Learning Social Navigation from Demonstrations with Conditional Neural Processes

TL;DR

This paper introduces a data-driven social navigation system for robots using Conditional Neural Processes, enabling adaptive, norm-compliant navigation with fewer personal-zone violations in diverse environments.

Contribution

The novel approach employs Conditional Neural Processes to learn navigation controllers from observations, integrating reactive mechanisms for safety in unfamiliar situations.

Findings

Successfully navigates social environments respecting norms

Reduces personal-zone violations compared to baseline methods

Adapts to diverse social settings with learned controllers

Abstract

Sociability is essential for modern robots to increase their acceptability in human environments. Traditional techniques use manually engineered utility functions inspired by observing pedestrian behaviors to achieve social navigation. However, social aspects of navigation are diverse, changing across different types of environments, societies, and population densities, making it unrealistic to use hand-crafted techniques in each domain. This paper presents a data-driven navigation architecture that uses state-of-the-art neural architectures, namely Conditional Neural Processes, to learn global and local controllers of the mobile robot from observations. Additionally, we leverage a state-of-the-art, deep prediction mechanism to detect situations not similar to the trained ones, where reactive controllers step in to ensure safe navigation. Our results demonstrate that the proposed framework can successfully carry out navigation tasks regarding social norms in the data. Further, we showed that our system produces fewer personal-zone violations, causing less discomfort.