Peter Stone's Selected Publications

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


Agile Robot Navigation through Hallucinated Learning and Sober Deployment

Xuesu Xiao, Bo Liu, and Peter Stone. Agile Robot Navigation through Hallucinated Learning and Sober Deployment. In Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA 2021), June 2021.
Video

Download

[PDF]3.1MB  

Abstract

Learning from Hallucination (LfH) is a recent machine learning paradigm for autonomous navigation, which uses training data collected in completely safe environments and adds numerous imaginary obstacles to make the environment densely constrained, to learn navigation planners that produce feasible navigation even in highly constrained (more dangerous) spaces. However, LfH requires hallucinating the robot perception during deployment to match with the hallucinated training data, which creates a need for sometimes-infeasible prior knowledge and tends to generate very conservative planning. In this work, we propose a new LfH paradigm that does not require runtime hallucination---a feature we call ``sober deployment"---and can therefore adapt to more realistic navigation scenarios. This novel Hallucinated Learning and Sober Deployment (HLSD) paradigm is tested in a benchmark testbed of 300 simulated navigation environments with a wide range of difficulty levels, and in the real-world. In most cases, HLSD outperforms both the original LfH method and a classical navigation planner.

BibTeX Entry

@inproceedings{icra21-xiao,
  title={Agile Robot Navigation through Hallucinated Learning and Sober Deployment},
  author={Xuesu Xiao and Bo Liu and Peter Stone},
  booktitle={Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA 2021)},
  abstract={Learning from Hallucination (LfH) is a recent machine learning paradigm for autonomous navigation, which uses training data collected in completely safe environments and adds numerous imaginary obstacles to make the environment densely constrained, to learn navigation planners that produce feasible navigation even in highly constrained (more dangerous) spaces. However, LfH requires hallucinating the robot perception during deployment to match with the hallucinated training data, which creates a need for sometimes-infeasible prior knowledge and tends to generate very conservative planning. In this work, we propose a new LfH paradigm that does not require runtime hallucination---a feature we call ``sober deployment"---and can therefore adapt to more realistic navigation scenarios. This novel Hallucinated Learning and Sober Deployment (HLSD) paradigm is tested in a benchmark testbed of 300 simulated navigation environments with a wide range of difficulty levels, and in the real-world. In most cases, HLSD outperforms both the original LfH method and a classical navigation planner. 
},
  location={Xi'an, China},
  year={2021},
  month={June},
  wwwnote={<a href="https://www.youtube.com/watch?v=LZcBN9zgtXg&t=30s">Video</a>}
}

Generated by bib2html.pl (written by Patrick Riley ) on Fri Jun 18, 2021 14:00:31