Interaction primitives for human-robot cooperation tasks

  title={Interaction primitives for human-robot cooperation tasks},
  author={H. B. Amor and G. Neumann and Sanket Kamthe and Oliver Kroemer and Jan Peters},
  journal={2014 IEEE International Conference on Robotics and Automation (ICRA)},
  • H. B. Amor, G. Neumann, +2 authors Jan Peters
  • Published 2014
  • Computer Science, Engineering
  • 2014 IEEE International Conference on Robotics and Automation (ICRA)
To engage in cooperative activities with human partners, robots have to possess basic interactive abilities and skills. However, programming such interactive skills is a challenging task, as each interaction partner can have different timing or an alternative way of executing movements. In this paper, we propose to learn interaction skills by observing how two humans engage in a similar task. To this end, we introduce a new representation called Interaction Primitives. Interaction primitives… Expand
Environment-adaptive interaction primitives for human-robot motor skill learning
Environment-adaptive Interaction Primitives (EalPs) are proposed as an extension of Inter interaction Primitives to improve the predicted motor skills of robot within a brief observed human motion, but also obtain the generalization ability to adapt to new environmental conditions by learning the relationships between each condition and the corresponding motor skills from training samples. Expand
Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks
An interaction learning method for collaborative and assistive robots based on movement primitives that allows for both action recognition and human–robot movement coordination and is scalable in relation to the number of tasks. Expand
Learning interaction for collaborative tasks with probabilistic movement primitives
This paper introduces the use of Probabilistic Movement Primitives (ProMPs) to devise an interaction method that both recognizes the action of a human and generates the appropriate movement primitive of the robot assistant. Expand
Environment-adaptive interaction primitives through visual context for human–robot motor skill learning
The approach to capture human–robot interactive skills by combining their demonstrative data with additional environmental parameters automatically derived from observation of task context without the need for heuristic assignment is documents, as an extension to overcome shortcomings of the interaction primitives framework. Expand
Anticipative Interaction Primitives for Human-Robot Collaboration
This paper introduces the initial investigation on the problem of providing a semi-autonomous robot collaborator with anticipative capabilities to predict human actions, and uses a probabilistic representation of interaction primitives to generate robot trajectories. Expand
Learning multiple collaborative tasks with a mixture of Interaction Primitives
A Mixture of Interaction Primitives is proposed to learn multiple interaction patterns from unlabeled demonstrations to overcome the limitation of this framework to represent and generalize a single interaction pattern. Expand
A system for learning continuous human-robot interactions from human-human demonstrations
The effectiveness of the data-driven imitation learning system for learning human-robot interactions from human-human demonstrations on complex, sequential tasks is shown by presenting two applications involving collaborative human- robot assembly. Expand
Prediction of Intention during Interaction with iCub with Probabilistic Movement Primitives
An approach to endow the iCub with basic capabilities of intention recognition, based on Probabilistic Movement Primitives (ProMPs), a versatile method for representing, generalizing, and reproducing complex motor skills is proposed. Expand
Modeling Spatio-Temporal Variability in Human-Robot Interaction with Probabilistic Movement Primitives
The task of physically assisting humans requires from robots the ability to adapt in many different ways: to changes in space of the human movement, to changes in the speed of the human, to changesExpand
Modeling Human-Robot Interaction with Probabilistic Movement Representations
Robots that can interact with humans represent a potential benefit to society. They may, among many other applications, help increasing the quality of life of motor impaired people. However, in orderExpand


Physical Human-Robot Interaction: Mutual Learning and Adaptation
It is shown that this algorithm helps to improve the quality of the interaction between a robot and a human caregiver and two human-in-the-loop learning scenarios that are inspired by human parenting behavior are presented. Expand
Interactive imitation learning of object movement skills
A new robot control and learning system that allows a humanoid robot to extend its movement repertoire by learning from a human tutor and combines a number of novel concepts to enhance the flexibility and generalization capabilities of the system. Expand
Robot Programming by Demonstration
Drawing on findings from robot control, human-robot interaction, applied machine learning, artificial intelligence, and developmental and cognitive psychology, the book contains a large set of didactic and illustrative examples. Expand
Mimetic Communication Model with Compliant Physical Contact in Human—Humanoid Interaction
The mimetic communication model proposed by Nakamura et al., is modified and communication in physical domain as well as the symbolic domain is achieved through the concept of motion primitives and interaction primitives. Expand
Learning to Walk through Imitation
This paper provides the first demonstration that a humanoid robot can learn to walk directly by imitating a human gait obtained from motion capture (mocap) data, and proposes a new modelfree approach to tractable imitation-based learning in humanoids. Expand
Robot Program 59. Robot Programming by Demonstration
Recent progresses in the field, which are reviewed in this chapter, show that the field has made a leap forward during the past decade toward these goals and it is anticipated that these promises may be fulfilled very soon. Expand
Evaluation of a probabilistic approach to learn and reproduce gestures by imitation
An approach based on Hidden Markov Model and Gaussian Mixture Regression to learning robust models of human motion through imitation is presented and contrasted with four state-of-the-art methods previously proposed in robotics to learn and reproduce new skills by imitation. Expand
Is imitation learning the route to humanoid robots?
  • S. Schaal
  • Psychology, Computer Science
  • Trends in Cognitive Sciences
  • 1999
It is postulated that the study of imitation learning offers a promising route to gain new insights into mechanisms of perceptual motor control that could ultimately lead to the creation of autonomous humanoid robots. Expand
Dynamic Imitation in a Humanoid Robot through Nonparametric Probabilistic Inference
This paper proposes an iterative, probabilistically constrained algorithm for exploring the space of motor commands and shows that the algorithm can quickly discover dynamically stable actions for whole-body imitation of human motion. Expand
Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors
Dynamical movement primitives is presented, a line of research for modeling attractor behaviors of autonomous nonlinear dynamical systems with the help of statistical learning techniques, and its properties are evaluated in motor control and robotics. Expand