CrowdSurfer: Sampling Optimization Augmented with Vector-Quantized Variational AutoEncoder for Dense Crowd Navigation

TL;DR

CrowdSurfer enhances dense crowd navigation for mobile robots by combining generative modeling with local plan optimization, achieving state-of-the-art success rates without dynamic obstacle prediction.

Contribution

The paper introduces a novel approach using Vector Quantized Variational AutoEncoder for trajectory prior learning and runtime optimization, improving crowd navigation performance.

Findings

40% success rate improvement over DRL-VO

6% reduction in travel time

State-of-the-art navigation performance

Abstract

Navigation amongst densely packed crowds remains a challenge for mobile robots. The complexity increases further if the environment layout changes, making the prior computed global plan infeasible. In this paper, we show that it is possible to dramatically enhance crowd navigation by just improving the local planner. Our approach combines generative modelling with inference time optimization to generate sophisticated long-horizon local plans at interactive rates. More specifically, we train a Vector Quantized Variational AutoEncoder to learn a prior over the expert trajectory distribution conditioned on the perception input. At run-time, this is used as an initialization for a sampling-based optimizer for further refinement. Our approach does not require any sophisticated prediction of dynamic obstacles and yet provides state-of-the-art performance. In particular, we compare against the recent DRL-VO approach and show a 40% improvement in success rate and a 6% improvement in travel time.