In this paper, we propose GOHOME, a method leveraging graph representations of the High Definition Map and sparse projections to generate a heatmap output representing the future position probability distribution for a given agent in a traffic scene.
This heatmap output yields an unconstrained 2D grid representation of agent future possible locations, allowing inherent multimodality and a measure of the uncertainty of the prediction. Our graph-oriented model avoids the high computation burden of representing the surrounding context as squared images and processing it with classical CNNs, but focuses instead only on the most probable lanes where the agent could end up in the immediate future. GOHOME reaches 3$rd$ on Argoverse Motion Forecasting Benchmark on the MissRate$_6$ metric while achieving significant speed-up and memory burden diminution compared to 1$^{st}$ place method HOME. We also highlight that heatmap output enables multimodal ensembling and improve 1$^{st}$ place MissRate$_6$ by more than 15$%$ with our best ensemble.
In this paper, we propose HOME, a framework tackling the motion forecasting problem with an image output representing the probability distribution of the agents future location. This method allows for a simple architecture with classic convolution ne
tworks coupled with attention mechanism for agent interactions, and outputs an unconstrained 2D top-view representation of the agents possible future. Based on this output, we design two methods to sample a finite set of agents future locations. These methods allow us to control the optimization trade-off between miss rate and final displacement error for multiple modalities without having to retrain any part of the model. We apply our method to the Argoverse Motion Forecasting Benchmark and achieve 1st place on the online leaderboard.
This paper presents a novel vehicle motion forecasting method based on multi-head attention. It produces joint forecasts for all vehicles on a road scene as sequences of multi-modal probability density functions of their positions. Its architecture u
ses multi-head attention to account for complete interactions between all vehicles, and long short-term memory layers for encoding and forecasting. It relies solely on vehicle position tracks, does not need maneuver definitions, and does not represent the scene with a spatial grid. This allows it to be more versatile than similar model while combining any forecasting capabilities, namely joint forecast with interactions, uncertainty estimation, and multi-modality. The resulting prediction likelihood outperforms state-of-the-art models on the same dataset.
