Urban transportation in the next few decades will shift worldwide toward electrification and automation, with the final aim of increasing energy efficiency and safety for passengers. Such a big change requires strong collaboration and efforts among public administration, research and stakeholders in developing, testing and promoting these technologies in public transportation. Working in this direction, this work provides a review of the impact of the introduction of driverless electric minibuses, for the first and last mile transportation, in public service. More specifically, this paper covers the state of the art in terms of technological background for automation, energy efficiency via electrification and the current state of the legal framework in Europe with a focus on the Baltic Sea Region.

Autonomous solutions for transportation are emerging worldwide, and one of the sectors that will benefit the most from these solutions is the public transport by shifting toward the new paradigm of Mobility as a Service (MaaS). Densely populated areas cannot afford an increase in individual transportation due to space limitation, congestion, and pollution.Working towards more effective and inclusive mobility in public areas, this paper compares user experiences of autonomous public transport across Baltic countries, with the final goal of gaining an increased insight into public needs. User experience was evaluated through questionnaires gathered along pilot projects implementing a public transportation line, using an automated electric minibus between 2018 and 2019. To have sufficient diversity in the data, the pilot projects were implemented in several cities in the Baltic Sea Area. The data analysed in this paper specifically refer to the cities of Helsinki (Finland), Tallinn (Estonia), Kongsberg (Norway), and Gdańsk (Poland).Across all cities, passengers provided remarkably positive feedback regarding personal security and safety onboard. The overall feedback, which was very positive in general, showed statistically significant differences across the groups of cities (Kongsberg, Helsinki, Tallinn and Gdansk), partially explicable by the differences in the route design. In addition, across all cities and feedback topics, males gave a lower score compared to females. The overall rating suggests that there is a demand for future last-mile automated services that could be integrated with the MaaS concept, although demand changes according to socio-economic and location-based conditions across different countries.

This letter aims to solve the challenging problems in multi-modal active vision for object detection on unmanned aerial vehicles (UAVs) with a monocular camera and a limited Field of View (FoV) LiDAR. The point cloud acquired from the low-cost LiDAR is firstly converted into a 3-channel tensor via motion compensation, accumulation, projection, and up-sampling processes. The generated 3-channel point cloud tensor and RGB image are fused into a 6-channel tensor using an early fusion strategy for object detection based on a Gaussian YOLO network structure. To solve the low computational resource problem and improve the real-time performance, the velocity information of the UAV is further fused with the detection results based on an extended Kalman Filter (EKF). A perception-aware model predictive control (MPC) is designed to achieve active vision on our UAV. According to our performance evaluation, our pre-processing step improves other literature methods running time by a factor of 10 while maintaining acceptable detection performance. Furthermore, our fusion architecture reaches 94.6 mAP on the test set, outperforming the individual sensor networks by roughly 5%. We also described an implementation of the overall algorithm on a UAV platform and validated it in real-world experiments.

In this work, a novel learning-based approach has been developed to generate driving paths by integrating LIDAR point clouds, GPS-IMU information, and Google driving directions. The system is based on a fully convolutional neural network that jointly learns to carry out perception and path generation from real-world driving sequences and that is trained using automatically generated training examples. Several combinations of input data were tested in order to assess the performance gain provided by specific information modalities. The fully convolutional neural network trained using all the available sensors together with driving directions achieved the best MaxF score of 88.13% when considering a region of interest of 60 × 60 meters. By considering a smaller region of interest, the agreement between predicted paths and ground-truth increased to 92.60%. The positive results obtained in this work indicate that the proposed system may help fill the gap between low-level scene parsing and behavior-reflex approaches by generating outputs that are close to vehicle control and at the same time human-interpretable.

This paper aims at evaluating the capabilities to detect road traversability in urban and extra-urban scenarios of support vector machine-based classifiers that use local descriptors extracted from point cloud data. The evaluation of the proposed classifiers is carried out by using four different kernels and comparing five point descriptors obtained from geometric and appearance-based features. A comparison among the performance of descriptors individually has demonstrated that the normal vector-based descriptor achieves an accuracy of 88%, outperforming by about 6%-15% all the other considered ones. To further improve the interpretation capabilities, the space of features is augmented by merging the components of each point descriptor, reaching 92% classification accuracy. A set of test scenarios have been acquired during an extensive experimental campaign using an all-terrain vehicle. Tests on real data show high classification performance for road scenarios and rural environments; the generality of the method makes it applicable for different types of mobile robots including, but not limited to, autonomous vehicles.