Biosensors measure signals from the human body, and usually process them with a small ML model on simple hardware.When a new person starts using such a device, a domain adaptation problem arises.We consider the case where no labels are known for the new person, but data (including labels) from several other people are available (unsupervised, multi-source).As an application scenario, we look at a shoe insole with 3-8 pressure sensors that estimates how much weight/force is put on the foot (regression problem).We propose a distance measure between a source and target domain, and a combination of all source models.Experiments on real world data from 13 persons show that our method outperforms all other tested methods by a good margin.

Locomotion in animals provides a model for adaptive behavior as it is able to deal with various kinds of perturbations. Work in insects suggests that this evolved flexibility results from a modular architecture, which can be characterized by a recurrent neural network allowing for various emerging attractor states. Whereas a lower control-level coordinates joint movements on a short timescale, a higher-level handles action selection on longer timescales. Implementation of such a control system on a walking hexapod robot was able to deal with various walking patterns including disturbances such as uneven terrain or loss of a leg. Here, we propose a cognitive expansion to the adaptive control system that allows dealing with novel challenging situations. This approach makes use of an internal simulation-based planner that is triggered when the model-free controller fails to recover from an unstable pose. Using a grounded internal body model, the planner then tries, in internal simulation, different solutions out of context, and thus, proposes a new plan to be executed on the real robot. We demonstrate the feasibility of this control approach for walking over terrain with uncertain footholds in three scenarios.

Adapting the concept of continuous tracks that are propelled and guided by wheels, a self-propelled continuous-track-robot has been designed and built. The robot consists of actuated chain segments, thus enabling it to change its form, independent of guiding mechanisms. Using integrated sensors, the robot is able to adapt to the terrain and to overcome obstacles. This allows the robot to “roll” and climb in two dimensions. Possible extensions of the concept to three-dimensional navigation are presented as an outlook.

The main advantage of multi-legged robots is the ability to traverse uneven terrain and to overcome obstacles that would impede the movement of a wheeled robot. Compliant joint drives can further improve the performance of legged robot systems by considerably reducing the problems associated with uneven or slippery footholds. Small changes of the foot position in uneven terrain are compensated by the passive joint compliance without the need for fast contact detection and controller responses while the mechanical tension is reduced. On rougher terrain with bigger elevations/depressions of the surface structure, however, a reliable ground contact detection and stance height regulation for each leg is required to distribute the weight of the robot evenly among the legs on ground during stance phase. This work presents a concept that allows the inherently compliant hexapod robot HECTOR to walk on uneven terrain and to overcome moderate obstacles by means of a decentralized walking controller. An important prerequisite is the availability of inherently compliant joint drives with an increased power/weight-ratio.

Recently, system designers are facing the challenge of developing systems that have diverse features, are more complex and more powerful, with less power consumption and reduced time to market. These contradictory constraints have forced technology providers to pursue design solutions that will allow design teams to meet the above design targets. In that respect, this paper introduces an innovative technology platform, called MORPHEUS, which intents to provide complete design framework for dealing with the aforementioned challenges. MORPHEUS consists of a state of the art architecture that encompasses heterogeneous reconfigurable accelerators for implementing on the same hardware architecture applications with varying characteristics and a tool chain that, through a software oriented approach, eases the implementation of highly complex applications with heterogeneous characteristics. The proposed approach has been tested and evaluated through state of the art cases studies borrowed from complementary application domains.

While internal models are recruited in many tasks and can subserve in this way perception and cognition, it is important that they are grounded and embodied in sensorimotor representation. In this paper we analyze an internal model of the body and show how it can be used for motor control. We extend the Mean of Multiple Computation principle to a dual quaternion representation of transformation and show how this can be directly applied to the control of a simulated robot leg. The model is encoded as a recurrent neural network acting as an autoassociator that is able to solve any kinematic problem in an iterative fashion. We will analyze the convergence properties, especially when additional constraints (acting on the joint level) are introduced that restrict the attractor space.

While internal models are a prerequisite for higher-level function, they have to be grounded in lower-level function serving sensorimotor control. In this paper we introduce an internal body model for the control of a hexapod walker. The internal model deals with a highly complex robotic structure of 22 degrees of freedom and coordinates the single joint movements to achieve an overall stable and adaptive walking behavior. It is implemented as a hierarchical recurrent neural network consisting of different levels of abstraction which are tightly intertwined. We demonstrate the feasibility of the concept by applying the model to a simulated robot and show how the different levels of the body model interact and how this allows to scale the model even further. While the internal model is used in this context explicitly for motor control, it is also a predictive model and can be applied for sensor fusion. We discuss how in this way such an internal model offers the flexibility to be utilized in motor control and to be used for planning ahead by a cognitive expansion of the movement controller.

Biological systems are generally able to change joint stiffness by co-activation of antagonistic muscles. A close study of the stiffness generated in an antagonistically actuated, muscle-driven hinge joint has shown that in dependence of some muscle and joint parameters, positions in the angular joint space can be found for which different levels of co-activation do not generate any change in stiffness (stiffness nodes). Consequently, for joint positions in the vicinity of such a node, any stiffness controller is expected to fail. This paper proposes a novel stiffness node controller whose objective is to shift the stiffness node away when the joint approaches the angular position of the node. In order to test the ability of the node controller, a simulation of simultaneous torque and stiffness control is performed. In the simulation, two different cases will be examined. In the first case, the joint position is in the vicinity of a node and the node controller is switched off. In this situation the torque and stiffness controllers alone are not able to reach their desired values. In the second case the node controller is switched on which leads to a node displacement and - as a consequence - the controllers reach their requested values.

