A Simple Ontology of Manipulation Actions Based on Hand-Object Relations

Accelerated Sensorimotor Learning of Compliant Movement Primitives

Action-grounded push affordance bootstrapping of unknown objects

Action-grounded surface geometry and volumetric shape feature representations for object affordance prediction

Active humanoid vision and object classification

Adaptation of bimanual assembly tasks using iterative learning framework

Adaptive Control of Exoskeleton Robots for Periodic Assistive Behaviours Based on EMG Feedback Minimisation

scientific article (publication date: 2016)

Analysis of human peg-in-hole executions in a robotic embodiment using uncertain grasps

Applying statistical generalization to determine search direction for reinforcement learning of movement primitives

scholarly article published November 2012

Autonomous acquisition of pushing actions to support object grasping with a humanoid robot

Bimanual human robot cooperation with adaptive stiffness control

Bio-inspired learning and database expansion of Compliant Movement Primitives

CB: A Humanoid Research Platform for Exploring NeuroScience

CB: Exploring neuroscience with a humanoid research platform

Coaching: An Approach to Efficiently and Intuitively Create Humanoid Robot Behaviors

Comparison of action-grounded and non-action-grounded 3-D shape features for object affordance classification

Constraining movement imitation with reflexive behavior: Robot squatting

Coupling Movement Primitives: Interaction With the Environment and Bimanual Tasks

article published in 2014

Distributed visual attention on a humanoid robot

Exploiting previous experience to constrain robot sensorimotor learning

Exploration in structured space of robot movements for autonomous augmentation of action knowledge

Extracting Objects for Aerial Manipulation on UAVs Using Low Cost Stereo Sensors

scientific article

Fast programming of Peg-in-hole Actions by human demonstration

Force adaptation with recursive regression Iterative Learning Controller

Foveated vision systems with two cameras per eye

scholarly article

From Sensorimotor Primitives to Manipulation and Imitation Strategies in Humanoid Robots

Generalization of discrete Compliant Movement Primitives

Generalization of example movements with dynamic systems

Generalization of orientational motion in unit quaternion space

Human-robot cooperation through force adaptation using dynamic motion primitives and iterative learning

Integrating surface-based hypotheses and manipulation for autonomous segmentation and learning of object representations

article published in 2012

Learning Actions from Observations

Learning Compliant Movement Primitives Through Demonstration and Statistical Generalization

Learning and adaptation of periodic motion primitives based on force feedback and human coaching interaction

Learning feature representations for an object recognition system

Learning of parametric coupling terms for robot-environment interaction

Learning primitive actions through object exploration

Modulation of motor primitives using force feedback: Interaction with the environment and bimanual tasks

Motion capture and reinforcement learning of dynamically stable humanoid movement primitives

scholarly article published May 2013

Motion imitation and recognition using parametric hidden Markov models

Object Learning through Interactive Manipulation and Foveated Vision

article

Object segmentation and learning through feature grouping and manipulation

On-line coaching of robots through visual and physical interaction: Analysis of effectiveness of human-robot interaction strategies

On-line periodic movement and force-profile learning for adaptation to new surfaces

Online approach for altering robot behaviors based on human in the loop coaching gestures

Online learning of task-specific dynamics for periodic tasks

Optimizing grippers for compensating pose uncertainties by dynamic simulation

Optimizing parameters of trajectory representation for movement generalization: robotic throwing

Orientation in Cartesian space dynamic movement primitives

article published in 2014

Peg-in-Hole assembly under uncertain pose estimation

Physical interaction for segmentation of unknown textured and non-textured rigid objects

Planning of joint trajectories for humanoid robots using B-spline wavelets

Pushing and grasping for autonomous learning of object models with foveated vision

article

Reactive, task-specific object manipulation by metric reinforcement learning

scholarly article published July 2015

Real-time 3D marker tracking with a WIIMOTE stereo vision system: Application to robotic throwing

Real-time generalization and integration of different movement primitives

Redundant control of a humanoid robot head with foveated vision for object tracking

Reinforcement learning of ball-in-a-cup playing robot

scholarly article published December 2011

Rich periodic motor skills on humanoid robots: Riding the pedal racer

Robot Skill Acquisition by Demonstration and Explorative Learning

Robot learning by Gaussian process regression

Segmentation and learning of unknown objects through physical interaction

Sensorimotor processes for learning object representations

Shaping Biological Motion: Adding realistic form cues to biological motion displays

Solving peg-in-hole tasks by human demonstration and exception strategies

article published in 2014

Speed profile optimization through directed explorative learning

Stereo grouping for model-based recognition

article

Stereo-based Markerless Human Motion Capture for Humanoid Robot Systems

Structural Bootstrapping—A Novel, Generative Mechanism for Faster and More Efficient Acquisition of Action-Knowledge

Structural bootstrapping at the sensorimotor level for the fast acquisition of action knowledge for cognitive robots

Synthesizing compliant reaching movements by searching a database of example trajectories

Synthesizing goal-directed actions from a library of example movements

Task adaptation through exploration and action sequencing

article published in 2009

The Karlsruhe Humanoid Head

Toward a library of manipulation actions based on semantic object-action relations

Trajectory representation by nonlinear scaling of dynamic movement primitives

Transfer of assembly operations to new workpiece poses by adaptation to the desired force profile

Transfer of contact skills to new environmental conditions

Using humanoid robots to study human behavior

Velocity adaptation for self-improvement of skills learned from user demonstrations