In this paper, a new approach for obstacle vehicle path prediction is proposed based on a deep neural network, which is important for Advanced Driver Assistance Systems (ADAS) and autonomous vehicles. In order to analyze sequential sensor data, a Recurrent Neural Network (RNN) is used and the input data for RNN is drawn from three sensors: LIDAR, camera and GPS. These sensor data are obtained experimentally with real vehicles. In addition, deep ensemble is used for robustness of the estimation and acquisition of the uncertainty. The predicted path of the proposed method is continuous and it predicts both short-term and long-term path with a single algorithm. The size of the network model is small, but it shows good performance in predicting future trajectory of obstacle vehicles.

Deep learning is a fast-growing field of research, in particular, for autonomous application. In this study, a deep learning network based on various sensor data is proposed for identifying the roads where the vehicle is driving. Long-Short Term Memory (LSTM) unit and ensemble learning are utilized for network design and a feature selection technique is applied such that unnecessary sensor data could be excluded without a loss of performance. Real vehicle experiments were carried out for the learning and verification of the proposed deep learning structure. The classification performance was verified through four different test roads. The proposed network shows the classification accuracy of 94.6% in the test data.

The safety of an automated vehicle requires accurate information of surrounding conditions, because a false sensor output can lead to a fatal accident during driving. Thus, monitoring of abnormalities in every sensor is important for robust perception of the environment. Since it is difficult to obtain anomalous data, it is hard to develop a robust detection algorithm using only a relatively small number of anomalies. In this paper, we propose a data augmentation method for oversampling minority anomalies in lane detection. Using a generative adversarial network that makes the generator learn to estimate the distribution of anomalous data, it generates synthesized minority anomalies. The generated anomalies are used to train an anomaly detection network while minimizing latency for use in real situations. During training, the generated anomalies, with various mixed quality, are sampled differently according to their quality. This helps the detection network to be optimized with better quality data. Experimental result shows that when using the proposed anomaly detection framework for monitoring lane abnormality, it improves the performance by 12% when compared to the vanilla recurrent neural network.

Highly automated driving requires the use of multiple sensors for reliable tracking functionality. In response to the requirement, the proposed method modifies the conventional Interacting Multiple Model (IMM) filter to fuse multi-sensor data by utilizing the independence of observations. In addition, the proposed IMM is integrated with a Centralized Kalman Filter (CKF) that ensures track continuity against sensor failures, providing optimal state estimates. When tracking objects in a moving reference frame, such as in autonomous vehicles, onboard sensor measurements represent relative values, making it challenging to estimate the actual motion of objects. While transforming states to a global coordinates is a solution, the solution can arise another problem where the tracking results depends on the status and performance of the localization. Therefore, to tackle the problem, a track compensation algorithm utilizing a hybrid coordinate system is proposed. The actual motions of objects are estimated based on errors between the track state and the associated measurement. The performance of the proposed algorithms is demonstrated using experimental scenario data conducted with an actual vehicle.