Deep Differentiable Grasp Planner for High-DOF Grippers
Min Liu, Zherong Pan, Kai Xu, Kanishka Ganguly, Dinesh Manocha
Abstract
We present an end-to-end algorithm for training deep neural networks to grasp novel objects. Our algorithm builds all the essential components of a grasping system using a forward-backward automatic differentiation approach, including the forward kinematics of the gripper, the collision between the gripper and the target object, and the metric for grasp poses.
Topics & Concepts
GRASPGrippersPlannerDifferentiable functionComputer scienceTrajectoryArtificial intelligenceEngineeringMathematicsMechanical engineeringPhysicsMathematical analysisAstronomyProgramming languageRobot Manipulation and LearningHuman Pose and Action RecognitionHand Gesture Recognition Systems