• Publications
  • Influence
Learning responsive robot behavior by imitation
TLDR
This paper simultaneously record the movements of two humans engaged in on-going interaction tasks and learn compact models of the interaction that can thereafter be used by a robot to engage in a similar interaction with a human partner.
Towards a Simulator for Imitation Learning with Kinesthetic Bootstrapping
TLDR
A physics based simulator that allows kinesthetic interactions between a human and a robot to be recorded, and later used for imitation learning, and a new scheme for robot motion learning based on kinesthetic bootstrapping is proposed.
Inferring guidance information in cooperative human-robot tasks
TLDR
A machine learning approach based on sensor data, such as accelerometer and pressure sensor information, is proposed for cooperative tasks between a human and a humanoid NAO robot and demonstrates the feasibility of this approach.
Dynamic Mode Decomposition for perturbation estimation in human robot interaction
TLDR
A machine learning approach which makes use of Dynamic Mode Decomposition (DMD) which is able to extract the dynamics of a nonlinear system and is well suited to separate noise from regular oscillations in sensor readings during cyclic robot movements under different behavior configurations is proposed.
Sparse Latent Space Policy Search
TLDR
A reinforcement learning method for sample-efficient policy search that exploits correlations between control variables, particularly frequent in motor skill learning tasks, and outperforms state-of-the-art policy search methods.
Learning Two-Person Interaction Models for Responsive Synthetic Humanoids
TLDR
This paper introduces a new imitation learning approach that is based on the simultaneous motion capture of two human interaction partners that allows the real-time generation of agent behaviors that are responsive to the body movements of an interaction partner.
Estimation of perturbations in robotic behavior using dynamic mode decomposition
TLDR
Results of a user study show that the DMD-based machine learning approach can be used to design physical human–robot interaction techniques that not only result in robust robot behavior but also enjoy a high usability.
A Data-Driven Method for Real-Time Character Animation in Human-Agent Interaction
TLDR
This work addresses the problem of creating believable animations for virtual humans that need to react to the body movements of a human interaction partner in real-time by extending the interaction mesh approach to prerecorded motion capture data of two interacting persons.
Kinesthetic Bootstrapping: Teaching Motor Skills to Humanoid Robots through Physical Interaction
TLDR
A new programming-by-demonstration method called Kinesthetic Bootstrapping for teaching motor skills to humanoid robots by means of intuitive physical interactions, which has been successfully applied to the learning of various complex motor skills such as walking and standing up.
Estimating perturbations from experience using neural networks and Information Transfer
TLDR
This paper presents an experience-based approach for accurately estimating external forces being applied to a robot without the need for a force-torque sensor and yields a substantial improvement in accuracy over force-Torque values provided by the robot firmware.
...
1
2
...