This paper describes the implementation of an FPGA prototype of an application based on embedded ASIC technology. The overall goal is to implement a system that can monitor an Ethernet data stream and extracts configuration data marked by the EtherType field in the Ethernet header. For evaluation the application is implemented on a prototype consisting of two XILINX FPGA boards. Since the target platform is an ASIC with embedded reconfigurable architectures the prototype is divided in the corresponding parts. One board emulates the embedded reconfigurable architecture that contains the Ethernet MAC. Ethernet packets can reconfigure this MAC. The second board emulates the static part of the application that controls the reconfiguration process.

Linear feedback shift registers (LFSRs) are common structures in many application fields, including cryptography, digital broadcasting and communication. High- throughput requirements need highly parallel implementations, usually accomplished in state of the art system on chips (SoCs) with application specific coprocessors. Although this approach achieves the required performance, it rapidly shows lack of flexibility when those devices are proposed, as an example, for multi-standard modems or for security applications in which run-time update can provide added value. This paper shows the implementation of parallel LFSR-based applications on an embedded adaptive DSP featuring a Pipelined Configurable Gate Array (PiCoGA). With respect to standard embedded FPGAs, pipelined devices usually provide better performance, e.g. in terms of speed, but they commonly show the undeniable drawback of additional design constraints. As a test-case, we consider the implementation of the 32-bit CRC used in the Ethernet standard that achieves on the target architecture up to ~25Gbit/sec throughput, with a parallel LFSR processing 128 bit at time, which is comparable to the performance offered by some ASIC devices.

Walknet, a biological inspired neural network, has been proposed to control walking of a 6-legged; 18 DoF walker. Control of stance movement is difficult because all legs in stance are mechanically coupled. Based on the idea of velocity feedback, recently a specific revision, local positive velocity feedback, has been proposed to solve this problem using an extremely decentralised architecture. In this control scheme the locally measured joint velocity of an elastic joint is fed into the same joint in the next time step to maintain the movement. At the same time an additional part of the same joint controller observes the mechanical joint power to confine the positive feedback. In this paper, we show that this principle can actually be successfully applied to move a complete 6-legged system. This is tested using a dynamic simulation.

Reconfigurable architectures and NoC (Network-on-Chip) communication systems have introduced new research directions for technology and flexibility issues, which have been largely investigated in the last decades. Exploiting the flexibility of reconfigurable architectures, the run-time adaptivity through run-time reconfiguration, opens a new area of research by considering dynamic reconfiguration. Since software parts of an embedded system can also be included into reconfigurable hardware by integration of an IP-based microcontroller, the reconfigurable architecture provides a flexible, multi-adaptive heterogeneous platformfor HW/SW co-design. In this paper, we present the European Integrated Project MORPHEUS (IST 027342). Its goal is to develop new heterogeneous reconfigurable SoCs with various sizes of reconfiguration granularity and to provide an integrated toolset of spatial and sequential design that can be used for mapping and execution of the target applications. Additionally a NoC approach is included in order to demonstrate the mentioned benefits and scalability for actual and future SoC design. The power of this approach will be demonstrated with four applications from the industrial environment.

Formal methods such as automated model checking are used commercially for digital circuit design verification. These techniques find errors early in the product cycle, which improves development time and cost. By contrast, the current practice in complex system design is to specify system functions and protocol details in natural language. Some errors are found early by manual inspections, but others are only revealed during implementation testing or by costly field failures. We describe our application of formal specification and model checking to real telecom product development, and enumerate the classes of specification errors that these formal techniques revealed at an early stage of the development cycle

Starting from studies which revealed that positive feedback is found in the control system for walking in arthropods, we have constructed a new positive feedback driven joint that can be used for solving compliant motion tasks. We propose two different joint constructions each of which shows passive compliance. Based on these joints we introduce three different local positive velocity feedback (LPVF) controllers and discuss their properties in the context of motion generation in closed kinematic chains. The third circuit named undelayed dLPVF is used for the control of a compliant planar manipulator which turns a crank. Our concept is of highly decentralized nature and follows the idea of embodiment. In our case this means that a process which is controlled by LPVF controllers reveals its nature when the controllers interact with this process.

In this paper we present a mobile robot system that is capable of automating the sample management in a biotechnological laboratory. The system consists of a mobile platform and a robot arm. It can navigate freely in the laboratory and operate standard devices needed for the sample management. The platform uses an extended Kalman filter for localization and A* algorithm for path planning on a tangent graph computed from the laboratory's map. Motion execution has been designed to be as predictable as possible to not irritate, disturb or harm human personnel. The robot arm uses color vision to detect devices and compensate for positioning errors. The parameters and tasks needed to operate the devices are specified in simple scripts to allow quick and easy adaptations to other situations.