Software specification and architecture for decision making and navigation This deliverable provides insights of the current software architecture representing the decision-making and navigation framework assigned to WP7 of the UP-Drive project. pdf
First development and integration cycle of scene understanding This deliverable contributes to the Up-Drive project´s endeavor to create a car capable of self-driving in an unconstrained urban environment with speeds up to 30 km/h. D6.2 covers the WP6 (Scene/scenario understanding) related development and the first integration cycle of its implementation into the Up-Drive-wide system. pdf
Software specification and architecture for scene understanding This deliverable contributes to the UP-Drive (automated Urban Parking) project’s endeavor to create a car capable of self-driving in an unconstrained urban environment with speeds up to 30 km/h. pdf
First development and integration cycle of lifelong mapping This deliverable describes the lifelong mapping framework after the first development & integration cycle. All components, notably the metric and semantic map, the metric online localization, the semantic data aggregation and the map summarization are functional and integrated on the vehicles, fulfill their basic purposes and interact with each other in a limited fashion. All components deliver first evaluation results. pdf
Specification of the Map Frontend and Storage Concept This deliverable corresponds to task 5.1, 5.2 and 5.3. It describes the hardware and software requirements and specifications for the mapping and localization frontend and storage concepts in the cloud-based backend. pdf
Final specification and design of on-board sensing This deliverable states the updates on two major aspects since Deliverable 4.1: The first aspect consists in the detailed specification of the perception goals and of the sensor model of the environment. The second aspect consists in the selection and the definition of the robust and redundant perception solution for each individual perception task based on the available or new sensors. pdf
Initial version of higher-level perception functions The deliverable provides an initial design and implementation of the higher level perception functions referring to road surface and obstacle perception, parking spot detection, road users classification, tracking and signaling perception. pdf
Initial version of low-level perception functions The deliverable provides an initial design and implementation of the spatio-temporal and appearance based low level representation (STAR) which represents the basis of building a virtual super-sensor that may perceive the environment like it has the capabilities of all available sensors mounted on the vehicles. pdf
Initial specification and design of on-board sensing This deliverable states the sensing possibilities, suitable to enable vehicle’s highly automated driving capabilities, as well as to collect useful information for map related operations including map enrichment, alignment, etc. pdf
First development and integration cycle of cloud infrastructure This deliverable corresponds to Task 3.2: First development and integration cycle of cloud infrastructure. It documents the cloud infrastructure that has been selected and implemented within the project. Building on D3.1, this deliverable focuses on the Gitlab source code management system, the Swift object store and OpenStack cloud compute infrastructure functionality. pdf