Karl-Heinz Glander

A real-time capable model predictive approach to lateral vehicle guidance

The paper at hand proposes a real-time capable approach to combined trajectory planning and control. One single prediction model is used to plan a feasible trajectory and to perform lateral guidance of the vehicle at the same time. Nonlinear model predictive control (NMPC) methods are applied to solve the optimal control problem, which incorporates environmental constraints leading to a model predictive planning and control approach (MPPC). Experiments are conducted utilizing a rapid prototyping system. The analysis shows the versatile application range of the developed algorithm, such as challenging emergency evasive maneuvers as well as automated steering as an approach to lateral guidance of the vehicle in general.

How much automation do we really need

Nowadays many OEMs equip their cars with Advanced Driver Assistance System (ADAS) functions (see figure 1) which assist the driver e.g. to stay in the lane, keep an appropriate distance to the vehicle in front or identify if someone is driving in the driver’s blind spot. These functions have a mere informative character or only affect a single task in the driving process within comfort boundaries. Moreover, the driver is always able to overrule them.

Probabilistic time-to-lane-change prediction on highways

Situation understanding and assessment is one of the key features for automated driving. To enable safe and comfortable motion planning, sensing the current situation is not sufficient but maneuver predictions as accurate as possible are required. The paper presents a novel approach of predicting the remaining time to an upcoming lane change of adjacent vehicles on a highway. The prediction is performed in a probabilistic way to cope with the variety in execution and duration of lane change maneuvers. Two quantile regression techniques, namely Linear Quantile Regression and Quantile Regression Forests, are applied and compared in terms of prediction error and accuracy on data gathered with different drivers on a fixed base driving simulator. The superior technique is also evaluated on a dataset recorded with a test vehicle to demonstrate its general applicability in real world scenarios.

Definition of critical traffic scenarios to evaluate trigger criteria for collision avoidance

This contribution examines the parameters, which influence a critical situation in road traffic decisively. For this purpose, sets of simulations are performed to evaluate the impact. By this knowledge, a trigger criteria for collision avoidance, which take all parameters into account is defined. The criteria utilizes an easy planning method to assess if an evasive maneuver or braking intervention will lead to collision free driving.

Development and test of a lane change prediction algorithm for automated driving

Due to a large number of integrated advanced driver assistance systems (ADAS) the driver nowadays can hand over the driving task to the vehicle in specific, monotone driving scenarios. Short reaction times and the constant awareness of the computer reduces the number of accidents and thus increases safety. Currently available ADAS still need to be constantly monitored by the driver in case a situation appears that cannot be handled properly by the system.