Raising context awareness in motion forecasting

TL;DR

This paper presents CAB, a motion forecasting model that enhances the use of semantic contextual cues, introduces metrics for forecast consistency, and demonstrates improved performance on the nuScenes benchmark.

Contribution

The paper introduces a training procedure to promote semantic context utilization in motion forecasting and proposes new metrics for forecast consistency measurement.

Findings

CAB improves context awareness in trajectory prediction.

New metrics effectively measure forecast temporal consistency.

Enhanced performance on nuScenes benchmark.

Abstract

Learning-based trajectory prediction models have encountered great success, with the promise of leveraging contextual information in addition to motion history. Yet, we find that state-of-the-art forecasting methods tend to overly rely on the agent's current dynamics, failing to exploit the semantic contextual cues provided at its input. To alleviate this issue, we introduce CAB, a motion forecasting model equipped with a training procedure designed to promote the use of semantic contextual information. We also introduce two novel metrics - dispersion and convergence-to-range - to measure the temporal consistency of successive forecasts, which we found missing in standard metrics. Our method is evaluated on the widely adopted nuScenes Prediction benchmark as well as on a subset of the most difficult examples from this benchmark. The code is available at github.com/valeoai/CAB