Deploying SICNav in the Field: Safe and Interactive Crowd Navigation using MPC and Bilevel Optimization

TL;DR

This paper introduces SICNav, a bilevel MPC framework for safe, interactive crowd navigation that models human-robot interactions, demonstrated through real-world indoor and outdoor deployments.

Contribution

It presents a novel bilevel MPC approach integrating prediction and planning for crowd navigation, addressing limitations of prior decoupled methods.

Findings

Successfully navigated nearly 7 km in diverse environments

Demonstrated safe and interactive behavior in real-world scenarios

System operated over two hours in indoor and outdoor settings

Abstract

Safe and efficient navigation in crowded environments remains a critical challenge for robots that provide a variety of service tasks such as food delivery or autonomous wheelchair mobility. Classical robot crowd navigation methods decouple human motion prediction from robot motion planning, which neglects the closed-loop interactions between humans and robots. This lack of a model for human reactions to the robot plan (e.g. moving out of the way) can cause the robot to get stuck. Our proposed Safe and Interactive Crowd Navigation (SICNav) method is a bilevel Model Predictive Control (MPC) framework that combines prediction and planning into one optimization problem, explicitly modeling interactions among agents. In this paper, we present a systems overview of the crowd navigation platform we use to deploy SICNav in previously unseen indoor and outdoor environments. We provide a preliminary analysis of the system's operation over the course of nearly 7 km of autonomous navigation over two hours in both indoor and outdoor environments.