Enhanced Perception for Autonomous Driving Using Semantic and Geometric Data Fusion.

Environment perception remains one of the key tasks in autonomous driving for which solutions have yet to reach maturity. Multi-modal approaches benefit from the complementary physical properties specific to each sensor technology used, boosting overall performance. The added complexity brought on by data fusion processes is not trivial to solve, with design decisions heavily influencing the balance between quality and latency of the results. In this paper we present our novel real-time, 360∘ enhanced perception component based on low-level fusion between geometry provided by the LiDAR-based 3D point clouds and semantic scene information obtained from multiple RGB cameras, of multiple types. This multi-modal, multi-sensor scheme enables better range coverage, improved detection and classification quality with increased robustness. Semantic, instance and panoptic segmentations of 2D data are computed using efficient deep-learning-based algorithms, while 3D point clouds are segmented using a fast, traditional voxel-based solution. Finally, the fusion obtained through point-to-image projection yields a semantically enhanced 3D point cloud that allows enhanced perception through 3D detection refinement and 3D object classification. The planning and control systems of the vehicle receives the individual sensors' perception together with the enhanced one, as well as the semantically enhanced 3D points. The developed perception solutions are successfully integrated onto an autonomous vehicle software stack, as part of the UP-Drive project.

Lights and Shadows of the Perception of the Use of Telemedicine by Romanian Family Doctors During the COVID-19 Pandemic.

INTRODUCTION: Telemedicine has emerged as a critical technology to mitigate SARS-CoV-2 infection. We aim in this work to explore how general practitioners (GPs) perceived the use of telemedicine, recently recognized and reimbursed by the Public Health Insurance House (PHIH) for primary care (PC) provision. METHODS: A cross-sectional study was performed in 2020 in one county of Romania using an anonymous questionnaire that assessed physicians' perceptions regarding teleconsultation, reliability in tele-decision, remote pathology management, pregnant women's surveillance, patients' satisfaction with telemedicine, the need for its further reimbursement. Bivariate correlation was used to measure associations between the investigated issues. RESULTS: More than a quarter of GPs (28.6%) found it easier to address patients' healthcare needs remotely, while 60.7% considered time-consuming teleconsultations compared to face-to-face visits. Tele-diagnostic uncertainty was expressed by 64.3% of physicians, and a quarter were confident in tele-decisions. Almost half of GPs (43%) observed patients' satisfaction with tele-visits, while half said patients encountered difficulties using technology. A large percentage of doctors (62.5%) perceived that patients felt as well treated by virtual as in-person visit and 91.1% suggested post-pandemic reimbursement. The results of the bivariate correlation showed that physicians who perceived positive patient feedback on telemedicine were more supportive of subsequent reimbursement. CONCLUSION: This study showed the GPs' positive perception of the use of telemedicine. Its adoption in PC has shed light on the shadows of the pandemic. The time-consuming nature of teleconsultations, uncertainty in tele-decisions, patients' difficulties in using technology were seen as shadows of telecare. However, most of the GPs surveyed agreed with the need for further reimbursement. Future work should focus on innovative solutions for integrating telemedicine as complementary form of PC, the need for telemedicine-based training for GPs to improve capacity building, and patients' perceptions of virtual care, helping to build trust and satisfaction.