2015 · 52 citations · 16 references
EngineeringRobotics EngineeringTeachingMotor ControlMotor LearningRoboticsActuation SystemsContact DynamicsForce ControlForce SensingRobot ManipulationRobot ManipulatorsDynamical Movement PrimitivesForce EstimationForce-torque RequirementsForce-torque SensingForce-torque Sensor IntegrationKinesthetic TeachingLearning From Human DemonstrationTorque Sensors
This paper demonstrates a method for simultaneous transfer of positional and force requirements for in-contact tasks from a human instructor to a robotic arm through kinesthetic teaching. This is achieved by a specific use of the sensory configuration, where a force/torque sensor is mounted between the tool and the flange of a robotic arm endowed with integrated torque sensors at each joint. The human demonstration is modeled using Dynamic Movement Primitives. Following human demonstration, the robot arm is provided with the capacity to perform sequential in-contact tasks, for example writing on a notepad a previously demonstrated sequence of characters. During the reenactment of the task, the system is not only able to imitate and generalize from demonstrated trajectories, but also from their associated force profiles. In fact, the implemented framework is extended to successfully recover from perturbations of the trajectory during reenactment and to cope with dynamic environments.
16
A survey of robot learning from demonstration
Brenna Argall, Sonia Chernova, Manuela Veloso et al. · Robotics and Autonomous Systems · 2008 · 3.3K citations
Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors
Auke Jan Ijspeert, Jun Nakanishi, H. Hoffmann et al. · Neural Computation · 2012 · 1.6K citations · Full text
Introduction to robotics: Mechanics and control
M.G. Rodd · Automatica · 1987 · 1.5K citations
Engineering, Mechanical Engineering, Robotics Engineering +10