Abstract

This thesis targets the problem of motion planning for automated vehicles. As a prerequisite for their on-road deployment, automated vehicles must show an appropriate and reliable driving behavior in mixed traffic, i.e. alongside human drivers. Besides the uncertainties resulting from imperfect perception, occlusions and limited sensor range, also the uncertainties in the behavior of other traffic participants have to be considered. Related approaches for motion planning in mixed traffic often employ a deterministic problem formulation. The solution of such formulations is restricted to a single trajectory. Deviations from the prediction of other traffic participants are accounted for during replanning, while large uncertainties lead to conservative and over-cautious behavior. As a result of the shortcomings of these formulations in cooperative scenarios and scenarios with severe uncertainties, probabilistic approaches are pursued. Due to the need for real-time capability, however, a holistic uncertainty treatment often induces a strong limitation of the action space of automated vehicles. Moreover, safety and traffic rule compliance are often not considered. Thus, in this work, three motion planning approaches and a scenario-based safety approach are presented. The safety approach is based on an existing concept, which targets the guarantee that automated vehicles will never cause accidents. This concept is enhanced by the consideration of traffic rules for crossing and merging traffic, occlusions, limited sensor range and lane changes. The three presented motion planning approaches are targeted towards the different predominant uncertainties in different scenarios, while operating in a continuous action space. For non-interactive scenarios with clear precedence, a probabilistic approach is presented. The problem is modeled as a partially observable Markov decision process (POMDP). In contrast to existing approaches, the underlying assumption is that the prediction of the future progression of the uncertainty in the behavior of other traffic participants can be performed independently of the automated vehicle's motion plan. In addition to this prediction of currently visible traffic participants, the influence of occlusions and limited sensor range is considered. Despite its thorough uncertainty consideration, the presented approach facilitates planning in a continuous action space. Two further approaches are targeted towards the predominant uncertainties in interactive scenarios. In order to facilitate lane changes in dense traffic, a rule-based approach is proposed. The latter seeks to actively reduce the uncertainty in whether other vehicles willingly make room for a lane change. The generated trajectories are safe and traffic rule compliant with respect to the presented safety approach. To facilitate cooperation in scenarios without clear precedence, a multi-agent approach is presented. The globally optimal solution to the multi-agent problem is first analyzed regarding its ambiguity. If an unambiguous, cooperative solution is found, it is pursued. Still, the compliance of other vehicles with the presumed cooperation model is checked, and a conservative fallback trajectory is pursued in case of non-compliance. The performance of the presented approaches is shown in various scenarios with intersecting lanes, partly with limited visibility, as well as lane changes and a narrowing without predefined right of way.

Abstract

The increasing penetration of renewable energy sources and electric vehicles raises important challenges related to the operation of electricity grids. For instance, the amount of power generated by wind turbines is time-varying and dependent on the weather, which makes it hard to match flexible electric vehicle demand and uncertain wind power supply. In this paper we propose a vehicle aggregation framework which uses Markov Decision Processes to control charging of multiple electric vehicles and deals with uncertainty in renewable supply. We present a grouping technique to address the scalability aspects of our framework. In experiments we show that the aggregation framework maximizes the profit of the aggregator while reducing usage of conventionally-generated power and cost of customers.

Abstract

Renewable energy sources introduce uncertainty regarding generated power in smart grids. For instance, power that is generated by wind turbines is time-varying and dependent on the weather. Electric vehicles will become increasingly important in the development of smart grids with a high penetration of renewables, because their flexibility makes it possible to charge their batteries when renewable supply is available. Charging of electric vehicles can be challenging, however, because of uncertainty in renewable supply and the potentially large number of vehicles involved. In this paper we propose a vehicle aggregation framework which uses Markov Decision Processes to control electric vehicles and deals with uncertainty in renewable supply. We present a grouping technique to address the scalability aspects of our framework. In experiments we show that the aggregation framework maximizes the profit of the aggregator, reduces cost of customers and reduces consumption of conventionally-generated power.

Abstract

Renewable energy sources introduce uncertainty regarding generated power in smart grids. For instance, power that is generated by wind turbines is time-varying and dependent on the weather. Electric vehicles will become increasingly important in the development of smart grids with a high penetration of renewables, because their flexibility makes it possible to charge their batteries when renewable supply is available. Charging of electric vehicles can be challenging, however, because of uncertainty in renewable supply and the potentially large number of vehicles involved. In this paper we propose a vehicle aggregation framework which uses Markov Decision Processes to control electric vehicles and deals with uncertainty in renewable supply. We present a grouping technique to address the scalability aspects of our framework. In experiments we show that the aggregation framework maximizes the profit of the aggregator, reduces cost of customers and reduces consumption of conventionally-generated power.