5 papers
Continuous MDP Homomorphisms and Homomorphic Policy Gradient
Sahand Rezaei-Shoshtari, Rosie Zhao, Prakash Panangaden +2
Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms. In this paper, we study abstraction in the continuou…
Learning Intuitive Physics with Multimodal Generative Models
Sahand Rezaei-Shoshtari, Francois Robert Hogan, Michael Jenkin +2
Predicting the future interaction of objects when they come into contact with their environment is key for autonomous agents to take intelligent and anticipatory actions. This pape…
Seeing Through your Skin: Recognizing Objects with a Novel Visuotactile Sensor
Francois Robert Hogan, Michael Jenkin, Sahand Rezaei-Shoshtari +3
We introduce a new class of vision-based sensor and associated algorithmic processes that combine visual imaging with high-resolution tactile sending, all in a uniform hardware and…
Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference
Sahand Rezaei-Shoshtari, David Meger, Inna Sharf
Utilization of latent space to capture a lower-dimensional representation of a complex dynamics model is explored in this work. The targeted application is of a robotic manipulator…
Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning
Sahand Rezaei-Shoshtari, David Meger, Inna Sharf
Motivated by the recursive Newton-Euler formulation, we propose a novel cascaded Gaussian process learning framework for the inverse dynamics of robot manipulators. This approach l…