Search Results

Regarding safety, obstacle avoidance has been considered as one of the most important features among ADAS systems for ground vehicles. However, the implementation of obstacle avoidance functions to commercial vehicles are still under progress. In this paper, we demonstrate a complete process of obstacle avoidance strategy for unmanned ground vehicle and implement the strategy on the self-developed Arduino based RC Car. In this process, the sensor LIDAR was used to detect the obstacles on the fore-path. Based on the measured LIDAR data, an optimized path is automatically generated with accommodation of current car position, obstacle locations, car operation capability and global environmental restrictions. The path planning is updated in real time while new or changing obstacles being detected. This algorithm is validated by the simulation results with the RC car. The comparison will be discussed at the end of this paper.

ADAS features development involves multidisciplinary technical fields, as well as extensive variety of different sensors and actuators, therefore the early design process requires much more resources and time to collaborate and implement. This paper will demonstrate an alternative way of developing prototype ADAS concept features by using remote control car with low cost hobby type of controllers, such as Arduino Due and Raspberry Pi. Camera and a one-beam type Lidar are implemented together with Raspberry Pi. OpenCV free open source software is also used for developing lane detection and object recognition. In this paper, we demonstrate that low cost frame work can be used for the high level concept algorithm architecture, development, and potential operation, as well as high level base testing of various features and functionalities. The developed RC vehicle can be used as a prototype of the early design phase as well as a functional safety testing bench.

In this paper, a sensor fusion approach is introduced to estimate lane departure. The proposed algorithm combines the camera, inertial navigation sensor, and GPS data with the vehicle dynamics to estimate the vehicle path and the lane departure time. The lane path and vehicle path are estimated by using Kalman filters. This algorithm can be used to provide early warning for lane departure in order to increase driving safety. By integrating inertial navigation sensor and GPS data, the inertial sensor biases can be estimated and the vehicle path can be estimated where the GPS data is not available or is poor. Additionally, the algorithm can be used to reduce the latency of information embedded in the controls, so that the vehicle lateral control performance can be significantly improved during lane keeping in Advanced Driver Assistance Systems (ADAS) or autonomous vehicles. Furthermore, it improves lane detection reliability in situations when camera fails to detect lanes.

In this paper, two correlations, Windowed Selected Moving Autocorrelation (WSMA) and Tri-Correlation (TriC), are introduced and discussed. The WSMA is simpler than the conventional autocorrelation. WSMA uses less data points to obtain useful signal content at desired frequencies. The computational requirement is therefore reduced compared to the conventional autocorrelation. The simplified TriC provides improved signal to noise separation capability than WSMA does while still requiring reduced computational effort compared to the standard autocorrelation. Very often, computation resource limitation exists for real-time applications. Therefore, the WSMA and TriC offer more opportunities for real-time monitor and feedback control applications in the frequency domain due to their high efficiencies. As an example, applications in internal combustion (IC) engine misfire detection are presented. Simulation and vehicle test results are also presented in this paper.