Compact omnidirectional mobile robots are required to automate transportation of raw materials, products, etc. within an industrial plant. This paper focuses on omni wheel robots with low vibration and wheel arrangements that contribute to compactness. Due to its wheels’ configuration, our proposed compact robot may have different sensitivity to noise (controller) and different performance (errors) when following a predetermined path, compared to conventional ones. Using a simple DC motor, a robot with the proposed arrangement and a conventional robot run along a predetermined path. A linear–quadratic regulator that is processed lightly is used to control the robots for practicality. As a result, the robot’s trajectory in the proposed arrangement showed a distortion different from that of the conventional type. The distortion of the trajectory was attributed to the inability of the DC motor to rotate stably at low speed. The different distortions exhibited suggest that the wheel arrangement changes the effect of imperfect control on the robot’s motion. In addition, the proposed arrangement showed the possibility of being suitable for a transport robot because the wheels are placed in the four corners of the robot, facing forward, backward, left, and right.

In this work we propose a novel approach for fusing information from multiple access points in order to enhance WiFi-based self-localization. A common approach for designing WiFi based localization systems is to learn location-to-signal strength mappings for each access point in an environment. Each mapping is then used to compute the likelihood of the robot's location conditioned on sensed signal strength data, yielding as many likelihood functions as mappings available. Office buildings typically have from several tens to few hundreds of access points, making it essential to properly combine all available likelihoods into a single, coherent, joint likelihood that yields precise likelihoods, yet is not overconfident. While most research has focused on techniques for learning these mappings and better data acquisition; research on techniques to adequately fuse them has been neglected. Our approach for data information fusion is based on information theory and yields considerably better joint distributions than previous approaches. Furthermore, through extensive testing we show that these joint likelihoods considerably increases the system's localization performance.

Indoor robot localization systems using wireless signal measurements have gained popularity in recent years, as wireless Local Area Networks can be found practically everywhere. In this field, a popular approach is the use of fingerprinting techniques, such as Gaussian Processes. In our approach, we improve Gaussian Processes based mapping using path loss models as priors. Path loss models encode information regarding the signal propagation phenomena into the mapping. Our approach first fits training data to a simple path loss model, and then trains a zero-mean Gaussian Process with the mismatches between the models and the data. Signal strength mean predictions are done using both the path loss model and the Gaussian Process output, while variances are calculated by bounding the Gaussian Process variance using the path loss models. Notably, the main improvement generated by our approach is not an enhanced mean value prediction, but rather a better model variance prediction. This translates into better likelihood estimations, leading to higher localization accuracy. Experiments using data acquired in an indoor environment and our approach as the perceptual likelihood of a dual Monte Carlo localization algorithm are used to demonstrate this improvement. Furthermore, this idea can be extrapolated to other fingerprinting techniques and to applications other than wireless-based localization.

In this paper, we propose a method to classify glass and non-glass objects and build glass confidence maps for indoor mobile robots using laser range-finders (LRFs). The glass confidence map is aimed to improve robot localization systems' robustness and accuracy in glass environments. For most LRF-based localization systems, objects are assumed to be detectable from all incident angles, which is true for non-reflective and non-transparent objects, like walls. However, glass can only be detected by LRFs in certain incident angles. This glass detection failure decreases robots' localization accuracy. Exhibiting glass' position in the map and taking its detection failure into consideration can increase the localization accuracy. We propose the usage of a neural network to classify glass and non-glass objects, with LRF's measured intensity, distance and incident angles as inputs. We verified our method experimentally, and experimental results show that our method can successfully distinguish glass from non-glass objects and accurately construct a glass confidence map with high confidence.

This paper presents an approach to detect and solve the kidnapped robot problem using range data from a laser range finder and wifi signals. Localization based on range finders has high accuracy, but fails to detect the kidnapped robot problem, a situation where a well-localized robot is moved to a random location without itself noticing about it. On the other hand, localization based on wifi signals has very high reliability and can be used to detect the occurrence of the kidnapped robot problem; but lacks accuracy. In our approach, a probability density function is constructed using particles sampled from the wifi signal models using kernel density estimation, then the likelihood of every laser range finder particle with respect to the constructed probability density function is calculated. The mobile robot reset its localization process if these probabilities are too low.