About ChAOS

Crowd simulation is a transdisciplinary research theme by nature. Computer science is a natural contributor to this theme, especially the Computer Graphics community, with teams such as ours. This community is attached to being able to evaluate the results of a simulation on the basis of an animation such as…

Continue reading

Release of the UMANS software

The Crowd Group of Inria Rennes is proud to release UMANS! UMANS (Unified Microscopic Agent Navigation Simulator) is open crowd-simulation software that can reproduce many different algorithms for collision avoidance in crowds. UMANS translates these algorithms to a single principle, while unifying as many simulation details as possible. This makes…

Continue reading

Kick-off meeting of the CLIPE project

The international research project CLIPE kicks off today and tomorrow (April 2+3, 2020). The kick-off meeting involves the following institutes: University of Cyprus Universitat Politecnica de Catalunya INRIA University College London Trinity College Dublin Max Planck Institute for Intelligent Systems KTH Royal Institute of Technology, Stockholm Ecole Polytechnique Silversky3d This…

Continue reading

Thesis defense: Axel López

After 3 years as a PhD student in the Rainbow team, Axel López has defended his thesis titled “Optical flow-based navigation algorithms for virtual humans” on Monday 16th December. He now exchanges Rennes for Barcelona to start an engineering position at the Computer Vision Center.         

Continue reading

Publication (CASA 2019): Data-Driven Crowd Simulation with GANs

(This paper has been published in the 2019 International Conference on Computer Animation and Social Agents.) Abstract: This paper presents a novel data-driven crowd simulation method that can mimic the observed traffic of pedestrians in a given environment. Given a set of observed trajectories, we use a recent form of…

Continue reading

Publication (CVPR 2019): Social Ways

(This paper has been published in the workshops of the 2019 Computer Vision and Pattern Recognition Conference.) Abstract: A novel approach for predicting the motion of pedestrians interacting with others. It uses a Generative Adversarial Network (GAN) to sample plausible predictions for any agent in the scene. As GANs are…

Continue reading