Uncertainty-aware occupancy map prediction using generative networks for robot navigation

Kapil Katyal, Katie Popek, Chris Paxton, Philippe Burlina, Gregory Hager

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Efficient exploration through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion is often severely limited by sensor field of view (FOV). By contrast, biological systems routinely make decisions by taking into consideration what might exist beyond their FOV based on prior experience. We present an approach for predicting occupancy map representations of sensor data for future robot motions using deep neural networks. We develop a custom loss function used to make accurate prediction while emphasizing physical boundaries. We further study extensions to our neural network architecture to account for uncertainty and ambiguity inherent in mapping and exploration. Finally, we demonstrate a combined map prediction and information-theoretic exploration strategy using the variance of the generated hypotheses as the heuristic for efficient exploration of unknown environments.

Original languageEnglish (US)
Title of host publication2019 International Conference on Robotics and Automation, ICRA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5453-5459
Number of pages7
ISBN (Electronic)9781538660263
DOIs
StatePublished - May 1 2019
Event2019 International Conference on Robotics and Automation, ICRA 2019 - Montreal, Canada
Duration: May 20 2019May 24 2019

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
Volume2019-May
ISSN (Print)1050-4729

Conference

Conference2019 International Conference on Robotics and Automation, ICRA 2019
CountryCanada
CityMontreal
Period5/20/195/24/19

Fingerprint

Navigation
Robots
Sensors
Biological systems
Network architecture
Robotics
Neural networks
Uncertainty
Deep neural networks

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Katyal, K., Popek, K., Paxton, C., Burlina, P., & Hager, G. (2019). Uncertainty-aware occupancy map prediction using generative networks for robot navigation. In 2019 International Conference on Robotics and Automation, ICRA 2019 (pp. 5453-5459). [8793500] (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2019.8793500

Uncertainty-aware occupancy map prediction using generative networks for robot navigation. / Katyal, Kapil; Popek, Katie; Paxton, Chris; Burlina, Philippe; Hager, Gregory.

2019 International Conference on Robotics and Automation, ICRA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 5453-5459 8793500 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Katyal, K, Popek, K, Paxton, C, Burlina, P & Hager, G 2019, Uncertainty-aware occupancy map prediction using generative networks for robot navigation. in 2019 International Conference on Robotics and Automation, ICRA 2019., 8793500, Proceedings - IEEE International Conference on Robotics and Automation, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 5453-5459, 2019 International Conference on Robotics and Automation, ICRA 2019, Montreal, Canada, 5/20/19. https://doi.org/10.1109/ICRA.2019.8793500
Katyal K, Popek K, Paxton C, Burlina P, Hager G. Uncertainty-aware occupancy map prediction using generative networks for robot navigation. In 2019 International Conference on Robotics and Automation, ICRA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 5453-5459. 8793500. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2019.8793500
Katyal, Kapil ; Popek, Katie ; Paxton, Chris ; Burlina, Philippe ; Hager, Gregory. / Uncertainty-aware occupancy map prediction using generative networks for robot navigation. 2019 International Conference on Robotics and Automation, ICRA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 5453-5459 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{8aba7717c4394094affa6b5a54e4c9b1,
title = "Uncertainty-aware occupancy map prediction using generative networks for robot navigation",
abstract = "Efficient exploration through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion is often severely limited by sensor field of view (FOV). By contrast, biological systems routinely make decisions by taking into consideration what might exist beyond their FOV based on prior experience. We present an approach for predicting occupancy map representations of sensor data for future robot motions using deep neural networks. We develop a custom loss function used to make accurate prediction while emphasizing physical boundaries. We further study extensions to our neural network architecture to account for uncertainty and ambiguity inherent in mapping and exploration. Finally, we demonstrate a combined map prediction and information-theoretic exploration strategy using the variance of the generated hypotheses as the heuristic for efficient exploration of unknown environments.",
author = "Kapil Katyal and Katie Popek and Chris Paxton and Philippe Burlina and Gregory Hager",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICRA.2019.8793500",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5453--5459",
booktitle = "2019 International Conference on Robotics and Automation, ICRA 2019",

}

TY - GEN

T1 - Uncertainty-aware occupancy map prediction using generative networks for robot navigation

AU - Katyal, Kapil

AU - Popek, Katie

AU - Paxton, Chris

AU - Burlina, Philippe

AU - Hager, Gregory

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Efficient exploration through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion is often severely limited by sensor field of view (FOV). By contrast, biological systems routinely make decisions by taking into consideration what might exist beyond their FOV based on prior experience. We present an approach for predicting occupancy map representations of sensor data for future robot motions using deep neural networks. We develop a custom loss function used to make accurate prediction while emphasizing physical boundaries. We further study extensions to our neural network architecture to account for uncertainty and ambiguity inherent in mapping and exploration. Finally, we demonstrate a combined map prediction and information-theoretic exploration strategy using the variance of the generated hypotheses as the heuristic for efficient exploration of unknown environments.

AB - Efficient exploration through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion is often severely limited by sensor field of view (FOV). By contrast, biological systems routinely make decisions by taking into consideration what might exist beyond their FOV based on prior experience. We present an approach for predicting occupancy map representations of sensor data for future robot motions using deep neural networks. We develop a custom loss function used to make accurate prediction while emphasizing physical boundaries. We further study extensions to our neural network architecture to account for uncertainty and ambiguity inherent in mapping and exploration. Finally, we demonstrate a combined map prediction and information-theoretic exploration strategy using the variance of the generated hypotheses as the heuristic for efficient exploration of unknown environments.

UR - http://www.scopus.com/inward/record.url?scp=85071445180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071445180&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2019.8793500

DO - 10.1109/ICRA.2019.8793500

M3 - Conference contribution

AN - SCOPUS:85071445180

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 5453

EP - 5459

BT - 2019 International Conference on Robotics and Automation, ICRA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -