EqDrive: Efficient Equivariant Motion Forecasting with Multi-Modality for Autonomous Driving
This addresses motion forecasting for autonomous vehicles, but it is incremental as it adapts an existing equivariant model to this domain.
The paper tackles the problem of forecasting vehicular motions in autonomous driving by using an equivariant model with multi-modal predictions, achieving state-of-the-art performance with 1.2 million parameters and training in under 2 hours.
Forecasting vehicular motions in autonomous driving requires a deep understanding of agent interactions and the preservation of motion equivariance under Euclidean geometric transformations. Traditional models often lack the sophistication needed to handle the intricate dynamics inherent to autonomous vehicles and the interaction relationships among agents in the scene. As a result, these models have a lower model capacity, which then leads to higher prediction errors and lower training efficiency. In our research, we employ EqMotion, a leading equivariant particle, and human prediction model that also accounts for invariant agent interactions, for the task of multi-agent vehicle motion forecasting. In addition, we use a multi-modal prediction mechanism to account for multiple possible future paths in a probabilistic manner. By leveraging EqMotion, our model achieves state-of-the-art (SOTA) performance with fewer parameters (1.2 million) and a significantly reduced training time (less than 2 hours).