Steffen Heinrich

Shader-based sensor simulation for autonomous car testing

During autonomous car system development, sensor simulation can help to test and evaluate algorithms such as sensor fusion and object tracking in simulated dynamic scenarios at an early stage; thus, time and cost can be spared and more reliable system can be guaranteed. In this paper, shader-based LiDAR and Radar simulations are extended into autonomous car testing. Besides realizing sensor simulations producing information of interest scan data, conceptual programming interfaces to full featured physical models are also provided. Simulation accuracy is discussed and corresponding improvement methods are proposed. Optimistic results are displayed with a software-in-loop test for autonomous car and the computational cost is reported. Comparison between ray-tracing based and shader-based LiDAR simulation in terms of computational cost is also carried out and discussed.

Real-time trajectory optimization under motion uncertainty using a GPU

This paper presents a sampling-based planning method considering motion uncertainty to generate more human-like driving paths for automated vehicles. Given information in the form of a small set of rules and driving heuristics the planning system optimizes trajectories in a seven dimensional state space. In a post-processing step a set of candidates is evaluated considering the uncertainty of the vehicles motion executing the given trajectory using a Linear-Quadratic Gaussian (LQG). This addresses the problem of indecisive planning behavior in case the optimal solution is unlikely to be followed precisely. The results of our experiments show that the mobile graphics processing unit (GPU) technology can be used as an enabler for real-time applications of computationally expensive planning approaches.

Optimizing a driving strategy by its sensor coverage of relevant environment information

We propose a novel approach for automated vehicle motion planning systems that introduces the likelihood of an information gain at future positions to trajectory optimization. In the same way as human drivers, computer controlled vehicles have to be fully aware of their surroundings and the current driving situation. Even though automated cars have a full 360 degrees field of view through sensor data fusion, objects can be hidden behind other obstacles. We optimize the vehicles future pose (position and orientation) on the road and within the traffic stream, so that it can perceive as much as possible while fulfilling other constraints related to the overall safety or driving comfort. Our results show that perception benefits from maximizing the entropy in areas of interest (EAI) over field of view (FOV). The computation of an EAI is expensive and achieved by using an optimized algorithm for modern GPGPUs.