COROBOREES · COllective ROBOtics through Real-time Entrainment of Evolved dynamical Systems
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2021-09-01 → 2024-01-25
- EU contribution
- €202,159
- Participants
- 1
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
COllective ROBOtics through Real-time Entrainment of Evolved dynamical Systems
As intelligent animals, we make extensive use of social information at all cognitive levels, including the most basic. One striking example of this is that we unconsciously synchronize our walking, not only with musical rhythms, but also with each other. Such unconscious imitation means that at a basic level our sensorimotor systems are open to feedback not only from the physical environment, but also from the social environment. This has profoundly shaped how humans acquire behaviours, and hence how we learn and communicate in general. The robotics field has made great strides in sensorimotor control and learning using environmental feedback. This has included biologically-inspired use of central pattern generators (CPGs) modeled after spinal circuits, with many impressive examples of robust and flexible locomotion that emerge from interactions with the environment. Such “situated” robotics is often seen as a necessary condition for truly intelligent behaviour. However, low-level social feedback and learning have not received nearly the same level of focus, and have not been investigated in artificial CPGs. The novel research goal of the COROBOREES project was to develop robotic agents with socially adaptive CPGs that can overcome morphological differences and synchronize complex movement patterns. Achieving this goal can be seen as a significant step towards socially situated - and socially intelligent - robots. The project had two main objectives, each with its own work package devoted to it: 1. To develop and compare mechanisms for entrainment of CPG-based controllers to rhythmic acoustic signals. 2. To understand how sensorimotor control mechanisms affect the emergent outcome of multiple agents interacting.
Data: CORDIS, © European Union
Project objective
Socially interacting robots are widely envisioned to revolutionise learning and care, and as they become more ubiquitous, to perform tasks collaboratively. However, despite astounding progress in engineering adaptive capabilities in fundamental behaviours such as locomotion, social behaviour is still generally considered a separate 'add-on' component. COROBOREES will contribute to efforts to provide a bottom-up approach to social behaviour in automated systems. Combining methods from evolutionary robotics, collective behaviour and sound and music computing, the project will investigate ways to incorporate social information into the motion controllers of virtual agents, and to study how this can enable synchronisation of complex movement patterns. Specifically, the project will build on the central pattern generator (CPG) framework for robot motion. CPGs are widely used in robotic controllers for cyclic motions such as walking, and may include feedback mechanisms so that robots can adapt to new tasks and environments. Using evolutionary methods, COROBOREES will compare mechanisms for entrainment to rhythmic acoustic patterns as well as acoustically transmitted social cues. Methods from sound and music computing will be used to evaluate the complexity and synchronisation of the collective rhythms generated. In addition to the innovation within robotics, this work will result in a unique simulation platform for collective behaviour, complete with built-in sensorimotor mechanisms, for the use of researchers in artificial life, biology and neuroscience. The broadly applicable training-through-research nature of the action, the contact with numerous fields of research, as well as a tailored and extensive focus on transferable skills, will provide the Experienced Researcher with invaluable knowledge and experience for leading applied interdisciplinary research in the future.
Original text from CORDIS.
Participants
- UNIVERSITETET I OSLO · OsloCoordinatorNorway
Links
- View on CORDIS
- DOI: 10.3030/101030688
- https://www.uio.no/ritmo/english/projects/synchronized-robotics/index.html
Data: CORDIS, © European Union