Navigating the Human Maze: Real-Time Robot Pathfinding with Generative Imitation Learning

TL;DR

This paper presents a real-time robot navigation method in crowded environments by combining goal-conditioned generative models with sampling-based predictive control, effectively predicting human behaviors and improving safety and efficiency.

Contribution

It introduces goal-conditioned autoregressive models for crowd behavior prediction integrated with SMPC, enabling proactive and dynamic robot navigation in complex, crowded scenarios.

Findings

Reduces collision rates significantly

Shortens path lengths compared to baselines

Validated on real robotic platform in dynamic settings

Abstract

This paper addresses navigation in crowded environments by integrating goal-conditioned generative models with Sampling-based Model Predictive Control (SMPC). We introduce goal-conditioned autoregressive models to generate crowd behaviors, capturing intricate interactions among individuals. The model processes potential robot trajectory samples and predicts the reactions of surrounding individuals, enabling proactive robotic navigation in complex scenarios. Extensive experiments show that this algorithm enables real-time navigation, significantly reducing collision rates and path lengths, and outperforming selected baseline methods. The practical effectiveness of this algorithm is validated on an actual robotic platform, demonstrating its capability in dynamic settings.