Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives
When describing robot motion with dynamic movement primitives (DMPs), goal (trajectory
endpoint), shape and temporal scaling parameters are used. In reinforcement learning with …
endpoint), shape and temporal scaling parameters are used. In reinforcement learning with …
Motion adaptation based on learning the manifold of task and dynamic movement primitive parameters
Y Cohen, O Bar-Shira, S Berman - Robotica, 2021 - cambridge.org
Dynamic movement primitives (DMP) are motion building blocks suitable for real-world
tasks. We suggest a methodology for learning the manifold of task and DMP parameters …
tasks. We suggest a methodology for learning the manifold of task and DMP parameters …
Task adaptation through exploration and action sequencing
B Nemec, M Tamošiūnaitė… - 2009 9th IEEE-RAS …, 2009 - ieeexplore.ieee.org
General-purpose autonomous robots need to have the ability to sequence and adapt the
available sensorimotor knowledge, which is often given in the form of movement primitives …
available sensorimotor knowledge, which is often given in the form of movement primitives …
Improving robot motor learning with negatively valenced reinforcement signals
Both nociception and punishment signals have been used in robotics. However, the
potential for using these negatively valenced types of reinforcement learning signals for …
potential for using these negatively valenced types of reinforcement learning signals for …
The effects on adaptive behaviour of negatively valenced signals in reinforcement learning
N Navarro-Guerrero, RJ Lowe… - 2017 Joint IEEE …, 2017 - ieeexplore.ieee.org
Reinforcement learning algorithms and particularly those based on temporal-difference
learning are widely adopted and have been successfully applied to a number of problems …
learning are widely adopted and have been successfully applied to a number of problems …
Deterministic policy gradient based robotic path planning with continuous action spaces
Path planners for robotic manipulators often require precise target object locations based on
which inverse kinematics return the required joint-angles for approaching the object. This …
which inverse kinematics return the required joint-angles for approaching the object. This …
Coaching robots: online behavior learning from human subjective feedback
M Hirkoawa, K Suzuki - Innovations in Intelligent Machines-3 …, 2013 - Springer
This chapter describes a novel methodology for behavior learning of an agent, called
Coaching. The proposed method is an interactive and iterative learning method which …
Coaching. The proposed method is an interactive and iterative learning method which …
Learning arm movements of target reaching for humanoid robot
Z Liu, F Hu, D Luo, X Wu - 2015 IEEE International Conference …, 2015 - ieeexplore.ieee.org
The autonomous motor skill learning is crucial for the humanoid robot to adapt to various
tasks in complex environments and develop human-like behaviors. In this paper a method of …
tasks in complex environments and develop human-like behaviors. In this paper a method of …
Prenatal to postnatal transfer of motor skills through motor-compatible sensory representations
How can sensory-motor skills developed as a fetus transfer to postnatal life? We investigate
a simulated reaching task by training controllers under prenatal conditions (ie confined …
a simulated reaching task by training controllers under prenatal conditions (ie confined …
Teaching a robot to perform tasks with voice commands
AC Tenorio-Gonzalez, EF Morales… - Advances in Artificial …, 2010 - Springer
The full deployment of service robots in daily activities will require the robot to adapt to the
needs of non-expert users, particularly, to learn how to perform new tasks from “natural” …
needs of non-expert users, particularly, to learn how to perform new tasks from “natural” …