1 code implementation • 15 Oct 2020 • Marcus Gualtieri, Robert Platt
One approach is (a) use object instance segmentation and shape completion to model the objects and (b) use a regrasp planner to decide grasps and places displacing the models to their goals.
Robotics
1 code implementation • 19 Apr 2019 • Marcus Gualtieri, Robert Platt
Learning generalizable skills in robotic manipulation has long been challenging due to real-world sized observation and action spaces.
Robotics
1 code implementation • 15 Jun 2018 • Marcus Gualtieri, Robert Platt
We address a class of manipulation problems where the robot perceives the scene with a depth sensor and can move its end effector in a space with six degrees of freedom -- 3D position and orientation.
Robotics
1 code implementation • 18 Jul 2017 • Marcus Gualtieri, Andreas ten Pas, Robert Platt
Whereas most deep RL approaches to robotic manipulation frame the problem in terms of low level states and actions, we propose a more abstract formulation.
Robotics
1 code implementation • 29 Jun 2017 • Andreas ten Pas, Marcus Gualtieri, Kate Saenko, Robert Platt
Many grasp detection methods achieve grasp success rates (grasp successes as a fraction of the total number of grasp attempts) between 75% and 95% for novel objects presented in isolation or in light clutter.
Robotics
3 code implementations • 4 Mar 2016 • Marcus Gualtieri, Andreas ten Pas, Kate Saenko, Robert Platt
Our focus in this paper is on improving the second step by using depth sensor scans from large online datasets to train a convolutional neural network.
Robotics
