A Vision-Based Learning Method for Pushing Manipulation

By Marcos Salganicoff, Giorgio Metta, Andrea Oddera, Giulio Sandini. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning (2018, background): “rs that can lead to erroneous predictions of friction-modeling pushing solutions in real-world settings. While recent methods have explored data-driven algorithms for learning the dynamics of pushing [17], [18], [19], many of these works have largely focused on the execution of stable pushes for one”
Deep visual foresight for planning robot motion (2016, methodology): “This approach has been applied to a range of problems, including robotic pushing [7], [8], [9].”
More than a million ways to be pushed. A high-fidelity experimental dataset of planar pushing (2016, methodology): “More recently, data-driven models [17, 7, 18, 19, 20] have been proposed as an alternative approach to analysis.”
Policy transfer via modularity (2017, background): “Some previous efforts have been made to deal with the uncertainties in friction by learning how to push objects [19], [20], [21], [22], [23], [18].”
A probabilistic data-driven model for planar pushing (2017, background): “Over the years, several works have applied data-driven techniques to the problem of planar pushing [12, 13, 14, 15, 16].”
Policy transfer via modularity and reward guiding (2017, background): “Some previous efforts have been made to deal with the uncertainties in friction by learning how to push objects [24], [25], [26], [27], [28], [20], [29].”
Learning Visual Affordances for Robotic Manipulation (2019, background): “While recent methods have explored data-driven algorithms for learning the dynamics of pushing [100, 73, 128], many of these works have largely focused on the execution of stable”
Push-manipulation of complex passive mobile objects using experimentally acquired motion models (2014, methodology): “An early work by Salganicoff et al. (1993) presents a very simple, 1-nearest neighbor based approximation method for the forward model of an object being pushed from a single rotational contact point in an obstacle-free environment by controlling only one degree of freedom.”