|Autonomous Valet Parking and Charging for eMobility|
|From 2011-06-01 to 2015-09-30||Completed|
The project V-Charge is based on the vision that, due to required drastic decrease of CO2 production and energy consumption, mobility will undergo important changes in the years to come. This includes new concept for an optimal combination of public and individual transportation as well as the introduction of electrical cars that need coordinated recharging. The final goal in four years is the demonstration and implementation of a fully operational future car system including autonomous local transportation, valet parking and battery charging on the campus of ETH Zurich and TU Braunschweig.
Within the proposed project, the focus was set on the following main topics:
- Development of machine vision systems based upon close-to-market sensor systems (such as stereo vision, ultrasonic etc.) as well as the integration and fusion of each sensors data into a detailed world model describing static and dynamic world contents by means of online mapping and obstacle detection and tracking.
- Computer-base situation assessment within the world model as well as describing dependencies and interactions between separate model components (e.g. separate dynamic objects). For this purpose, the integration of market-ready map-material (i.e. originating from navigation systems) as well as the use of vehicle-to-infrastructure communication shall be explored.
- Precise low-cost localization in urban environments through the integration of standard satellite-based technologies with visual map-matching approaches combining both the onboard-perception system and available map material.
- Highly adaptive global and local planning considering dynamic obstacles (cars, pedestrians) and their potential trajectory.
Three fully functional prototypes capable of automated operation in both outdoor or indoor parking lots and garages. The project developed secure data transmission concepts between the vehicle and the remote parking lot server via local or wireless connections. Handling of a lot of parking spots and charging stations by the parking lot server were demonstrated in simulation. The vehicle localizes itself in the environment with the help of monocular cameras and natural landmarks. During the localization, the vehicle compares the perceived images to an online database which contains visual information about the parking lot. The localization technique was optimized during the project to yield centimetre-level accuracy.
The vehicle follows a route planned on a topological map of the parking lot, and receives information about the parking spot locations and speed limits. When navigating through the route, the vehicle perceives its surroundings differentiating between static obstacles and other mobile traffic agents. A local motion planner computes safe motion commands for the platform, so the vehicle can safely mitigate static obstacles and negotiate with other vehicles in mixed traffic. In the designated parking spot, the vehicle computes potentially complex manoeuvre into parking spot.
The project analysed valuable insights around the parking spots and charging stations, including concepts for high density parking. The V-Charge system proved itself to be fully capable of navigation in static environments, on-lane planning and parking were reliable given environment perception and localization in these scenarios.
ETH Zurich, Switzerland Volkswagen, Germany University of Oxford, UK Robert Bosch, Germany Università degli Studi di Parma, Italy Technische Universität Braunschweig
Budget / Funding
Total cost: € 8 694 872 / EU contribution: € 5 630 000
Funded under the call: FP7-ICT-2009-6
Topic: ICT-2009.2.1 - Cognitive Systems and Robotics