Learning to Navigate Sidewalks in Outdoor Environments
This addresses the challenge of outdoor navigation for assistive applications like last-mile delivery, but it is incremental as it builds on existing learning methods for robotics.
The paper tackled the problem of enabling a quadruped robot to navigate sidewalks in urban environments by developing a two-staged learning framework that trains a teacher agent with privileged information and transfers skills to a student agent with realistic sensors, resulting in the robot walking 3.2 kilometers with limited human interventions in real-world tests.
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.