term (across-day) gesture recognition, including a novel algorithm, named TADANN.
4 code implementations • 10 Jan 2018 • Ulysse Côté-Allard, Cheikh Latyr Fall, Alexandre Drouin, Alexandre Campeau-Lecours, Clément Gosselin, Kyrre Glette, François Laviolette, Benoit Gosselin
Consequently, this paper proposes applying transfer learning on aggregated data from multiple users, while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets.