Florian Röhrbein

Chemnitz University of Technology · Neurorobotics

A fast and reliable visual search is crucial for representing visual scenes. The modulation of bottom-up attention plays an important role here. The knowledge about target features is often used to bias the bottom-up pathway. In this paper we propose a system which does not only make use of knowledge about the target features, but also uses already...

Behavioral studies for humans, monkeys and rats have shown that, while traversing an environment, these mammals tend to use different frames of reference and frequently switch between them. Those frames represent either allocentric, egocentric or route-centric views of the environment. However combinations of either of them are often deployed. Neur...

Anthropomimetic robots are robots that sense, behave, interact and feel like humans. By this definition, anthropomimetic robots require human-like physical hardware and actuation, but also brain-like control and sensing. The most self-evident realization to meet those requirements would be a humanlike musculoskeletal robot with a brain-like neural...

This monograph by Florian Röhrbein, Germano Veiga and Ciro Natale is an edited collection of 15 authoritative contributions in the area of robot technology transfer between academia and industry. It comprises three parts on Future Industrial Robotics, Robotic Grasping as well as Human-Centered Robots. The book chapters cover almost all the topics n...

A central research question in natural vision is how to allocate fixation to extract informative cues for scene perception. With high quality images, psychological and computational studies have made significant progress to understand and predict human gaze allocation in scene exploration. However, it is unclear whether these findings can be genera...

Currently, it is accepted that animal locomotion is controlled by a central pattern generator in the spinal cord. Experiments and models show that rhythm generating neurons and genetically determined network properties could sustain oscillatory output activity suitable for locomotion. However, current central pattern generator models do not explain...

Deep neural networks (DNNs) often perform poorly in the presence of domain shift and category shift. How to upcycle DNNs and adapt them to the target task remains an important open problem. Unsupervised Domain Adaptation (UDA), especially recently proposed Source-free Domain Adaptation (SFDA), has become a promising technology to address this issue...

Recent experiments indicate that pretraining of end-to-end reinforcement learning neural networks on general tasks can speed up the training process for specific robotic applications. However, it remains open if these networks form general feature extractors and a hierarchical organization that can be reused as in, for example, convolutional neural...

The spinal cord is engaged in all forms of motor performance but its functions are far from understood. Because network connectivity defines function, we explored the connectivity for muscular, tendon and tactile sensory inputs among a wide population of spinal interneurons in the lower cervical segments. Using low noise intracellular whole cell re...

Animal locomotion is hypothesized to be controlled by a central pattern generator in the spinal cord. Experiments and models show that rhythm generating neurons and genetically determined network properties could sustain oscillatory output activity suitable for locomotion. However, current CPG models do not explain how a spinal cord circuitry, whic...

The spinal cord is engaged in all forms of motor performance but its functions are far from understood. Because network connectivity defines function, we explored the connectivity for muscular, tendon and tactile sensory inputs among a wide population of spinal interneurons in the lower cervical segments. Using low noise intracellular whole cell re...

Locomotion control in mammals has been hypothesized to be governed by a central pattern generator (CPG) located in the circuitry of the spinal cord. The most common model of the CPG is the half center model, where two pools of neurons generate alternating, oscillatory activity. In this model, the pools reciprocally inhibit each other ensuring alter...

As a bio-inspired and emerging sensor, an event-based neuromorphic vision sensor has a different working principle compared to the standard frame-based cameras, which leads to promising properties of low energy consumption, low latency, high dynamic range (HDR), and high temporal resolution. It poses a paradigm shift to sense and perceive the envir...

Legged locomotion is a challenging task in the field of robotics but a rather simple one in nature. This motivates the use of biological methodologies as solutions to this problem. Central pattern generators are neural networks that are thought to be responsible for locomotion in humans and some animal species. As for robotics, many attempts were m...

Legged locomotion is a challenging task in the field of robotics but a rather simple one in nature. This motivates the use of biological methodologies as solutions to this problem. Central pattern generators are neural networks that are thought to be responsible for locomotion in humans and some animal species. As for robotics, many attempts were m...

Locomotion control in mammals has been hypothesized to be governed by a central pattern generator (CPG) located in the circuitry of the spinal cord. The most common model of the CPG is the half center model, where two pools of neurons generate alternating, oscillatory activity. In this model, the pools reciprocally inhibit each other ensuring alter...

In this paper we utilize Numenta's Hierarchical Temporal Memory implementation NuPIC for online visual motion pattern prediction and test its performance on virtual animations as well as real world human motion data. For evaluation we run a series of progressively more complex experiments testing specific capabilities: Prediction of fixed-time nois...

