Morphological symmetries in robot learning

Conference Article


RSS Workshop on Symmetries in Robot Learning (SYM)





Doc link


Download the digital copy of the doc pdf document


This work studies the impact of morphological symmetries in learning applications in robotics. Morphological symmetries are a predominant feature in both biological and robotic systems, arising from the presence of planes/axis of symmetry in the system’s morphology. This results in harmonious duplication and distribution of body parts (e.g., humans’ sagittal/left-right symmetry). Morphological symmetries become a significant learning prior as they extend to symmetries in the system’s dynamics, optimal control policies, and in all proprio- ceptive and exteroceptive measurements, related to the system’s dynamics evolution. Exploiting these symmetries in learning applications offers several advantageous outcomes, such as the use of data augmentation to mitigate the cost and challenges of data collection, or the use of equivariant/invariant function approximation models (e.g., neural networks) to improve sample efficiency and generalization, while reducing the number of trainable parameters. We provide an open access repository reproducing our experiments and allowing for rapid prototyping in robot learning applications exploiting morphological symmetries.


mathematical programming.

Author keywords

robot learning

Scientific reference

D.F. Ordoñez, M. Martin, A. Agudo and F. Moreno-Noguer. Morphological symmetries in robot learning, 2023 RSS Workshop on Symmetries in Robot Learning, 2023, Daegu (South Korea), pp. 1-5.