Learning 6-DoF Grasping and Pick-Place Using Attention Focus

Abstract

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. Our approach is to formulate the problem as a Markov decision process (MDP) with abstract yet generally applicable state and action representations. Finding a good solution to the MDP requires adding constraints on the allowed actions. We develop a specific set of constraints called hierarchical $\text{SE}(3)$ sampling (HSE3S) which causes the robot to learn a sequence of gazes to focus attention on the task-relevant parts of the scene. We demonstrate the effectiveness of our approach on three challenging pick-place tasks (with novel objects in clutter and nontrivial places) both in simulation and on a real robot, even though all training is done in simulation.

References in corpus (4)

• Continuous control with deep reinforcement learning
• Recurrent Models of Visual Attention
• Hindsight Experience Replay
• On-line Policy Improvement using Monte-Carlo Search

Cited by in corpus (7)

• S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes
• Bounding Box Regression with Uncertainty for Accurate Object Detection
• Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions
• Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations
• Object Finding in Cluttered Scenes Using Interactive Perception
• Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures
• Policy learning in SE(3) action spaces