HOME: Heatmap Output for future Motion Estimation

Thomas Gilles (1, 2) , Stefano Sabatini (2) , Dzmitry Tsishkou (2) , Bogdan Stanciulescu (1) , Fabien Moutarde (1)

1 CAOR - Centre de Robotique
2 Huawei Technologies France [Boulogne-Billancourt]

In this paper, we propose HOME, a framework tackling the motion forecasting problem with an image output representing the probability distribution of the agent's future location. This method allows for a simple architecture with classic convolution networks coupled with attention mechanism for agent interactions, and outputs an unconstrained 2D topview representation of the agent's possible future. Based on this output, we design two methods to sample a finite set of agent's 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 1 st place on the online leaderboard.

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Automatique / Robotique; Traitement du signal et de l'image [eess.SP]

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou, Bogdan Stanciulescu, Fabien Moutarde. HOME: Heatmap Output for future Motion Estimation. 2021 IEEE International Intelligent Transportation Systems Conference (ITSC'2021), Sep 2021, Indianapolis, United States. ⟨hal-03356794⟩