Diffeomorphic Transforms for Generalised Imitation Learning

Weiming Zhi, Tin Lai, Lionel Ott, Fabio Ramos
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:508-519, 2022.

Abstract

We address the generalised imitation learning problem of producing robot motions to imitate expert demonstrations, while adapting to novel environments. Past studies have often focused on methods that closely mimic demonstrations. However, to operate reliably in novel environments, robots should be able to adapt their learned motions accordingly. Motivated by this, we devise a framework capable of learning a time-invariant dynamical system to imitate demonstrations, and generalise to account for changes to the surroundings. To ensure the system is robust to perturbations, we need to maintain its stability. Our framework enforces stability in a principled manner: we start with a known stable system and use differentiable bijections (diffeomorphisms) to morph the system into the desired target system. We modularise robot motion and develop diffeomorphic transforms to encode individual actions. A composition of transforms produces generalised behaviour that complies with multiple requirements, such as mimicking demonstrations while avoiding obstacles. We evaluate our framework in both simulation and on a real-world 6-DOF JACO manipulator. Results show our framework is capable of producing a stable system that is collision-free and incorporates user-specified biases, while closely resembling demonstrations.

Cite this Paper


BibTeX
@InProceedings{pmlr-v168-zhi22a, title = {Diffeomorphic Transforms for Generalised Imitation Learning}, author = {Zhi, Weiming and Lai, Tin and Ott, Lionel and Ramos, Fabio}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {508--519}, year = {2022}, editor = {Firoozi, Roya and Mehr, Negar and Yel, Esen and Antonova, Rika and Bohg, Jeannette and Schwager, Mac and Kochenderfer, Mykel}, volume = {168}, series = {Proceedings of Machine Learning Research}, month = {23--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v168/zhi22a/zhi22a.pdf}, url = {https://proceedings.mlr.press/v168/zhi22a.html}, abstract = {We address the generalised imitation learning problem of producing robot motions to imitate expert demonstrations, while adapting to novel environments. Past studies have often focused on methods that closely mimic demonstrations. However, to operate reliably in novel environments, robots should be able to adapt their learned motions accordingly. Motivated by this, we devise a framework capable of learning a time-invariant dynamical system to imitate demonstrations, and generalise to account for changes to the surroundings. To ensure the system is robust to perturbations, we need to maintain its stability. Our framework enforces stability in a principled manner: we start with a known stable system and use differentiable bijections (diffeomorphisms) to morph the system into the desired target system. We modularise robot motion and develop diffeomorphic transforms to encode individual actions. A composition of transforms produces generalised behaviour that complies with multiple requirements, such as mimicking demonstrations while avoiding obstacles. We evaluate our framework in both simulation and on a real-world 6-DOF JACO manipulator. Results show our framework is capable of producing a stable system that is collision-free and incorporates user-specified biases, while closely resembling demonstrations.} }
Endnote
%0 Conference Paper %T Diffeomorphic Transforms for Generalised Imitation Learning %A Weiming Zhi %A Tin Lai %A Lionel Ott %A Fabio Ramos %B Proceedings of The 4th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2022 %E Roya Firoozi %E Negar Mehr %E Esen Yel %E Rika Antonova %E Jeannette Bohg %E Mac Schwager %E Mykel Kochenderfer %F pmlr-v168-zhi22a %I PMLR %P 508--519 %U https://proceedings.mlr.press/v168/zhi22a.html %V 168 %X We address the generalised imitation learning problem of producing robot motions to imitate expert demonstrations, while adapting to novel environments. Past studies have often focused on methods that closely mimic demonstrations. However, to operate reliably in novel environments, robots should be able to adapt their learned motions accordingly. Motivated by this, we devise a framework capable of learning a time-invariant dynamical system to imitate demonstrations, and generalise to account for changes to the surroundings. To ensure the system is robust to perturbations, we need to maintain its stability. Our framework enforces stability in a principled manner: we start with a known stable system and use differentiable bijections (diffeomorphisms) to morph the system into the desired target system. We modularise robot motion and develop diffeomorphic transforms to encode individual actions. A composition of transforms produces generalised behaviour that complies with multiple requirements, such as mimicking demonstrations while avoiding obstacles. We evaluate our framework in both simulation and on a real-world 6-DOF JACO manipulator. Results show our framework is capable of producing a stable system that is collision-free and incorporates user-specified biases, while closely resembling demonstrations.
APA
Zhi, W., Lai, T., Ott, L. & Ramos, F.. (2022). Diffeomorphic Transforms for Generalised Imitation Learning. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:508-519 Available from https://proceedings.mlr.press/v168/zhi22a.html.

Related Material