TY  - CHAP
A1  - Chajan, Eduard
A1  - Schulte-Tigges, Joschua
A1  - Reke, Michael
A1  - Ferrein, Alexander
A1  - Matheis, Dominik
A1  - Walter, Thomas
T1  - GPU based model-predictive path control for self-driving vehicles
T2  - IEEE Intelligent Vehicles Symposium (IV)
N2  - One central challenge for self-driving cars is a proper path-planning. Once a trajectory has been found, the next challenge is to accurately and safely follow the precalculated path. The model-predictive controller (MPC) is a common approach for the lateral control of autonomous vehicles. The MPC uses a vehicle dynamics model to predict the future states of the vehicle for a given prediction horizon. However, in order to achieve real-time path control, the computational load is usually large, which leads to short prediction horizons. To deal with the computational load, the control algorithm can be parallelized on the graphics processing unit (GPU). In contrast to the widely used stochastic methods, in this paper we propose a deterministic approach based on grid search. Our approach focuses on systematically discovering the search area with different levels of granularity. To achieve this, we split the optimization algorithm into multiple iterations. The best sequence of each iteration is then used as an initial solution to the next iteration. The granularity increases, resulting in smooth and predictable steering angle sequences. We present a novel GPU-based algorithm and show its accuracy and realtime abilities with a number of real-world experiments.
KW  - Heuristic algorithms
KW  - Computational modeling
KW  - model-predictive control
KW  - GPU
KW  - autonomous driving
Y1  - 2021
SN  - 978-1-7281-5394-0
U6  - http://dx.doi.org/10.1109/IV48863.2021.9575619
N1  - 2021 IEEE Intelligent Vehicles Symposium (IV)
July 11-17, 2021. Nagoya, Japan
SP  - 1243
EP  - 1248
PB  - IEEE
ER  - 
TY  - CHAP
A1  - Nikolovski, Gjorgji
A1  - Reke, Michael
A1  - Elsen, Ingo
A1  - Schiffer, Stefan
T1  - Machine learning based 3D object detection for navigation in unstructured environments
T2  - 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)
N2  - In this paper we investigate the use of deep neural networks for 3D object detection in uncommon, unstructured environments such as in an open-pit mine. While neural nets are frequently used for object detection in regular autonomous driving applications, more unusual driving scenarios aside street traffic pose additional challenges. For one, the collection of appropriate data sets to train the networks is an issue. For another, testing the performance of trained networks often requires tailored integration with the particular domain as well. While there exist different solutions for these problems in regular autonomous driving, there are only very few approaches that work for special domains just as well. We address both the challenges above in this work. First, we discuss two possible ways of acquiring data for training and evaluation. That is, we evaluate a semi-automated annotation of recorded LIDAR data and we examine synthetic data generation. Using these datasets we train and test different deep neural network for the task of object detection. Second, we propose a possible integration of a ROS2 detector module for an autonomous driving platform. Finally, we present the performance of three state-of-the-art deep neural networks in the domain of 3D object detection on a synthetic dataset and a smaller one containing a characteristic object from an open-pit mine.
KW  - 3D object detection
KW  - LiDAR
KW  - autonomous driving
KW  - Deep learning
KW  - Three-dimensional displays
Y1  - 2021
SN  - 978-1-6654-7921-9
U6  - http://dx.doi.org/10.1109/IVWorkshops54471.2021.9669218
N1  - 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops), 11-17 July 2021,  Nagoya, Japan.
SP  - 236
EP  - 242
PB  - IEEE
ER  -