Goal-driven Long-Term Trajectory Prediction

TL;DR

This paper introduces a goal-driven neural network model for long-term human trajectory prediction, addressing error accumulation by modeling destination intentions and outperforming existing methods across diverse scenarios.

Contribution

It proposes a novel dual-channel neural network that generalizes goal-driven trajectory prediction across different environments, improving long-term accuracy.

Findings

Outperforms state-of-the-art in long-term trajectory prediction

Effective in diverse scenes with complex geometries

Demonstrates the importance of goal modeling in trajectory accuracy

Abstract

The prediction of humans' short-term trajectories has advanced significantly with the use of powerful sequential modeling and rich environment feature extraction. However, long-term prediction is still a major challenge for the current methods as the errors could accumulate along the way. Indeed, consistent and stable prediction far to the end of a trajectory inherently requires deeper analysis into the overall structure of that trajectory, which is related to the pedestrian's intention on the destination of the journey. In this work, we propose to model a hypothetical process that determines pedestrians' goals and the impact of such process on long-term future trajectories. We design Goal-driven Trajectory Prediction model - a dual-channel neural network that realizes such intuition. The two channels of the network take their dedicated roles and collaborate to generate future trajectories. Different than conventional goal-conditioned, planning-based methods, the model architecture is designed to generalize the patterns and work across different scenes with arbitrary geometrical and semantic structures. The model is shown to outperform the state-of-the-art in various settings, especially in large prediction horizons. This result is another evidence for the effectiveness of adaptive structured representation of visual and geometrical features in human behavior analysis.