Learning Lane Graph Representations for Motion Forecasting
arXiv:2007.13732
Abstract
We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions. Instead of encoding vectorized maps as raster images, we construct a lane graph from raw map data to explicitly preserve the map structure. To capture the complex topology and long range dependencies of the lane graph, we propose LaneGCN which extends graph convolutions with multiple adjacency matrices and along-lane dilation. To capture the complex interactions between actors and maps, we exploit a fusion network consisting of four types of interactions, actor-to-lane, lane-to-lane, lane-to-actor and actor-to-actor. Powered by LaneGCN and actor-map interactions, our model is able to predict accurate and realistic multi-modal trajectories. Our approach significantly outperforms the state-of-the-art on the large scale Argoverse motion forecasting benchmark.
ECCV 2020 Oral
References in corpus (8)
- Semi-Supervised Classification with Graph Convolutional Networks
- Deep Convolutional Networks on Graph-Structured Data
- Argoverse: 3D Tracking and Forecasting with Rich Maps
- MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
- Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
- Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions
- DSDNet: Deep Structured self-Driving Network
- Neural Turtle Graphics for Modeling City Road Layouts