Vectorized Representation Dreamer (VRD): Dreaming-Assisted Multi-Agent Motion-Forecasting

TL;DR

VRD introduces a dreaming-assisted multi-agent motion forecasting model that incorporates ego vehicle behavior, achieving state-of-the-art results by combining open-loop and closed-loop training with a kinematic reconstruction task.

Contribution

It presents a novel vectorized world model-inspired approach with a dreaming-assisted training pipeline for improved multi-agent motion prediction.

Findings

Achieves state-of-the-art single prediction miss rate on Argoverse 2

Performs on par with leading models on displacement metrics

Demonstrates effectiveness on Argoverse 2 and inD datasets

Abstract

For an autonomous vehicle to plan a path in its environment, it must be able to accurately forecast the trajectory of all dynamic objects in its proximity. While many traditional methods encode observations in the scene to solve this problem, there are few approaches that consider the effect of the ego vehicle's behavior on the future state of the world. In this paper, we introduce VRD, a vectorized world model-inspired approach to the multi-agent motion forecasting problem. Our method combines a traditional open-loop training regime with a novel dreamed closed-loop training pipeline that leverages a kinematic reconstruction task to imagine the trajectory of all agents, conditioned on the action of the ego vehicle. Quantitative and qualitative experiments are conducted on the Argoverse 2 multi-world forecasting evaluation dataset and the intersection drone (inD) dataset to demonstrate the performance of our proposed model. Our model achieves state-of-the-art performance on the single prediction miss rate metric on the Argoverse 2 dataset and performs on par with the leading models for the single prediction displacement metrics.