Researcher at CIMAT, Department of Computer Science. 
PhD (Univ. Toulouse III LAAS-CNRS), ENSTA engineer (Promotion 99). Erdos Number: 4.
[Google Scholar Profile][ResearchGate profile]

Professor at Maestría en las Ciencias de la Computación of CIMAT.

Research interests



My more recent publications

Ek-Hobak A, Sanchez A, Hayet J. Evaluation of Output Representations in Neural Network-based Trajectory Predictions Systems, in 2020 International Conference on Systems, Signals and Image Processing (IWSSIP). ; 2020 :447-452. Publisher's VersionAbstract
This work deals with the challenging problem of pedestrian trajectory prediction, when observations from these pedestrians can be gathered through a urban video monitoring system. Since most of state-of-the-art systems in this field are now based on deep recurrent neural networks, here we study one specific characteristic of these systems, namely the way they encode their output. We compare three different representations of the output, and show that those representations working on residuals (in particular, displacements with respect of last pedestrian position or linear regression models of residual errors) produce much more accurate predictions than those ones handling absolute coordinates.
Aldana-Murillo NG, Sandoval L, Hayet J-B, Esteves C, Becerra HM. Coupling humanoid walking pattern generation and visual constraint feedback for pose-regulation and visual path-following. Robotics and Autonomous Systems [Internet]. 2020;128 :103497. Publisher's VersionAbstract
In this article, we show how visual constraints such as homographies and fundamental matrices can be integrated tightly into the locomotion controller of a humanoid robot to drive it from one configuration to another (pose-regulation), only by means of images. The visual errors generated by these constraints are stacked as terms of the objective function of a Quadratic Program so as to specify the final pose of the robot with a reference image. By using homographies or fundamental matrices instead of specific points, we avoid the features occlusion problem. This image-based strategy is also extended to solve the problem of following a visual path by a humanoid robot, which allows the robot to execute much longer paths and plans than when using just one reference image. The effectiveness of our approach is validated with a humanoid dynamic simulator.
Amirian J, Hayet J-B, Pettré J. Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs, in CVPR Workshops. Long Beach, USA ; 2019. Publisher's VersionAbstract
This paper proposes 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 very susceptible to mode collapsing and dropping, we show that the recently proposed Info-GAN allows dramatic improvements in multi-modal pedestrian trajectory prediction to avoid these issues. We also left out L2-loss in training the generator, unlike some previous works, because it causes serious mode collapsing though faster convergence. We show through experiments on real and synthetic data that the proposed method leads to generate more diverse samples and to preserve the modes of the predictive distribution. In particular, to prove this claim, we have designed a toy example dataset of trajectories that can be used to assess the performance of different methods in preserving the predictive distribution modes.
Amirian J, van Toll W, Hayet J-B, Pettré J. Data-Driven Crowd Simulation with Generative Adversarial Networks, in Proceedings of the 32Nd International Conference on Computer Animation and Social Agents. New York, NY, USA: ACM ; 2019 :7–10. Publisher's VersionAbstract
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 neural networks, Generative Adversarial Networks (GANs), to learn the properties of this set and generate new trajectories with similar properties. We define a way for simulated pedestrians (agents) to follow such a trajectory while handling local collision avoidance. As such, the system can generate a crowd that behaves similarly to observations, while still enabling real-time interactions between agents. Via experiments with real-world data, we show that our simulated trajectories preserve the statistical properties of their input. Our method simulates crowds in real time that resemble existing crowds, while also allowing insertion of extra agents, combination with other simulation methods, and user interaction.
Carlos H, Hayet J-B, Murrieta-Cid R. An Analysis of Policies from Stochastic Linear Quadratic Gaussian in Robotics Problems with State- and Control-Dependent Noise. Journal of Intelligent & Robotic Systems [Internet]. 2018;2018 (92) :85-106. Publisher's VersionAbstract
Among all the mathematical frameworks used in the control and robotics communities to handle uncertainties, the stochastic variants of optimal control frameworks are appealing, in particular because of the existence of efficient tools to solve them computationally, such as dynamic programming. However, in many cases, because of their formulation as a classical optimization problem, it may be difficult to ponder the expected solutions for a given choice of the objective function to minimize. In this paper, we perform an in-depth analysis of the behavior of the policies obtained from solving Stochastic Linear Quadratic Gaussian problems, thinking in particular in robot motion planning applications. To perform this analysis, we assume simplified linear systems perturbed by Gaussian noise, with state-dependend and control-dependent components, and objective functions summing up control-related and state-related costs. We provide (1) useful bounds for understanding the effect of the objective function parameters, (2) insights on what the expected paths of system should be and (3) results on the optimal choice of the planning horizon.