This article presents a mobility prediction method for mobile phone users based on an enhanced Markov Chain algorithm. The mobile phone data has a highly dynamic nature and a sparcely sampled aspect; therefore, the prediction of user's mobility location poses a challenge. Our enhancement approach can be summarized as an embedded association of rules applied to a Markov chain algorithm. The proposed solution is encouraging for the next generation of mobile networks and it can be used to optimize the existing mobile network infrastructure, road traffic, tracking systems and localization. Validation of our system was carried out using real data collected from the field.

The technological advancement of sensors and computational power has opened a new chapter in machine learning for robotics applications, especially in image classification, segmentation, object detection, and self-driving cars. One of the challenges among these applications is improving the systems perception reliability and accuracy through sensors fusion. Hence, the focus on using Stereo-cameras and LiDARs as a complement to its accurate distance measurement. However, the calibration process of the sensors is mandatory before deployment. Some may use the conventional methods, including checkerboards, specific pattern labels, or even human labeling, which is labor-intensive and repetitive as it involves doing the same calibration process every time before using. In this work, we have proposed NetCalib – an auto-calibration methodology based on a deep neural network. This research aims to utilize the power of machine learning to find the geometric transformation between stereo cameras and LiDAR automatically. From the experiments, our method manages to find the transformations from randomly sampled artificial errors and outperforms the linear optimization-based ICP algorithm. Furthermore, this research work is open-sourced to the community to fully use the advances of the methodology and initiate collaboration and innovation in this field.

Tracking and positioning vehicles for navigation purposes are very important in many applications, ranging from simple routing problem to emergency planning and interventions. To this end, numerous approaches and industrial applications have been proposed to serve this purpose; however, there is a lot of work to be done to refine real-time systems for tracking in order to increase their accuracy and performance. Hence, in this paper we are presenting a real-time system that takes advantage of all the embedded sensors in the smartphone, using multi-sensor fusion to provide a real-time system capable of tracking, positioning, and even anticipating the maneuvers of vehicles in real-time.

A fusion of LiDAR and cameras have been widely used in many robotics applications such as classification, segmentation, object detection, and autonomous driving. It is essential that the LiDAR sensor can measure distances accurately, which is a good complement to the cameras. Hence, calibrating sensors before deployment is a mandatory step. The conventional methods include checkerboards, specific patterns, or human labeling, which is trivial and human-labor extensive if we do the same calibration process every time. The main purpose of this research work is to build a deep neural network that is capable of automatically finding the geometric transformation between LiDAR and cameras. The results show that our model manages to find the transformations from randomly sampled artificial errors. Besides, our work is open-sourced for the community to fully utilize the advances of the methodology for developing more the approach, initiating collaboration, and innovation in the topic.