Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain

Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain.
Xuesu Xiao, Joydeep Biswas, and Peter Stone.
IEEE Robotics and Automation Letters (RA-L), July 2021.
Contains material that was previously presented in an ICRA21 workshop paper Video

Download

[PDF]3.2MB  [slides.pdf]23.2MB  

Abstract

This paper presents a learning-based approach to consider the effect of unobservable world states in kinodynamic motion planning in order to enable accurate high-speed off- road navigation on unstructured terrain. Existing kinodynamic motion planners either operate in structured and homogeneous environments and thus do not need to explicitly account for terrain-vehicle interaction, or assume a set of discrete terrain classes. However, when operating on unstructured terrain, espe- cially at high speeds, even small variations in the environment will be magnified and cause inaccurate plan execution. In this paper, to capture the complex kinodynamic model and mathematically unknown world state, we learn a kinodynamic planner in a data-driven manner with onboard inertial observations. Our approach is tested on a physical robot in different indoor and outdoor environments, enables fast and accurate off-road navigation, and outperforms environment-independent alternatives, demonstrating 52.4 percent to 86.9 percent improvement in terms of plan execution success rate while traveling at high speeds.

BibTeX Entry

@article{ral21-xiaoa,
  title={Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain},
  author={Xuesu Xiao and Joydeep Biswas and Peter Stone},
  journal={IEEE Robotics and Automation Letters (RA-L)},
  abstract={This paper presents a learning-based approach to consider the effect of unobservable world states in kinodynamic motion planning in order to enable accurate high-speed off- road navigation on unstructured terrain. Existing kinodynamic motion planners either operate in structured and homogeneous environments and thus do not need to explicitly account for terrain-vehicle interaction, or assume a set of discrete terrain classes. However, when operating on unstructured terrain, espe- cially at high speeds, even small variations in the environment will be magnified and cause inaccurate plan execution. In this paper, to capture the complex kinodynamic model and mathematically unknown world state, we learn a kinodynamic planner in a data-driven manner with onboard inertial observations. Our approach is tested on a physical robot in different indoor and outdoor environments, enables fast and accurate off-road navigation, and outperforms environment-independent alternatives, demonstrating 52.4 percent to 86.9 percent improvement in terms of plan execution success rate while traveling at high speeds.
},
  year={2021},
  month={July},
  wwwnote={Contains material that was previously presented in an ICRA21 workshop paper <a href="https://www.youtube.com/watch?v=KwxP3apb38A">Video</a>}
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 17, 2021 22:18:57