Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning

Le Chen, Yunke Ao, Florian Tschopp, Andrei Cramariuc, Michel Breyer, Jen Jen Chung, Roland Siegwart, Cesar Cadena
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:1312-1325, 2021.

Abstract

Visual-inertial systems rely on precise calibrations of both camera intrinsics and inter-sensor extrinsics, which typically require manually performing complex motions in front of a calibration target. In this work we present a novel approach to obtain favorable trajectories for visual-inertial system calibration, using model-based deep reinforcement learning. Our key contribution is to model the calibration process as a Markov decision process and then use model-based deep reinforcement learning with particle swarm optimization to establish a sequence of calibration trajectories to be performed by a robot arm. Our experiments show that while maintaining similar or shorter path lengths, the trajectories generated by our learned policy result in lower calibration errors compared to random or handcrafted trajectories. The code is publicly available.

Cite this Paper

BibTeX
@InProceedings{pmlr-v155-chen21c, title = {Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning}, author = {Chen, Le and Ao, Yunke and Tschopp, Florian and Cramariuc, Andrei and Breyer, Michel and Chung, Jen Jen and Siegwart, Roland and Cadena, Cesar}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {1312--1325}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/chen21c/chen21c.pdf}, url = {https://proceedings.mlr.press/v155/chen21c.html}, abstract = {Visual-inertial systems rely on precise calibrations of both camera intrinsics and inter-sensor extrinsics, which typically require manually performing complex motions in front of a calibration target. In this work we present a novel approach to obtain favorable trajectories for visual-inertial system calibration, using model-based deep reinforcement learning. Our key contribution is to model the calibration process as a Markov decision process and then use model-based deep reinforcement learning with particle swarm optimization to establish a sequence of calibration trajectories to be performed by a robot arm. Our experiments show that while maintaining similar or shorter path lengths, the trajectories generated by our learned policy result in lower calibration errors compared to random or handcrafted trajectories. The code is publicly available.} }
Endnote
%0 Conference Paper %T Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning %A Le Chen %A Yunke Ao %A Florian Tschopp %A Andrei Cramariuc %A Michel Breyer %A Jen Jen Chung %A Roland Siegwart %A Cesar Cadena %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-chen21c %I PMLR %P 1312--1325 %U https://proceedings.mlr.press/v155/chen21c.html %V 155 %X Visual-inertial systems rely on precise calibrations of both camera intrinsics and inter-sensor extrinsics, which typically require manually performing complex motions in front of a calibration target. In this work we present a novel approach to obtain favorable trajectories for visual-inertial system calibration, using model-based deep reinforcement learning. Our key contribution is to model the calibration process as a Markov decision process and then use model-based deep reinforcement learning with particle swarm optimization to establish a sequence of calibration trajectories to be performed by a robot arm. Our experiments show that while maintaining similar or shorter path lengths, the trajectories generated by our learned policy result in lower calibration errors compared to random or handcrafted trajectories. The code is publicly available.
APA
Chen, L., Ao, Y., Tschopp, F., Cramariuc, A., Breyer, M., Chung, J.J., Siegwart, R. & Cadena, C.. (2021). Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:1312-1325 Available from https://proceedings.mlr.press/v155/chen21c.html.

Related Material