Humans drive in a holistic fashion which entails, in particular, understanding dynamic road events and their evolution. Injecting these capabilities in autonomous vehicles can thus take situational awareness and decision making closer to human-level performance. To this purpose, we introduce the ROad event Awareness Dataset (ROAD) for Autonomous Driving, to our knowledge the first of its kind. ROAD is designed to test an autonomous vehicle’s ability to detect road events, defined as triplets composed by an active agent, the action(s) it performs and the corresponding scene locations. ROAD comprises videos originally from the Oxford RobotCar Dataset, annotated with bounding boxes showing the location in the image plane of each road event. We benchmark various detection tasks, proposing as a baseline a new incremental algorithm for online road event awareness termed 3D-RetinaNet. We also report the performance on the ROAD tasks of Slowfast and YOLOv5 detectors, as well as that of the winners of the ICCV2021 ROAD challenge, which highlight the challenges faced by situation awareness in autonomous driving. ROAD is designed to allow scholars to investigate exciting tasks such as complex (road) activity detection, future event anticipation and continual learning. The dataset is available at https://github.com/gurkirt/road-dataset ; the baseline can be found at https://github.com/gurkirt/3D-RetinaNet .

The water-cooled lithium-lead (PbLi) breeding blanket is one of the candidate systems considered for the implementation in the European Demonstration Power Plant (DEMO) nuclear fusion reactor. This concept employs PbLi liquid metal as tritium breeder and neutron multiplier, water pressurized at 15.5 MPa as the coolant, and EUROFER as the structural material. The current design is based on the single module segment approach and follows the requirements of the DEMO-2015 baseline design. The module is constituted by a basic toroidal-radial cell that is recursively repeated along the poloidal direction where the liquid metal flows along a radial-poloidal path. The heat generated by the fusion reactions is extracted by means of separate cooling systems for the breeding zone and the first wall. A back supporting structure is dedicated to withstand loads of the module during normal and off-normal operations. Water and PbLi manifolds are integrated with primary heat transport and tritium extraction systems. The status of the conceptual design is presented, critically discussing its rationale and main features as supported by neutronic, thermal-hydraulic, magneto-hydrodynamic, and thermo-mechanic analyses. Recent results are outlined, pointing out open issues and development needs.