Safe Autonomous Navigation for Systems with Learned SE(3) Hamiltonian Dynamics

Zhichao Li, Thai Duong, Nikolay Atanasov
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:981-993, 2022.

Abstract

Safe autonomous navigation in unknown environments is an important problem for mobile robots. This paper proposes techniques to learn the dynamics model of a mobile robot from trajectory data and synthesize a tracking controller with safety and stability guarantees. The state of a rigid-body robot usually contains its position, orientation, and generalized velocity and satisfies Hamilton’s equations of motion. Instead of a hand-derived dynamics model, we use a dataset of state-control trajectories to train a translation-equivariant nonlinear Hamiltonian model represented as a neural ordinary differential equation (ODE) network. The learned Hamiltonian model is used to synthesize an energy-shaping passivity-based controller and derive conditions which guarantee safe regulation to a desired reference pose. We enable adaptive tracking of a desired path, subject to safety constraints obtained from obstacle distance measurements. The trade-off between the robot’s energy and the distance to safety constraint violation is used to adaptively govern a reference pose along the desired path. Our safe adaptive controller is demonstrated on a simulated hexarotor robot navigating in an unknown environments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v168-li22b, title = {Safe Autonomous Navigation for Systems with Learned SE(3) Hamiltonian Dynamics}, author = {Li, Zhichao and Duong, Thai and Atanasov, Nikolay}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {981--993}, 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/li22b/li22b.pdf}, url = {https://proceedings.mlr.press/v168/li22b.html}, abstract = {Safe autonomous navigation in unknown environments is an important problem for mobile robots. This paper proposes techniques to learn the dynamics model of a mobile robot from trajectory data and synthesize a tracking controller with safety and stability guarantees. The state of a rigid-body robot usually contains its position, orientation, and generalized velocity and satisfies Hamilton’s equations of motion. Instead of a hand-derived dynamics model, we use a dataset of state-control trajectories to train a translation-equivariant nonlinear Hamiltonian model represented as a neural ordinary differential equation (ODE) network. The learned Hamiltonian model is used to synthesize an energy-shaping passivity-based controller and derive conditions which guarantee safe regulation to a desired reference pose. We enable adaptive tracking of a desired path, subject to safety constraints obtained from obstacle distance measurements. The trade-off between the robot’s energy and the distance to safety constraint violation is used to adaptively govern a reference pose along the desired path. Our safe adaptive controller is demonstrated on a simulated hexarotor robot navigating in an unknown environments.} }
Endnote
%0 Conference Paper %T Safe Autonomous Navigation for Systems with Learned SE(3) Hamiltonian Dynamics %A Zhichao Li %A Thai Duong %A Nikolay Atanasov %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-li22b %I PMLR %P 981--993 %U https://proceedings.mlr.press/v168/li22b.html %V 168 %X Safe autonomous navigation in unknown environments is an important problem for mobile robots. This paper proposes techniques to learn the dynamics model of a mobile robot from trajectory data and synthesize a tracking controller with safety and stability guarantees. The state of a rigid-body robot usually contains its position, orientation, and generalized velocity and satisfies Hamilton’s equations of motion. Instead of a hand-derived dynamics model, we use a dataset of state-control trajectories to train a translation-equivariant nonlinear Hamiltonian model represented as a neural ordinary differential equation (ODE) network. The learned Hamiltonian model is used to synthesize an energy-shaping passivity-based controller and derive conditions which guarantee safe regulation to a desired reference pose. We enable adaptive tracking of a desired path, subject to safety constraints obtained from obstacle distance measurements. The trade-off between the robot’s energy and the distance to safety constraint violation is used to adaptively govern a reference pose along the desired path. Our safe adaptive controller is demonstrated on a simulated hexarotor robot navigating in an unknown environments.
APA
Li, Z., Duong, T. & Atanasov, N.. (2022). Safe Autonomous Navigation for Systems with Learned SE(3) Hamiltonian Dynamics. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:981-993 Available from https://proceedings.mlr.press/v168/li22b.html.

Related Material