Peter Stone's Selected Publications

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


From Agile Ground to Aerial Navigation: Learning from Learned Hallucination

From Agile Ground to Aerial Navigation: Learning from Learned Hallucination.
Zizhao Wang, Xuesu Xiao, Alexander J Nettekoven, Kadhiravan Umasankar, Anika Singh, Sriram Bommakanti, Ufuk Topcu, and Peter Stone.
In Proceedings of the International Conference on Intelligent Robots and Systems (IROS 2021), October 2021.
1-minute Video Summary; 15-minute Video Presentation

Download

[PDF]2.9MB  [slides.pdf]2.7MB  

Abstract

This paper presents a self-supervised Learning from Learned Hallucination (LfLH) method to learn fast and reactive motion planners for ground and aerial robots to navigate through highly constrained environments. The recent Learning from Hallucination (LfH) paradigm for autonomous navigation executes motion plans by random exploration in completely safe obstacle-free spaces, uses hand-crafted hallucination techniques to add imaginary obstacles to the robot’s perception, and then learns motion planners to navigate in realistic, highly-constrained, dangerous spaces. However, current handcrafted hallucination techniques need to be tailored for specific robot types (e.g., a differential drive ground vehicle), and use approximations heavily dependent on certain assumptions (e.g., a short planning horizon). In this work, instead of manually designing hallucination functions, LfLH learns to hallucinate obstacle configurations, where the motion plans from random exploration in open space are optimal, in a self-supervised manner. LfLH is robust to different robot types and does not make assumptions about the planning horizon. Evaluated in both simulated and physical environments with a ground and an aerial robot, LfLH outperforms or performs comparably to previous hallucination approaches, along with sampling- and optimization-based classical methods.

BibTeX Entry

@InProceedings{iros21_lflh-wang,
  author = {Zizhao Wang and Xuesu Xiao and Alexander J Nettekoven and Kadhiravan Umasankar and Anika Singh and Sriram Bommakanti and Ufuk Topcu and Peter Stone},
  title = {From Agile Ground to Aerial Navigation: Learning from Learned Hallucination},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems (IROS 2021)},
  location = {Prague, Czech Republic},
  month = {October},
  year = {2021},
  abstract = {
  This paper presents a self-supervised Learning 
  from Learned Hallucination (LfLH) method to learn fast and 
  reactive motion planners for ground and aerial robots to 
  navigate through highly constrained environments. The recent 
  Learning from Hallucination (LfH) paradigm for autonomous 
  navigation executes motion plans by random exploration in 
  completely safe obstacle-free spaces, uses hand-crafted hallucination 
  techniques to add imaginary obstacles to the robot’s perception, 
  and then learns motion planners to navigate in realistic, 
  highly-constrained, dangerous spaces. However, current handcrafted 
  hallucination techniques need to be tailored for specific 
  robot types (e.g., a differential drive ground vehicle), and use 
  approximations heavily dependent on certain assumptions (e.g., 
  a short planning horizon). In this work, instead of manually 
  designing hallucination functions, LfLH learns to hallucinate 
  obstacle configurations, where the motion plans from random 
  exploration in open space are optimal, in a self-supervised 
  manner. LfLH is robust to different robot types and does not 
  make assumptions about the planning horizon. Evaluated in 
  both simulated and physical environments with a ground and 
  an aerial robot, LfLH outperforms or performs comparably to 
  previous hallucination approaches, along with sampling- and 
  optimization-based classical methods.
  },
  wwwnote={<a href="https://youtu.be/X1X8fWTjW0E">1-minute Video Summary</a>; 
  <a href="https://youtu.be/BaqkZ1Tw9-M">15-minute Video Presentation</a>},
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 17, 2021 22:18:59