Zobrazeno 1 - 10
of 226
pro vyhledávání: '"Siddiqi, Kaleem"'
Autor:
Ablett, Trevor, Limoyo, Oliver, Sigal, Adam, Jilani, Affan, Kelly, Jonathan, Siddiqi, Kaleem, Hogan, Francois, Dudek, Gregory
Contact-rich tasks continue to present a variety of challenges for robotic manipulation. In this work, we leverage a multimodal visuotactile sensor within the framework of imitation learning (IL) to perform contact rich tasks that involve relative mo
Externí odkaz:
http://arxiv.org/abs/2311.01248
Autor:
Mondal, Arnab Kumar, Panigrahi, Siba Smarak, Rajeswar, Sai, Siddiqi, Kaleem, Ravanbakhsh, Siamak
The accurate modeling of dynamics in interactive environments is critical for successful long-range prediction. Such a capability could advance Reinforcement Learning (RL) and Planning algorithms, but achieving it is challenging. Inaccuracies in mode
Externí odkaz:
http://arxiv.org/abs/2306.11941
Autor:
Khodadad, Mohammad, Rezanejad, Morteza, Kasmaee, Ali Shiraee, Siddiqi, Kaleem, Walther, Dirk, Mahyar, Hamidreza
The analysis of 3D point clouds has diverse applications in robotics, vision and graphics. Processing them presents specific challenges since they are naturally sparse, can vary in spatial resolution and are typically unordered. Graph-based networks
Externí odkaz:
http://arxiv.org/abs/2303.17748
Autor:
Rezanejad, Morteza, Samari, Babak, Karimi, Elham, Rekleitis, Ioannis, Dudek, Gregory, Siddiqi, Kaleem
We consider how to directly extract a road map (also known as a topological representation) of an initially-unknown 2-dimensional environment via an online procedure that robustly computes a retraction of its boundaries. In this article, we first pre
Externí odkaz:
http://arxiv.org/abs/2111.13826
Autor:
Rezanejad, Morteza, Khodadad, Mohammad, Mahyar, Hamidreza, Lombaert, Herve, Gruninger, Michael, Walther, Dirk B., Siddiqi, Kaleem
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects represented by surface meshes, their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increase
Externí odkaz:
http://arxiv.org/abs/2111.13295
Current deep learning models for classification tasks in computer vision are trained using mini-batches. In the present article, we take advantage of the relationships between samples in a mini-batch, using graph neural networks to aggregate informat
Externí odkaz:
http://arxiv.org/abs/2105.03237
In Reinforcement Learning (RL), Convolutional Neural Networks(CNNs) have been successfully applied as function approximators in Deep Q-Learning algorithms, which seek to learn action-value functions and policies in various environments. However, to d
Externí odkaz:
http://arxiv.org/abs/2007.03437
Autor:
Camaro, Charles-Olivier Dufresne, Rezanejad, Morteza, Tsogkas, Stavros, Siddiqi, Kaleem, Dickinson, Sven
We combine ideas from shock graph theory with more recent appearance-based methods for medial axis extraction from complex natural scenes, improving upon the present best unsupervised method, in terms of efficiency and performance. We make the follow
Externí odkaz:
http://arxiv.org/abs/2004.02677
Affinity graphs are widely used in deep architectures, including graph convolutional neural networks and attention networks. Thus far, the literature has focused on abstracting features from such graphs, while the learning of the affinities themselve
Externí odkaz:
http://arxiv.org/abs/2003.09049
View based strategies for 3D object recognition have proven to be very successful. The state-of-the-art methods now achieve over 90% correct category level recognition performance on appearance images. We improve upon these methods by introducing a v
Externí odkaz:
http://arxiv.org/abs/1906.01592