A5048975019- Robot Manipulation and Learning
- Robotic Locomotion and Control
- EEG and Brain-Computer Interfaces
- Prosthetics and Rehabilitation Robotics
- Advanced Sensor and Energy Harvesting Materials
- Muscle activation and electromyography studies
- Tactile and Sensory Interactions
- Neural dynamics and brain function
- Reinforcement Learning in Robotics
- Human Pose and Action Recognition
- Neuroscience and Neural Engineering
- Modular Robots and Swarm Intelligence
- Social Robot Interaction and HRI
- Robotic Path Planning Algorithms
- Action Observation and Synchronization
- Teleoperation and Haptic Systems
- Gaze Tracking and Assistive Technology
- Robotic Mechanisms and Dynamics
- Robotics and Sensor-Based Localization
- Robotics and Automated Systems
- Advanced Vision and Imaging
- Soft Robotics and Applications
- Advanced Memory and Neural Computing
- Stroke Rehabilitation and Recovery
- Neural and Behavioral Psychology Studies
Technical University of Munich
2016-2025
Fraunhofer Institute for Cognitive Systems
2016-2025
Yangzhou University
2025
Institut des Sciences Cognitives
2011-2019
Ludwig-Maximilians-Universität München
2013-2017
The University of Tokyo
2017
Xi'an Institute of Optics and Precision Mechanics
2016
GlobalFoundries (Germany)
2015
University of Bremen
2013
Institut Lavoisier de Versailles
2008-2009
A soft touch Measuring the force it takes for a hand to grasp an object requires sensors be placed on fingertips, but these will interfere with or affect how much ends up being applied. Lee et al. developed nanomesh sensor built from series of electrospun materials (see Perspective by Liu). Using robotic tester, they show that this device can repeatably detect pressure involved in gripping object. They also attached human fingers and does not used Science , issue p. 966 ; see 910
Brain-machine interfaces (BMIs) provide a new assistive strategy aimed at restoring mobility in severely paralyzed patients. Yet, no study animals or human subjects has indicated that long-term BMI training could induce any type of clinical recovery. Eight chronic (3-13 years) spinal cord injury (SCI) paraplegics were subjected to (12 months) with multi-stage BMI-based gait neurorehabilitation paradigm locomotion. This combined intense immersive virtual reality training, enriched...
This paper proposes an effective framework of human-humanoid robot physical interaction. Its key component is a new control technique for full-body balancing in the presence external forces, which presented and then validated empirically. We have adopted integrated system approach to develop humanoid robots. Herein, we describe importance replicating human-like capabilities responses during human-robot interaction this context. Our controller provides gravity compensation, making passive...
In this paper, we present a new generation of active tactile modules (i.e., HEX-O-SKIN), which are developed in order to approach multimodal whole-body-touch sensation for humanoid robots. To better perform like humans, robots need the variety different sensory modalities interact with their environment. This calls certain robustness and fault tolerance as well an intelligent solution connect robot. Each HEX-O-SKIN is small hexagonal printed circuit board equipped multiple discrete sensors...
Non-invasive, electroencephalography (EEG)-based brain-computer interfaces (BCIs) on motor imagery movements translate the subject's intention into control signals through classifying EEG patterns caused by different imagination tasks, e.g., hand movements. This type of BCI has been widely studied and used as an alternative mode communication environmental for disabled patients, such those suffering from a brainstem stroke or spinal cord injury (SCI). Notwithstanding success traditional...
This article presents a holistic approach to the engineering of an artificial robot skin for robots. An example multimodal cell is given, one that supports multiple human-like sensing modalities, and support network also provided; this essential form large-area patches in order cover surfaces The elements efficiently handling large amount tactile data are explained. A general control framework, which robots commanded position, velocity, torque, provided validated. Several applications will...
In this paper we describe a learning framework for central pattern generator (CPG)-based biped locomotion controller using policy gradient method. Our goals in study are to achieve CPG-based walking with 3D hardware humanoid and develop an efficient algorithm CPG by reducing the dimensionality of state space used learning. We demonstrate that appropriate feedback can be acquired within few thousand trials numerical simulations obtained simulation achieves stable physical robot real world....
This paper presents a 50-d.o.f. humanoid robot, Computational Brain (CB). CB is robot created for exploring the underlying processing of human brain while dealing with real world. We place our investigations within real—world contexts, as humans do. In so doing, we focus on utilizing system that closer to humans—in sensing, kinematics configuration and performance. present real-time network-based architecture control all 50 d.o.f. The controller provides full position/velocity/force sensing...
Flexible electronics has huge potential to bring revolution in robotics and prosthetics as well about the next big evolution industry. In related applications, it is expected revolutionise way with which machines interact humans, real-world objects environment. For example, conformable electronic or tactile skin on robot's body, enabled by advances flexible electronics, will allow safe robotic interaction during physical contact of robot various objects. Developing a conformable, bendable...
Humans are particularly skilled in mentalizing, the inference of other agents' hidden mental states. Here we question whether activity brain areas involved mentalizing is specific to processing states or can be generalized non-mental by investigating responses during interaction with an artificial agent. Participants were scanned using fMRI interactive rock-paper-scissors games while believing opponent was a fellow human (Intentional agent), humanoid robot endowed algorithm developed win...
In this paper, we present a new approach to realize whole-body tactile interactions with self-organizing, multi-modal artificial skin on humanoid robot. We, therefore, equipped the whole upper body of HRP-2 various patches CellulARSkin – modular skin. order automatically handle potentially high number sensor cells and motors units, robot uses open-loop exploration motions, distributed accelerometers in cells, acquire its self-centered sensory-motor knowledge. This self-knowledge is then...
Recently, there has been a growing interest in biologically inspired biped locomotion control with Central Pattern Generator (CPG). However, few experimental attempts on real hardware 3D humanoid robots have yet made. Our goal this paper is to present our achievement of using neural oscillator applied robot, QRIO. We employ reduced number oscillators as the CPG model, along task space Cartesian coordinate system and utilizing entrainment property establish stable walking gait. verify...
As humanoid robots become more commonplace in our society, it is important to understand the relation between humans and robots. In human face-to-face interaction, observation of another individual performing an action facilitates execution a similar action, interferes with different action. This phenomenon has been explained by existence shared neural mechanisms for perception actions, which would be automatically engaged individual's one interference experiment, null was reported when...
Biological systems seem to have a simpler but more robust locomotion strategy than that of the existing biped walking controllers for humanoid robots. We show robot can step and walk using simple sinusoidal desired joint trajectories with their phase adjusted by coupled oscillator model. use center-of-pressure location velocity detect lateral dynamics. This information is used modulate trajectories. do not explicitly dynamical parameters robot. hypothesize similar mechanism may exist in...
In this paper, we propose a set of novel tactile descriptors to enable robotic systems extract robust information during object explorations, regardless the number sensors, sensing technologies, type exploratory movements, and duration objects' surface exploration. The performance robustness are verified by testing on four different technologies (dynamic pressure accelerometers, capacitive impedance electrode arrays) with two platforms (one anthropomorphic hand one humanoid), large objects...
Tactile sensing feedback provides feasible solutions to robotic dexterous manipulation tasks. In this paper, we present a novel tactile-based framework for detecting/correcting slips and regulating grasping forces while manipulating deformable objects with the dynamic center of mass. This consists tangential force based slip detection method deformation prevention approach relying on weight estimation. Moreover, propose new strategy heavy objects. Objects different stiffnesses, surface...