Kirchner, Frank
Lade...
Preferred name
Kirchner, Frank
Official Name
Kirchner, Frank
ORCID
GND
6 Ergebnisse
Einstellungen
Gerade angezeigt 1 - 6 von 6
- Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Embedded multimodal interfaces in robotics: applications, future trends, and societal implicationsIn the past, robots were primarily used to perform work that was either too hard, too dangerous or simply too repetitive for humans, e.g., assembly line work, or work that could be done much faster by a robotic system, such as placement work. In the future, human-robot interaction will cover a much broader range of scenarios, from working interactively with humans in the context of industrial manufacturing to robotic appliances designed to care the elderly; even in applied areas, such as autonomous robots in space or operating underwater, the demand for robots to interact or to be intuitively controlled is growing. Hence, interaction will not only involve direct control of a robot or information exchange but will include direct cooperation and physical interaction between human and robot, i.e., humanrobot cooperation. While direct cooperation has tremendous advantages it also presents a number of significant challenges that should not be underestimated. Advanced interfaces to enable human-robot cooperation will be required to meet these challenges and the needs of human-robot interaction in the future.Wissenschaftlicher Artikel192 225 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Adaptive multimodal biosignal control for exoskeleton supported stroke rehabilitation(IEEE, 2017-11-30); ; ; ; A relevant issue of neuro-interfacing wearable robots in rehabilitation is the necessity to have training data, since the collection of sufficient data from patients within a reasonable recording time is not always possible. However, the use of historic data (e.g., session-to-session transfer, subject-to-subject transfer) can often lead to a reduction in classification performance which is affected by the selection of the historic data (i.e., which historic data was chosen for transfer). In this paper, we analyze two approaches to handle this reduction. First, we used incremental algorithms that can be adapted to the current session when trainable components (the spatial filter and the classifier) are transferred between different sessions. Second, we increased the number of sessions to learn more generalized models. To evaluate the approaches, we used electroencephalographic data that was recorded as training data for demonstrating our neuro-interfacing wearable robot in the application of upper-body sensorimotor rehabilitation. The data was collected from the same healthy subject on 14 different days (14 sessions). Our results showed that the use of a mixture of training sessions improved the classification performance. Further, we could show that the adaptive approaches contributed to less variability in performance that allows the system to be more robust. Hence, one can efficiently use both approaches (i.e., adapting and generalizing the models) depending on how much training data is available. Finally, the analyzed approaches are very promising to increase system applicability in upper-body sensorimotor robotic rehabilitation.Wissenschaftlicher Artikel93 102 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, PhysWM: Physical World Models for Robot LearningWithin the last decade machine learning methods have shown remarkable results in pattern recognition tasks and behavior learning. However, when applied to real-world robotics tasks, these approaches have limitations, such as sample inefficiency and limited generalization to out-of-distribution samples. Despite the availability of precise physics in simulation engines, model-based reinforcement learning (RL) resorts to learning an approximation of these dynamics. On the other hand, optimal control approaches often assume a static, complete model of the world, addressing the simulation-reality gap by adding low level controllers. In order to handle these issues, we propose a hybrid simulator consisting of differentiable physics and rendering modules, which employ symbolic representations and reduce the model complexity of neural policies, while retaining gradient computation for model and behavior optimization. Moreover, this reduced parametric representation enables the use of Bayesian inference to estimate the uncertainty over physical parameters. This uncertainty quantification allows us to generate a curriculum of exploration behaviors for continuously improving the world model.Konferenzbeitrag70 22 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, A Combined Rigid-Soft Thruster Based on Jetting Propulsion(IEEE, 2023); ; ; ; Ahstract- A new underwater thrust device is proposed in this work that makes use of a soft outer structure in combination with a parallel linkage and driven by a classical actuator. By merging soft and rigid parts, we hope to increase the performance of pulsed jet propulsion that plays a crucial role in attitude control for AUVs. But also simpler models for design and control can be applied by this approach. A specific linkage design for actuation, along with two different soft structures (mantles) are introduced and evaluated in experiments which indicate efficient thrust creation. Particle Image Velocimetry (PIV) experiments show the formation of vortex rings that suggest efficient propulsion, whereby the wider and more flexible mantel is characterized by higher momentum and thrust.Wissenschaftlicher Artikel109 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Design and field testing of a rover with an actively articulated suspension system in a Mars analog terrainThis study presents the electromechanical design, the control approach, and the results of a field test campaign with the hybrid wheeled-leg rover SherpaTT. The rover ranges in the 150 kg class and features an actively articulated suspension system comprising four legs with actively driven and steered wheels at each leg’s end. Five active degrees of freedom are present in each of the legs, resulting in 20 active degrees of freedom for the complete locomotion system. The control approach is based on force measurements at each wheel mounting point and roll–pitch measurements of the rover’s main body, allowing active adaption to sloping terrain, active shifting of the center of gravity within the rover’s support polygon, active roll–pitch influencing, and body-ground clearance control. Exteroceptive sensors such as camera or laser range finder are not required for ground adaption. A purely reactive approach is used, rendering a planning algorithm for stability control or force distribution unnecessary and thus simplifying the control efforts. The control approach was tested within a 4-week field deployment in the desert of Utah. The results presented in this paper substantiate the feasibility of the chosen approach: The main power requirement for locomotion is from the drive system, active adaption only plays a minor role in power consumption. Active force distribution between the wheels is successful in different footprints and terrain types and is not influenced by controlling the body’s roll–pitch angle in parallel to the force control. Slope-climbing capabilities of the system were successfully tested in slopes of up to 28° inclination, covered with loose soil and duricrust. The main contribution of this study is the experimental validation of the actively articulated suspension of SherpaTT in conjunction with a reactive control approach. Consequently, hardware and software design as well as experimentation are part of this study.Wissenschaftlicher Artikel166 282 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Kinematic Analysis of a Novel Parallel 2SPRR+1U Ankle Mechanism in Humanoid Robot(Springer, 2018-06-23); ; ; ; Parallel mechanisms are increasingly being used as modular subsystems in various robots and man-machine interfaces for their good stiffness, payload to weight ratio and dynamic properties. This paper presents the kinematic analysis of a novel parallel mechanism of type 2SPRR+1U for application as a humanoid ankle joint with two degrees of freedom. Tools from computational algebraic geometry are used to provide solutions to the forward and inverse kinematics problems. These are further used to characterize the workspace of this mechanism and provide description of its singularity curves. The kinematic analysis demonstrates that the chosen design can provide human ankle like workspace and good torque transmission capability without suffering from any singularities which makes it an ideal candidate for ankle joint module in humanoid robots.Wissenschaftlicher Artikel97 176