Learning To Grasp Under Uncertainty Using POMDPs

Robust object grasping under uncertainty is an essential capability of service robots. Many existing approaches rely on far-field sensors, such as cameras, to compute a grasp pose and perform open-loop grasp after placing gripper under the pose. This often fails as a result of sensing or environment uncertainty. This paper presents a principled, general and efficient approach to adaptive grasping, using both tactile and visual sensing as feedback. We first model adaptive grasping as a partially observable Markov decision process (POMDP), which handles uncertainty naturally. We solve the POMDP for sampled objects from a set, in order to generate data for learning. Finally, we train a grasp policy, represented as a deep recurrent neural network (RNN), in simulation through imitation learning. By combining model-based POMDP planning and imitation learning, the proposed approach achieves robustness under uncertainty, generalization over many objects, and fast execution. In particular, we show that modeling only a small sample of objects enables us to learn a robust strategy to grasp previously unseen objects of varying shapes and recover from failure over multiple steps. Experiments on the G3DB object dataset in simulation and a smaller object set with a real robot indicate promising results.

Authors

• Neha P. Garg
• David Hsu
• Wee Sun Lee

Keywords

• Uncertainty
• Grippers
• Grasping
• Planning
• Sensors
• Shape
• Computational modeling
• Recurrent Neural Network
• Real Robot
• Imitation Learning
• Deep Recurrent Neural Network
• Large Amount Of Data
• Proprioceptive
• Point Cloud
• Object Classification
• Joint Angles
• Depth Images
• Object Shape
• Object Motion
• Policy Learning
• Open Loop
• Force Feedback
• Object Instances
• Distribution Of Objects
• Object Pose
• Term Plan
• Belief Updating
• Touch Sensor
• Sensor Feedback
• Touching Objects
• Household Objects
• Finger Joints
• Visual Feedback
• Perceptual Uncertainty
• Principled Way
• State Space