Accelerating Trajectory Generation for Quadrotors Using Transformers

Srinath Tankasala, Mitch Pryor
Proceedings of The 5th Annual Learning for Dynamics and Control Conference, PMLR 211:600-611, 2023.

Abstract

In this work, we address the problem of computation time for trajectory generation in quadrotors. Most trajectory generation methods for waypoint navigation of quadrotors, for example minimum snap/jerk and minimum-time, are structured as bi-level optimizations. The first level involves allocating time across all input waypoints and the second step is to minimize the snap/jerk of the trajectory under that time allocation. Such an optimization can be computationally expensive to solve. In our approach we treat trajectory generation as a supervised learning problem between a sequential set of inputs and outputs. We adapt a transformer model to learn the optimal time allocations for a given set of input waypoints, thus making it into a single step optimization. We demonstrate the performance of the transformer model by training it to predict the time allocations for a minimum snap trajectory generator. The trained transformer model is able to predict accurate time allocations with fewer data samples and smaller model size, compared to a feedforward network (FFN), demonstrating that it is able to model the sequential nature of the waypoint navigation problem.

Cite this Paper

BibTeX
@InProceedings{pmlr-v211-tankasala23a, title = {Accelerating Trajectory Generation for Quadrotors Using Transformers}, author = {Tankasala, Srinath and Pryor, Mitch}, booktitle = {Proceedings of The 5th Annual Learning for Dynamics and Control Conference}, pages = {600--611}, year = {2023}, editor = {Matni, Nikolai and Morari, Manfred and Pappas, George J.}, volume = {211}, series = {Proceedings of Machine Learning Research}, month = {15--16 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v211/tankasala23a/tankasala23a.pdf}, url = {https://proceedings.mlr.press/v211/tankasala23a.html}, abstract = { In this work, we address the problem of computation time for trajectory generation in quadrotors. Most trajectory generation methods for waypoint navigation of quadrotors, for example minimum snap/jerk and minimum-time, are structured as bi-level optimizations. The first level involves allocating time across all input waypoints and the second step is to minimize the snap/jerk of the trajectory under that time allocation. Such an optimization can be computationally expensive to solve. In our approach we treat trajectory generation as a supervised learning problem between a sequential set of inputs and outputs. We adapt a transformer model to learn the optimal time allocations for a given set of input waypoints, thus making it into a single step optimization. We demonstrate the performance of the transformer model by training it to predict the time allocations for a minimum snap trajectory generator. The trained transformer model is able to predict accurate time allocations with fewer data samples and smaller model size, compared to a feedforward network (FFN), demonstrating that it is able to model the sequential nature of the waypoint navigation problem.} }
Endnote
%0 Conference Paper %T Accelerating Trajectory Generation for Quadrotors Using Transformers %A Srinath Tankasala %A Mitch Pryor %B Proceedings of The 5th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2023 %E Nikolai Matni %E Manfred Morari %E George J. Pappas %F pmlr-v211-tankasala23a %I PMLR %P 600--611 %U https://proceedings.mlr.press/v211/tankasala23a.html %V 211 %X In this work, we address the problem of computation time for trajectory generation in quadrotors. Most trajectory generation methods for waypoint navigation of quadrotors, for example minimum snap/jerk and minimum-time, are structured as bi-level optimizations. The first level involves allocating time across all input waypoints and the second step is to minimize the snap/jerk of the trajectory under that time allocation. Such an optimization can be computationally expensive to solve. In our approach we treat trajectory generation as a supervised learning problem between a sequential set of inputs and outputs. We adapt a transformer model to learn the optimal time allocations for a given set of input waypoints, thus making it into a single step optimization. We demonstrate the performance of the transformer model by training it to predict the time allocations for a minimum snap trajectory generator. The trained transformer model is able to predict accurate time allocations with fewer data samples and smaller model size, compared to a feedforward network (FFN), demonstrating that it is able to model the sequential nature of the waypoint navigation problem.
APA
Tankasala, S. & Pryor, M.. (2023). Accelerating Trajectory Generation for Quadrotors Using Transformers. Proceedings of The 5th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 211:600-611 Available from https://proceedings.mlr.press/v211/tankasala23a.html.

Related Material