Neuromorphic vision sensors are bio-inspired cameras that naturally capture the dynamics of a scene with ultra-low latency, filtering out redundant information with low power consumption. Few works are addressing the object detection with this sensor. In this work, we propose to develop pedestrian detectors that unlock the potential of the event da...

A neuromorphic vision sensors is a novel passive sensing modality and frameless sensors with several advantages over conventional cameras. Frame-based cameras have an average frame-rate of 30 fps, causing motion blur when capturing fast motion, e.g., hand gesture. Rather than wastefully sending entire images at a fixed frame rate, neuromorphic visi...

Neuromorphic vision sensor is a new passive sensing modality and a frameless sensor with a number of advantages over traditional cameras. Instead of wastefully sending entire images at fixed frame rate, neuromorphic vision sensor only transmits the local pixel-level changes caused by the movement in a scene at the time they occur. This results in a...

Classical Conditioning plays a vital role for learning in every mammal. It is is based on unsupervised neural learning embodied in a physical body that is in continuous interaction with the environment. Embedding the Hierarchical Temporal Memory (HTM) in the closed-loop of the sensorimotor space of a Myorobotics tendondriven robotic arm we demonstr...

Biological intelligence processes information using impulses or spikes, which makes those living creatures able to perceive and act in the real world exceptionally well and outperform state-of-the-art robots in almost every aspect of life. To make up the deficit, emerging hardware technologies and software knowledge in the fields of neuroscience, e...

Learning-based methods have demonstrated clear advantages in controlling robot tasks, such as the information fusion abilities, strong robustness, and high accuracy. Meanwhile, the on-board systems of robots have limited computation and energy resources, which are contradictory with state-of-the-art learning approaches. They are either too lightwei...

Instead of wastefully sending entire images at fixed frame rates, neuromorphic vision sensors only transmits the local pixel-level changes caused by movement in a scene at the time they occur. This results in a stream of events, with a latency in the order of micro-seconds. While these sensors offer tremendous advantages in terms of latency and ban...

Timing and motor control are two classic cerebellar learning tasks. Starting from the seminal work of Marr[1] and Albus[2], a number of theories have been developed describing the underlying mechanisms[3,4]. In general, timing is regarded as the more fundamental task, since sequencing and timing of motor primitives is a prerequisite to dexterous mo...

We demonstrate a spiking neural network that extracts spatial depth information from a stereoscopic visual input stream. The system makes use of a scalable neuromorphic computing platform, SpiNNaker, and neuromorphic vision sensors, so called silicon retinas, to solve the stereo matching (correspondence) problem in real-time. It dynamically fuses t...

The field of neurorobotics encompasses the intersection of computational neuroscience and robotics. The TUM led Neurorobotics subproject of the Human Brain Project is actively researching concepts within the field and developing the tools to allow researchers to fully explore simulated robotics driven by computational neuroscience models. Further,...

Neurorobotic mimics the structural and functional principles of living creature systems. Modeling a single system by robotic hardware and software has existed for decades. However, an integrated toolset studying the interaction of all systems has not been demonstrated yet. We present a hybrid neuromorphic computing paradigm to bridge this gap by co...

Biometric security systems based on predefined speech sentences are extremely common nowadays, particularly in low-cost applications where the simplicity of the hardware involved is a great advantage. Audio spoofing verification is the problem of detecting whether a speech segment acquired from such a system is genuine, or whether it was synthesize...

Snake-like robots with 3D locomotion ability have significant advantages of adaptive travelling in diverse complex terrain over traditional legged or wheeled mobile robots. Despite numerous developed gaits, these snake-like robots suffer from unsmooth gait transitions by changing the locomotion speed, direction, and body shape, which would potentia...

The field of neurorobotics encompasses the intersection of computational neuroscience and robotics. The TUM-led neurorobotics subproject of the Human Brain Project is actively researching concepts within the field and developing the tools to allow researchers to fully explore simulated robotics driven by computational neuroscience models. Further,...

Snake-like robots with 3D locomotion ability have significant advantages of adaptive travelling in diverse complex terrain over traditional legged or wheeled mobile robots. Despite numerous developed gaits, these snake-like robots suffer from unsmooth gait transitions by changing the locomotion speed, direction, and body shape, which would potentia...

Combined efforts in the fields of neuroscience, computer science and biology allowed to design biologically realistic models of the brain based on spiking neural networks. For a proper validation of these models, an embodiment in a dynamic and rich sensory environment, where the model is exposed to a realistic sensory-motor task, is needed. Due to...

Neuro-evolutionary algorithms optimize the synaptic connectivity of sets of candidate neural networks based on a task-dependent fitness function. Compared to the commonly used methods from machine learning, many of them not only support the adaptation of connection weights but also of the network topology. However, the evaluation of the current fit...

