TPAD: Identifying Effective Trajectory Predictions Under the Guidance of Trajectory Anomaly Detection Model

TL;DR

This paper introduces TPAD, a novel evaluation method for trajectory prediction models that uses anomaly detection to identify high-quality predictions, enhancing their practical utility.

Contribution

The paper proposes a new trajectory evaluation approach combining AutoML and anomaly detection to assess and select rational predictions from stochastic models.

Findings

TPAD effectively identifies near-optimal trajectories.

Improves the practical application of stochastic trajectory prediction models.

Demonstrates superior performance in experimental evaluations.

Abstract

Trajectory Prediction (TP) is an important research topic in computer vision and robotics fields. Recently, many stochastic TP models have been proposed to deal with this problem and have achieved better performance than the traditional models with deterministic trajectory outputs. However, these stochastic models can generate a number of future trajectories with different qualities. They are lack of self-evaluation ability, that is, to examine the rationality of their prediction results, thus failing to guide users to identify high-quality ones from their candidate results. This hinders them from playing their best in real applications. In this paper, we make up for this defect and propose TPAD, a novel TP evaluation method based on the trajectory Anomaly Detection (AD) technique. In TPAD, we firstly combine the Automated Machine Learning (AutoML) technique and the experience in the AD and TP field to automatically design an effective trajectory AD model. Then, we utilize the learned trajectory AD model to examine the rationality of the predicted trajectories, and screen out good TP results for users. Extensive experimental results demonstrate that TPAD can effectively identify near-optimal prediction results, improving stochastic TP models' practical application effect.