A Planning Framework for Non-Prehensile Manipulation under Clutter and Uncertainty

By M. Dogar, Siddhartha S. Srinivasa. 2012

172 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning (2018, background): “[11] presents a robust planning framework for push-grasping (non-prehensile motions baked within grasping primitives) to reduce grasp uncertainty as well as an additional motion primitive – sweeping – to move around obstacles in clutter.”
Deep visual foresight for planning robot motion (2016, methodology): “Standard model-based methods for robotic manipulation might involve estimating the physical properties of the environment, and then solving for the controls based on the known laws of physics [4], [5], [6].”
Learning Visual Affordances for Robotic Manipulation (2019, background): “While hard-coded heuristics for supervising push-grasping policies have been successfully developed by exploiting domain-specific knowledge [24], they limit the types of synergistic behaviors between pushing and grasping that can be performed.”
Nonprehensile Dynamic Manipulation: A Survey (2018, unknown): “Such a problem is addressed within the push-grasping task in [56]: the robot manipulator pushes away the obstacles during the approaching path for object grasping.”
GPLAC: Generalizing Vision-Based Robotic Skills Using Weakly Labeled Images (2017, unknown): “Although standard meth-ods in robotics and autonomous vehicle control typically separate perception and decision making into separate stages [20, 34, 8, 7], the success of deep learning meth-ods has prompted considerable recent interest in learning sensorimotor policies that directly map image…”
Integrated task and motion planning in belief space (2013, background): “The work of Dogar and Srinivasa (2012) comes closest among existing systems to satisfying our goals.”
Push-manipulation of complex passive mobile objects using experimentally acquired motion models (2014, unknown): “Another recent study by Dogar and Srinivasa (2012) uses push-manipulation in a tabletop manipulation scenario as a way to reduce uncertainty prior to grasping by utilizing the funneling effect of pushing.”