activity
20192022
most citedExploiting map information for self-supervised learning in motion forecasting

4 citations · 5 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CV20224 cited

Exploiting map information for self-supervised learning in motion forecasting

Caio Azevedo, Thomas Gilles, Stefano Sabatini +1

Inspired by recent developments regarding the application of self-supervised learning (SSL), we devise an auxiliary task for trajectory prediction that takes advantage of map-only…

cs.RO2022

Enhanced Behavioral Cloning with Environmental Losses for Self-Driving Vehicles

Nelson Fernandez Pinto, Thomas Gilles

Learned path planners have attracted research interest due to their ability to model human driving behavior and rapid inference. Recent works on behavioral cloning show that simple…

cs.CV20211 cited

GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou +2

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 p…

cs.CV2021

HOME: Heatmap Output for future Motion Estimation

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou +2

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. T…

cs.LG2019

Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting

Jean Mercat, Thomas Gilles, Nicole El Zoghby +3

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-moda…