An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark

TL;DR

This paper evaluates various deep neural network models for pedestrian trajectory prediction on the TrajNet benchmark, highlighting the effectiveness of the RED-predictor and analyzing failure cases to improve future approaches.

Contribution

It provides a comparative analysis of deep neural networks for trajectory prediction and introduces the RED-predictor as a competitive model on the TrajNet benchmark.

Findings

RED-predictor achieves strong results compared to complex models

Analysis of failure cases offers insights for future improvements

Recommendations are provided to address observed shortcomings

Abstract

In recent years, there is a shift from modeling the tracking problem based on Bayesian formulation towards using deep neural networks. Towards this end, in this paper the effectiveness of various deep neural networks for predicting future pedestrian paths are evaluated. The analyzed deep networks solely rely, like in the traditional approaches, on observed tracklets without human-human interaction information. The evaluation is done on the publicly available TrajNet benchmark dataset, which builds up a repository of considerable and popular datasets for trajectory-based activity forecasting. We show that a Recurrent-Encoder with a Dense layer stacked on top, referred to as RED-predictor, is able to achieve sophisticated results compared to elaborated models in such scenarios. Further, we investigate failure cases and give explanations for observed phenomena and give some recommendations for overcoming demonstrated shortcomings.