The evolution of the central nervous system of limbed vertebrates has strongly been driven by the need to move with small nutritional requirements. While the brain still consumes 20% of the resting metabolic energy, the evolved neural motor circuits are highly optimized, as illustrated by the comparison to the controller hardware in bio-mimicking r...

We present a simple cerebellar model[1], real-time simulated on the SpiNNaker platform[2], and connected[3] to musculoskeletal robots[4]. We demonstrate that the same network can learn two seemingly different tasks, antagonistic motor control[4] and delay timing, using the exact same learning mechanism. Whereas conventional models of cerebellar del...

Anthropomimetic robots sense, behave, interact, and feel like humans. By this definition, they require human-like physical hardware and actuation but also brain-like control and sensing. The most self-evident realization to meet those requirements would be a human-like musculoskeletal robot with a brain-like neural controller. While both musculoske...

Over the last years, the amount of research performed in the field of spik-ing neural networks has been growing steadily. Spiking neurons are modeled to approximate the complex dynamic behavior of biological neurons. They communicate via discrete impulses called spikes with the actual information being encoded in the timing of these spikes. As alre...

Objectives Even today's most advanced robots perform poorly at simple everyday tasks carried out routinely by humans and animals. This has very early motivated researchers to adopt neurobiological principles of cognition and control in robotics, yielding numerous approaches based on artificial neural networks and machine learning. However, many of...

Bayesian networks (BNs) are an essential tool for the model-ing of cognitive processes. They represent probabilistic knowledge in an intuitive way and allow to draw inferences based on current evidence and built-in hypotheses. In this paper, a structure learning scheme for BNs will be examined that is based on so-called Child-friendly Parent Divorc...

Roboticists have early recognized the high potential of neuro-biological control structures for robotic applications. However, limited processing power and the lack of appropriate models and tools shifted the focus of research far away from biological neural networks. Today, combined efforts in the fields of neurosciences, computer science and many...

Flexible and compliant real-time control of artificial limbs is a challenging endeavor for conventional control algorithms. Conversely, the neuro-control of biological limbs is usually highly stable despite the apparent complex nonlinearities and flexibilities. Part of this is caused by cerebellar fast learning of motor actions embedded in a comple...

The application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even...

In this contribution the authors examine robotics research itself. We look at the data which the European funded ECHORD project (European Clearing House for Open Robotics Development) generated. The project began in January 2009 with the ambitious goal of bringing togeth-er European robotics manufacturers with the European research institutions and...

Motion detection is an essential and basic feat of any natural vision system. The speed and efficiency found in natural systems is hard to match by engineered artifacts. The limiting factors are slow frame-based cameras on the one hand, and computationally costly data-processing on sequential computers on the other hand. We circumvent both by utili...

In this contribution, we look at technology transfer in robotics. Generally, there is a delay between a science-push and a market-pull. In order of finding means to decrease this lag, we are going to look at the causes of this effect and at the means for improving technology transfer. For this purpose, we use a variety of data sources which shed lig...

The European funded ECHORD project European Clearing House for Open Robotics Development began in January 2009 with the ambitious goal of bringing together European robotics manufacturers with the excellent European research institutions. Europe has a very strong robot industry and there is significant research potential as well as technological kn...

Dr. Alexander Waibel is a Professor of Computer Science at Carnegie Mellon University, Pittsburgh and at the Karlsruhe Institute of Technology, Germany. He is the director of the International Center for Advanced Communication Technologies, a joint center at eight international research institutions world-wide. The Center develops multimodal and mu...

Organisms are equipped with value systems that signal the salience of environmental cues to their nervous system, causing a change in the nervous system that results in modification of their behavior. These systems are necessary for an organism to adapt its behavior when an important environmental event occurs. A value system constitutes a basic as...

A central research question in natural vision is how to allocate fixation to extract informative cues for scene perception. With high quality images, psychological and computational studies have made significant progress to understand and predict human gaze allocation in scene exploration. However, it is unclear whether these findings can be genera...

In this paper we present an approach for contour based object representation. To this end we use a curvature signal gained by a level-set segmentation method. The advantage of that curvature signal is that it generates no computational overhead as it is a byproduct of standard level-set segmentation methods. Different methods for the description of...

The autonomous learning of concept hierarchies is still a matter of research. Here we present a learning schema for Bayesian networks which results in a nested structure of sub- and superclass relationships. It is based on so-called parent divorcing but exploits the similarity of all nodes involved as expressed by their connectivity pattern. If the...

Semantic systems for the representation of declarative knowledge are usually unconnected to neurobiological mechanisms in the brain. In this paper we report on efforts to bridge this gap by proposing a neural-symbolic network based on processing principles of the cortical column. We show how a locally controlled activation spread on conceptual node...