Learning to Navigate Sidewalks in Outdoor Environments


Maks Sorokin1    Jie Tan2    C. Karen Liu3    Sehoon Ha1,2

1 Georgia Institute of Technology    2 Robotics at Google    3 Stanford University

Abstract

Outdoor navigation on sidewalks in urban environments is the key technology behind important human assistive applications, such as last-mile delivery or neighborhood patrol. This paper aims to develop a quadruped robot that follows a route plan generated by public map services, while remaining on sidewalks and avoiding collisions with obstacles and pedestrians. We devise a two-staged learning framework, which first trains a teacher agent in an abstract world with privileged ground-truth information, and then applies Behavior Cloning to teach the skills to a student agent who only has access to realistic sensors. The main research effort of this paper focuses on overcoming challenges when deploying the student policy on a quadruped robot in the real world. We propose methodologies for designing sensing modalities, network architectures, and training procedures to enable zero-shot policy transfer to unstructured and dynamic real outdoor environments. We evaluate our learning framework on a quadrupedal robot navigating sidewalks in the city of Atlanta, USA. Using the learned navigation policy and its onboard sensors, the robot is able to walk 3.2 kilometers with a limited number of human interventions.

Paper: [pdf]
Preprint: [arXiv]

Video overview

More Videos:

Speedrun

Obstacle Avoidance

Bibtex

@misc{sorokin2021learning,
  title={Learning to Navigate Sidewalks in Outdoor Environments}, 
  author={Maks Sorokin and Jie Tan and C. Karen Liu and Sehoon Ha},
  year={2021},
  eprint={2109.05603},
  archivePrefix={arXiv},
  primaryClass={cs.RO}
}