부산대학교 도서관

Connected, cooperative autonomous driving and mobility promises increased comfort and safety for public transportation and logistics in urban and suburban regions. Stationary roadside infrastructure equipped with intelligent perception sensors and communication units has the potential to increase the field of view and mitigate occlusions in perception, but is limited to fixed places in the development process. We present a mobile development platform for connected roadside infrastructure that can be used in an extensible and flexible fashion for various purposes: as a traffic monitoring device, as a reference sensor platform to benchmark in-vehicle perception, as a test platform for collaborative perception algorithms and to operate as connected edge computation infrastructure to support vehicles in decision making in real world settings. In this work, we present an overview over the Infra2Go concept and give details about the hardware and software architecture. We evaluate our platform by deploying it in an outdoor real world scenario for cooperative perception between the platform and a vehicle equipped with an on-board V2X communication unit. The platform is used to track vulnerable road users (VRU) and transmits the information via V2X communication for cooperative perception (Cooperative Perception Messages) to an autonomous vehicle in order to extend it's sensor field of view.