Paul-Gerhard Plöger

Identification of motion with echo state network

Echo State Networks (ESNs) use a recurrent artificial neural network as a reservoir. Finding a good one depends on choosing the right parameters for the generation of the reservoir, intuition and luck. The method proposed in this article eliminates the need for the tuning by hand by replacing it with a double evolutionary computation. First a broad search to find the right parameters which generate the reservoir is used. Then a search directly on the connectivity matrices fine-tunes the ESN. Both steps show improvements over other known methods for an experimental limit-cycle dataset of the Twin-Burger underwater robot.

Echo State Networks for Mobile Robot Modeling and Control

Applications of recurrent neural networks (RNNs) tend to be rare because training is difficult. A recent theoretical breakthrough [Jae01b] called Echo State Networks (ESNs) has made RNN training easy and fast and makes RNNs a versatile tool for many problems. The key idea is training the output weights only of an otherwise topologically unrestricted but contractive network. After outlining the mathematical basics, we apply ESNs to two examples namely to the generation of a dynamical model for a differential drive robot using supervised learning and secondly to the training of a respective motor controller.

Motion Control of Swedish Wheeled Mobile Robots in the Presence of Actuator Saturation

Swedish wheeled mobile robots have remarkable mobility properties allowing them to rotate and translate at the same time. Being holonomic systems, their kinematics model results in the possibility of designing separate and independent position and heading trajectory tracking control laws. Nevertheless, if these control laws should be implemented in the presence of unaccounted actuator saturation, the resulting saturated linear and angular velocity commands could interfere with each other thus dramatically affecting the overall expected performance. Based on Lyapunovs direct method, a position and heading trajectory tracking control law for Swedish wheeled robots is developed. It explicitly accounts for actuator saturation by using ideas from a prioritized task based control framework.

A Software System for Robotic Learning by Experimentation

The goal of this work is to develop an integration framework for a robotic software system which enables robotic learning by experimentation within a distributed and heterogeneous setting. To meet this challenge, the authors specified, defined, developed, implemented and tested a component-based architecture called XPERSIF. The architecture comprises loosely-coupled, autonomous components that offer services through their well-defined interfaces and form a service-oriented architecture. The Ice middleware is used in the communication layer. Additionally, the successful integration of the XPERSim simulator into the system has enabled simultaneous quasi-realtime observation of the simulation by numerous, distributed users.

Task Based Kinematical Robot Control in the Presence of Actuator Velocity Saturation and Its Application to Trajectory Tracking for an Omni-wheeled Mobile Robot

Swedish wheeled mobile robots have remarkable mobility properties allowing them to rotate and translate at the same time. Being holonomic systems, their kinematics model results in the possibility of designing separate and independent position and heading trajectory tracking control laws. Nevertheless, if these control laws should be implemented in the presence of unaccounted actuator peak velocity limits, the resulting saturated linear and angular velocity commands could interfere with each other thus dramatically affecting the overall expected performance. Based on Lyapunovs direct method, a position and heading trajectory tracking control law for Swedish wheeled robots is developed. It explicitly accounts for actuator velocity saturation by using ideas from a prioritized task based control framework.

Active Scene Text Recognition for a Domestic Service Robot

We developed a scene text recognition system with active vision capabilities, namely: auto-focus, adaptive aperture control and auto-zoom. Our localization system is able to delimit text regions in images with complex backgrounds, and is based on an attentional cascade, asymmetric adaboost, decision trees and Gaussian mixture models. We think that text could become a valuable source of semantic information for robots, and we aim to raise interest in it within the robotics community. Moreover, thanks to the robot’s pan-tilt-zoom camera and to the active vision behaviors, the robot can use its affordances to overcome hindrances to the performance of the perceptual task. Detrimental conditions, such as poor illumination, blur, low resolution, etc. are very hard to deal with once an image has been captured and can often be prevented. We evaluated the localization algorithm on a public dataset and one of our own with encouraging results. Furthermore, we offer an interesting experiment in active vision, which makes us consider that active sensing in general should be considered early on when addressing complex perceptual problems in embodied agents.

Motion Detection in the Presence of Egomotion Using the Fourier-Mellin Transform

Vision-based motion detection, an important skill for an autonomous mobile robot operating in dynamic environments, is particularly challenging when the robot’s camera is in motion. In this paper, we use a Fourier-Mellin transform-based image registration method to compensate for camera motion before applying temporal differencing for motion detection. The approach is evaluated online as well as offline on a set of sequences recorded with a Care-O-bot 3, and compared with a feature-based method for image registration. In comparison to the feature-based method, our method performs better both in terms of robustness of the registration and the false discovery rate.

On Recognizing Transparent Objects in Domestic Environments Using Fusion of Multiple Sensor Modalities.

Current object recognition methods fail on object sets that include both diffuse, reflective and transparent materials, although they are very common in domestic scenarios. We show that a combination of cues from multiple sensor modalities, including specular reflectance and unavailable depth information, allows us to capture a larger subset of household objects by extending a state of the art object recognition method. This leads to a significant increase in robustness of recognition over a larger set of commonly used objects.

Unexpected Situations in Service Robot Environment: Classification and Reasoning Using Naive Physics

Despite perfect functioning of its internal components, a robot can be unsuccessful in performing its tasks because of unforeseen situations. Mostly these situations arise from the interaction of a robot with its ever-changing environment. In this paper we refer to these unsuccessful operations as external unknown faults. We reason along the most frequent failures in typical scenarios which we observed during real-world demonstrations and competitions using our Care-O-bot III robot. These events take place in an apartment-like environment.

Component Based Architecture for an Intelligent Mobile Manipulator

We describe the development of an architecture for the DESIRE technology demonstrator based on principles of classical component based software engineering. The architecture is directly derived from the project requirements and resides on the concept of an Autonomous Component utilizing a smart feedback value called WishLists. This return type is able to provide expert advice about the reasons of occurring failures and give hints for possible recovery strategies. This is of key importance to advance towards robustness. The integration of an AI task planner allows the realization of higher flexibility, dependability and capability during task execution and may resolve conflicts between occurring WishLists. Furthermore the necessity of a central system-state model (Eigenmodel), which represents the current state and configuration of the whole system at runtime, is explained and illustrated. We conclude with some lessons learned.