Autotuning Symbolic Optimization Fabrics for Trajectory Generation

Autotuning Symbolic Optimization Fabrics for Trajectory Generation

Spahn, M. (TU Delft Learning & Autonomous Control)
Alonso-Mora, J. (TU Delft Learning & Autonomous Control)

2023

In this paper, we present an automated parameter optimization method for trajectory generation. We formulate parameter optimization as a constrained optimization problem that can be effectively solved using Bayesian optimization. While the approach is generic to any trajectory generation method, we showcase it using optimization fabrics. Optimization fabrics are a geometric trajectory generation method based on non-Riemannian geometry. By symbolically pre-solving the structure of the tree of fabrics, we obtain a parameterized trajectory generator, called symbolic fabrics. We show that autotuned symbolic fabrics reach expert-level performance in a few trials. Additionally, we show that tuning transfers across different robots, motion planning problems and between simulation and real world. Finally, we qualitatively showcase that the framework could be used for coupled mobile manipulation.

http://resolver.tudelft.nl/uuid:1712d436-ac4c-4183-b7e9-882151a2aad8

https://doi.org/10.1109/ICRA48891.2023.10160458

IEEE

2024-01-04

979-8-3503-2365-8

Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2023)

ICRA 2023: International Conference on Robotics and Automation, 2023-05-29 → 2023-06-02, London, United Kingdom

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2023 M. Spahn, J. Alonso-Mora