Litcius/Paper detail

Improved Generalization of Probabilistic Movement Primitives for Manipulation Trajectories

Xueyang Yao, Yinghan Chen, Bryan Tripp

2023IEEE Robotics and Automation Letters11 citationsDOI

Abstract

Imitation learning methods have proven effective in learning robotic tasks by leveraging multiple human-controlled demonstrations. However, existing approaches often struggle to generalize across a wide range of tasks, such as extrapolating to unseen object locations, incorporating via-point modulation, accurately modeling orientation, handling trajectories with multiple options, and capturing aiming actions. In this study, we propose a novel framework that combines ideas from task-parameterized Gaussian mixture models and probabilistic movement primitives to address these limitations and satisfy all the aforementioned properties within a single framework. We conduct comprehensive evaluations of our approach on four real-life tasks: pick-and-place, water pouring, shooting a hockey puck into a net, and sweeping.

Topics & Concepts

Computer scienceProbabilistic logicArtificial intelligenceGeneralizationTask (project management)Movement (music)Machine learningTrajectoryObject (grammar)Parameterized complexityGRASPPoint (geometry)AlgorithmMathematicsEngineeringMathematical analysisSystems engineeringGeometryPhysicsAestheticsAstronomyPhilosophyProgramming languageRobot Manipulation and LearningReinforcement Learning in RoboticsHuman Pose and Action Recognition
Improved Generalization of Probabilistic Movement Primitives for Manipulation Trajectories | Litcius