Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction

TL;DR

This paper introduces BOsampler, an unsupervised Bayesian optimization-based sampling method that enhances stochastic human trajectory prediction by better exploring long-tail paths without retraining existing models.

Contribution

The paper proposes a novel adaptive sampling method using Bayesian optimization to improve coverage of potential human trajectories in stochastic prediction models.

Findings

BOsampler effectively explores long-tail trajectory paths.

The method improves prediction diversity without retraining models.

Experimental results show enhanced coverage of realistic trajectories.

Abstract

The indeterminate nature of human motion requires trajectory prediction systems to use a probabilistic model to formulate the multi-modality phenomenon and infer a finite set of future trajectories. However, the inference processes of most existing methods rely on Monte Carlo random sampling, which is insufficient to cover the realistic paths with finite samples, due to the long tail effect of the predicted distribution. To promote the sampling process of stochastic prediction, we propose a novel method, called BOsampler, to adaptively mine potential paths with Bayesian optimization in an unsupervised manner, as a sequential design strategy in which new prediction is dependent on the previously drawn samples. Specifically, we model the trajectory sampling as a Gaussian process and construct an acquisition function to measure the potential sampling value. This acquisition function applies the original distribution as prior and encourages exploring paths in the long-tail region. This sampling method can be integrated with existing stochastic predictive models without retraining. Experimental results on various baseline methods demonstrate the effectiveness of our method.