Predicting Energy Consumption of Ground Robots on Uneven Terrains

Minghan Wei, Volkan Isler

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

Optimizing energy consumption for robot navigation in fields requires energy-cost maps. However, obtaining such a map is still challenging, especially for large, uneven terrains. Physics-based energy models work for uniform, flat surfaces but do not generalize well to these terrains. Furthermore, slopes make the energy consumption at every location directional and add to the complexity of data collection and energy prediction. In this letter, we address these challenges in a data-driven manner. We consider a function which takes terrain geometry and robot motion direction as input and outputs expected energy consumption. The function is represented as a ResNet-based neural network whose parameters are learned from field-collected data. The prediction accuracy of our method is within 12% of the ground truth in our test environments that are unseen during training. We compare our method to a baseline method in the literature: a method using a basic physics-based model. We demonstrate that our method significantly outperforms it by more than 10% measured by the prediction error. More importantly, our method generalizes better when applied to test data from new environments with various slope angles and navigation directions.

Original languageEnglish (US)
Pages (from-to)594-601
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume7
Issue number1
DOIs
StatePublished - Jan 1 2022

Bibliographical note

Funding Information:
This work was supported by NSF under Grants 1525045, 1617718, 1849107, and MN State LCCMR program

Publisher Copyright:
IEEE

Keywords

  • Deep learning methods
  • Energy and environment-aware automation
  • Field robots

Fingerprint

Dive into the research topics of 'Predicting Energy Consumption of Ground Robots on Uneven Terrains'. Together they form a unique fingerprint.

Cite this