Convolutions for Spatial Interaction Modeling

Abstract

In many different fields interactions between objects play a critical role in determining their behavior. Graph neural networks (GNNs) have emerged as a powerful tool for modeling interactions, although often at the cost of adding considerable complexity and latency. In this paper, we consider the problem of spatial interaction modeling in the context of predicting the motion of actors around autonomous vehicles, and investigate alternatives to GNNs. We revisit 2D convolutions and show that they can demonstrate comparable performance to graph networks in modeling spatial interactions with lower latency, thus providing an effective and efficient alternative in time-critical systems. Moreover, we propose a novel interaction loss to further improve the interaction modeling of the considered methods.

Supplementary material included, to appear at CVPR2022

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Semi-Supervised Classification with Graph Convolutional Networks
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• IntentNet: Learning to Predict Intention from Raw Sensor Data
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
• Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
• VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation