Combining Optimal Control and Learning for Visual Navigation in Novel Environments

Somil Bansal, Varun Tolani, Saurabh Gupta, Jitendra Malik, Claire Tomlin
; Proceedings of the Conference on Robot Learning, PMLR 100:420-429, 2020.

Abstract

Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the environment is a priori unknown and can only be observed partially through onboard sensors on the robot. In this work, we address this short-coming by coupling model-based control with learning-based perception. The learning-based perception module produces a series of waypoints that guide the robot to the goal via a collision-free path. These waypoints are used by a model-based planner to generate a smooth and dynamically feasible trajectory that is executed on the physical system using feedback control. Our experiments in simulated real-world cluttered environments and on an actual ground vehicle demonstrate that the proposed approach can reach goal locations more reliably and efficiently in novel environments as compared to purely geometric mapping-based or end-to-end learning-based alternatives. Our approach does not rely on detailed explicit 3D maps of the environment, works well with low frame rates, and generalizes well from simulation to the real world. Videos describing our approach and experiments are available on the project website4.

Cite this Paper


BibTeX
@InProceedings{pmlr-v100-bansal20a, title = {Combining Optimal Control and Learning for Visual Navigation in Novel Environments}, author = {Bansal, Somil and Tolani, Varun and Gupta, Saurabh and Malik, Jitendra and Tomlin, Claire}, pages = {420--429}, year = {2020}, editor = {Leslie Pack Kaelbling and Danica Kragic and Komei Sugiura}, volume = {100}, series = {Proceedings of Machine Learning Research}, address = {}, month = {30 Oct--01 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v100/bansal20a/bansal20a.pdf}, url = {http://proceedings.mlr.press/v100/bansal20a.html}, abstract = {Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the environment is a priori unknown and can only be observed partially through onboard sensors on the robot. In this work, we address this short-coming by coupling model-based control with learning-based perception. The learning-based perception module produces a series of waypoints that guide the robot to the goal via a collision-free path. These waypoints are used by a model-based planner to generate a smooth and dynamically feasible trajectory that is executed on the physical system using feedback control. Our experiments in simulated real-world cluttered environments and on an actual ground vehicle demonstrate that the proposed approach can reach goal locations more reliably and efficiently in novel environments as compared to purely geometric mapping-based or end-to-end learning-based alternatives. Our approach does not rely on detailed explicit 3D maps of the environment, works well with low frame rates, and generalizes well from simulation to the real world. Videos describing our approach and experiments are available on the project website4.} }
Endnote
%0 Conference Paper %T Combining Optimal Control and Learning for Visual Navigation in Novel Environments %A Somil Bansal %A Varun Tolani %A Saurabh Gupta %A Jitendra Malik %A Claire Tomlin %B Proceedings of the Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2020 %E Leslie Pack Kaelbling %E Danica Kragic %E Komei Sugiura %F pmlr-v100-bansal20a %I PMLR %J Proceedings of Machine Learning Research %P 420--429 %U http://proceedings.mlr.press %V 100 %W PMLR %X Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the environment is a priori unknown and can only be observed partially through onboard sensors on the robot. In this work, we address this short-coming by coupling model-based control with learning-based perception. The learning-based perception module produces a series of waypoints that guide the robot to the goal via a collision-free path. These waypoints are used by a model-based planner to generate a smooth and dynamically feasible trajectory that is executed on the physical system using feedback control. Our experiments in simulated real-world cluttered environments and on an actual ground vehicle demonstrate that the proposed approach can reach goal locations more reliably and efficiently in novel environments as compared to purely geometric mapping-based or end-to-end learning-based alternatives. Our approach does not rely on detailed explicit 3D maps of the environment, works well with low frame rates, and generalizes well from simulation to the real world. Videos describing our approach and experiments are available on the project website4.
APA
Bansal, S., Tolani, V., Gupta, S., Malik, J. & Tomlin, C.. (2020). Combining Optimal Control and Learning for Visual Navigation in Novel Environments. Proceedings of the Conference on Robot Learning, in PMLR 100:420-429

Related Material