Capacitive sensors based human-machine interfaces (HMI) have revolutionised in-cabin user interaction in automobiles. However, robust functionality and stability of the sensors in dynamic environmental conditions necessitate profound domain expertise coupled together with computationally intensive multi-physics simulations. As a promising alternative, this paper investigates the application of Physics-informed neural networks (PINNs) as a surrogate sensor model to capture the electrostatic behaviour of a capacitive sensor interacting with a conductor such as a human finger. Maxwell's equations are the fundamental governing laws for understanding the interplay of electric field interactions in a capacitive sensor. The PINN model solves these electrostatic equations for different positions of a finger interacting with the sensor. Given a finger position and a spatial coordinate in a 3D domain encompassing the finger, sensor, and PCB, the trained surrogate model is capable of predicting key electrostatic properties such as electric potential, electric field distribution, and charge density. The governing equations are incorporated into the neural network's loss function to capture the underlying physics. The performance of the model is evaluated on a wide range of unseen test scenarios, encompassing a diverse set of finger positions. Additionally, the capacity of the learnt PINN model to emulate a real-world sensor array setup is presented. Results demonstrate the significant potential of PINNs as surrogate models in electrostatics, thereby paving the way for a promising future in sensor design optimisation and degradation analysis.

The design of visual robotic behaviors constitutes a substantial challenge. It requires to draw meaningful relation ships and constraints between the acquired visual perception and the geometry of the environment both empirically and programmatically. This contribution proposes a novel robot learning framework to classify and acquire scenario specific autonomous behaviors through demonstration. During demonstration, robocentric 3D range and omnidirectional images are recorded as training instances of typical robot navigation situations pertaining to different contexts in multiple indoor scenarios. A programming by demonstration approach generalizes the demonstrated trajectories to a general mapping between visual features extracted from the omnidirectional image onto a corresponding robot motion. The approach is able to distinguish among different traversing scenarios and further identifies the best matching context within the scenario to predict an appropriate robot motion. As a comparison to context matching, the behaviors are trained by means of an artificial neural network and its generalization ability is evaluated against the former. The experimental validation on the mobile robot indicates that the acquired visual behavior is robust and generalizes meaningful actions beyond the specific environments and scenarios presented during training.

This paper presents a novel approach for floor obstacle segmentation in omnidirectional images which rests upon the fusion of multiple classification generated from heterogeneous segmentation schemes. The individual naive Bayes classifiers rely on different features and cues to determine a pixel's class label. Ground truth data for training and testing the classifiers is obtained from the superposition of 3D scans captured by a photonic mixer device camera. The classification is supported by edge detection which indicate the presence of obstacles and sonar range data. The complementary expert decisions are aggregated by stacked generalization, behavior knowledge space or voting combination. The combined floor classifier achieves a classification accuracy of up to 0.96 true positive rate with only 0.03 false positive rate. A robust robot navigation is accomplished by arbitration among a reactive obstacle avoidance and a corridor following behavior using the robots local free space as perception.

This paper describes a novel approach for purely vision based mobile robot navigation. The visual obstacle avoidance and corridor following behavior rely on the segmentation of the traversable floor region in the omnidirectional robocentric view. The image processing employs a supervised approach in which the segmentation optimal with respect to the appearance of the local environment is determined by cross validation over 3D scans captured by a photonic mixer device (PMD) camera. The range data in the front view provides the seeds and validation data to supervise the appearance based segmentation in the omniview. Segmentation relies on histogram backprojection which maintains separate appearance models for floor, obstacles and background. A naive Bayes classifier predicts the occupancy of the robots local environment by fusing the evidence provided by different segmentations and models. The classification error is analyzed on ground truth data generated by a PMD camera and manually segmented scenes. The scheme is highly robust with respect to ambiguous and misleading visual appearances of obstacles and floor, thus enabling the robot to navigate safely in unstructured environments of diverse appearance, texture and illumination. The proposed vision algorithm and the navigation behavior demonstrate a robust performance in extensive robotic experiments across several hours of autonomous operation.