Vectorized Representation Dreamer (VRD): Dreaming-Assisted Multi-Agent Motion-Forecasting
This addresses the problem of accurate trajectory forecasting for dynamic objects in autonomous driving, though it appears incremental by building on existing world model concepts.
The paper tackles multi-agent motion forecasting for autonomous vehicles by introducing VRD, a vectorized world model that incorporates the ego vehicle's behavior through a dreamed closed-loop training pipeline, achieving state-of-the-art performance on the Argoverse 2 dataset's single prediction miss rate metric.
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.