2015 · 166 citations · 38 references
EngineeringRobotics EngineeringHuman-robot InteractionRobot LearningRoboticsDexterous ManipulationManipulation LearningModel-based Robot LearningRobot ManipulationTactile LearningTactile SensingManipulation Skill LearningReinforcement Learning For ManipulationRobotic Manipulation LearningTactile FeaturesTactile FeedbackTactile In-hand ManipulationTactile ManipulationTactile Sensors
Dexterous manipulation enables repositioning of objects in a robot's hand, but for unknown objects exact models are unavailable, so compliance and tactile feedback are used to adapt, though compliant hands and sensors add modeling complexity. The study proposes acquiring in‑hand manipulation skills via reinforcement learning that does not rely on analytic dynamics or kinematics models. They use reinforcement learning to acquire tactile manipulation skills with a passively compliant hand, avoiding the need for analytic dynamics or kinematics models. The approach successfully acquires a tactile manipulation skill with a passively compliant hand and generalizes to novel objects.
Dexterous manipulation enables repositioning of objects and tools within a robot's hand. When applying dexterous manipulation to unknown objects, exact object models are not available. Instead of relying on models, compliance and tactile feedback can be exploited to adapt to unknown objects. However, compliant hands and tactile sensors add complexity and are themselves difficult to model. Hence, we propose acquiring in-hand manipulation skills through reinforcement learning, which does not require analytic dynamics or kinematics models. In this paper, we show that this approach successfully acquires a tactile manipulation skill using a passively compliant hand. Additionally, we show that the learned tactile skill generalizes to novel objects.
38
Human-Inspired Robotic Grasp Control With Tactile Sensing
Joseph M. Romano, Kaijen Hsiao, Günter Niemeyer et al. · IEEE Transactions on Robotics · 2011 · 411 citations
Skill learning and task outcome prediction for manipulation
Peter Pástor, Mrinal Kalakrishnan, Sachin Chitta et al. · 2011 · 207 citations