no code implementations • 12 Dec 2023 • Kenny A. Q. Caldas, Filipe M. Barbosa, Junior A. R. Silva, Tiago C. Santos, Iago P. Gomes, Luis A. Rosero, Denis F. Wolf, Valdir Grassi Jr
The longitudinal control strategy relies on a Non-Linear Model Predictive Controller (NMPC), which considers the path geometry and simplified vehicle dynamics to compute a smooth and comfortable input velocity, without violating the imposed constraints.
1 code implementation • 2 Nov 2022 • Gabriel S. Gama, Nícolas S. Rosa, Valdir Grassi Jr
Several SLAM methods benefit from the use of semantic information.
2 code implementations • 14 Apr 2022 • Angelica Tiemi Mizuno Nakamura, Denis Fernando Wolf, Valdir Grassi Jr
Multi-Task Learning is a learning paradigm that uses correlated tasks to improve performance generalization.
no code implementations • 14 Oct 2020 • Gustavo Alves Prudencio de Morais, Lucas Barbosa Marcos, Filipe Marques Barbosa, Bruno Henrique Groenner Barbosa, Marco Henrique Terra, Valdir Grassi Jr
The ability to deal with systems parametric uncertainties is an essential issue for heavy self-driving vehicles in unconfined environments.
no code implementations • 13 Oct 2020 • Raul de Queiroz Mendes, Eduardo Godinho Ribeiro, Nicolas dos Santos Rosa, Valdir Grassi Jr
Inferring the depth of images is a fundamental inverse problem within the field of Computer Vision since depth information is obtained through 2D images, which can be generated from infinite possibilities of observed real scenes.
Ranked #1 on Surface Normals Estimation on NYU-Depth V2 Surface Normals (using extra training data)
1 code implementation • 24 Sep 2018 • Nícolas Rosa, Vitor Guizilini, Valdir Grassi Jr
This paper addresses the problem of single image depth estimation (SIDE), focusing on improving the quality of deep neural network predictions.
no code implementations • 7 Aug 2018 • Filipe Marques Barbosa, Lucas Barbosa Marcos, Maira Martins da Silva, Marco Henrique Terra, Valdir Grassi Jr
Parametric uncertainties were assumed to be on the payload, and an $\mathcal{H}_{\infty}$ controller was used for performance comparison.
Systems and Control Systems and Control 37N35(Primary), 62G35, 70Q05, 93C85, 70E60 (Secondary)
no code implementations • 17 Feb 2018 • Rafael Oliveira, Fernando H. M. Rocha, Lionel Ott, Vitor Guizilini, Fabio Ramos, Valdir Grassi Jr
On the other hand, the cost to evaluate the policy's performance might also be high, being desirable that a solution can be found with as few interactions as possible with the real system.