Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting

TL;DR

This paper introduces a socially-informed pedestrian trajectory forecasting model that leverages a reconstructor and a variational autoencoder to generate pseudo-trajectories, improving social awareness and stability in predictions.

Contribution

It proposes a novel social loss and a reconstruction-based augmentation approach to enhance social interaction modeling in pedestrian trajectory prediction.

Findings

Outperforms state-of-the-art on ETH/UCY and SDD benchmarks

Demonstrates improved stability in trajectory forecasts

Shows effectiveness of pseudo-trajectory augmentation

Abstract

Pedestrian trajectory prediction remains a challenge for autonomous systems, particularly due to the intricate dynamics of social interactions. Accurate forecasting requires a comprehensive understanding not only of each pedestrian's previous trajectory but also of their interaction with the surrounding environment, an important part of which are other pedestrians moving dynamically in the scene. To learn effective socially-informed representations, we propose a model that uses a reconstructor alongside a conditional variational autoencoder-based trajectory forecasting module. This module generates pseudo-trajectories, which we use as augmentations throughout the training process. To further guide the model towards social awareness, we propose a novel social loss that aids in forecasting of more stable trajectories. We validate our approach through extensive experiments, demonstrating strong performances in comparison to state of-the-art methods on the ETH/UCY and SDD benchmarks.