no code implementations • 23 Mar 2024 • Jiangbei Yue, Baiyi Li, Julien Pettré, Armin Seyfried, He Wang
We investigate a new task in human motion prediction, which is predicting motions under unexpected physical perturbation potentially involving multiple people.
no code implementations • 22 Sep 2023 • Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, Marie-Paule Cani
Crowd simulation is important for video-games design, since it enables to populate virtual worlds with autonomous avatars that navigate in a human-like manner.
no code implementations • 11 Feb 2023 • Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, Marie-Paule Cani
We also show experimentally that agents with non-exponential discounting trained via UGAE outperform variants trained with Monte Carlo advantage estimation.
1 code implementation • 19 Sep 2022 • Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, Marie-Paule Cani
Each of these choices has a significant, and potentially nontrivial impact on the results, and so researchers should be mindful about choosing and reporting them in their work.
no code implementations • 7 Mar 2022 • Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, C. Karen Liu, Julien Pettré, Michiel Van de Panne, Marie-Paule Cani
Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment.
no code implementations • 27 Aug 2021 • Beatriz Cabrero Daniel, Ricardo Marques, Ludovic Hoyet, Julien Pettré, Josep Blat
A quality metric, QF, is proposed to abstract from reference data while capturing the most salient features that affect the perception of trajectory realism.
1 code implementation • 23 May 2019 • Javad Amirian, Wouter van Toll, Jean-Bernard Hayet, Julien Pettré
This paper presents a novel data-driven crowd simulation method that can mimic the observed traffic of pedestrians in a given environment.
no code implementations • 16 Sep 2014 • Aniket Bera, David Wolinski, Julien Pettré, Dinesh Manocha
We automatically compute the optimal parameters for each of these different models based on prior tracked data and use the best model as motion prior for our particle-filter based tracking algorithm.