One important aspect of autonomous driving lies in the selection of maneuver sequences. Here, the objective is to optimize the driving comfort and travel-duration, while always keeping within the safety limits. Human drivers analyze and try to anticipate the traffic situation choosing their actions not only based on current information but also based on experience. Different from assistance systems, where the last decision and the responsibility still falls back on the driver, on a highly automated driving vehicle, the driver does not have continuous control. Thus, the system has to guarantee the safety during the autonomous driving phase. The challenge is to perform the driving activity based on the only partially available knowledge of the situation. Even if the observed data can be complemented by back-end information, the sensor range is still limited. Besides, the behavior of other road members is only partially predictable for a short time horizon. Therefore, the planning system is forced to deal with uncertainties and partial knowledge. The ability to react to unexpected situations should be ensured under defined constraints. The system needs to: • Present robustness over uncertainties and traffic evolutions. • Provide feasible solutions regarding the dynamic limitations of the vehicle, the weather conditions and meeting real-time requirements. • Handle complexity in a traceable way, remaining intuitive for the driver. This thesis proposes a planning system that ensures driving safety on short horizons and integrates previous experiences to optimize the expected reward. The planner presents a multi-level architecture, similar to the human reasoning process, which combines continuous planning with semantical information. This allows the planning system to deal with the complexity of the problem in a computationally efficient way and also provides an intuitive interface to communicate the decisions to the driver. A qualitative analysis of the different parameters that influence the passenger perception of comfort and safety is presented. The planner clusters the different options, assesses them and selects the best policy based on the expected reward over the time. The integration of different abstraction levels allows to deal with the increasing time horizon as well as with the increasing uncertainties. This approach takes not only the information provided by the environment into account, but also the observed and learned values from past situations.
Maneuver planning for highly automated vehicles
2021
Sonstige
Elektronische Ressource
Englisch
Maneuver Planning for Highly Automated Vehicles
British Library Conference Proceedings | 2017
|Maneuver planning for highly automated vehicles
IEEE | 2017
|