Abstract
Curb detection and localization systems constitute an important aspect of environmental recognition systems of autonomous driving vehicles. This is because detecting curbs can provide information about the boundary of a road, which can be used as a safety system to prevent unexpected intrusions into pedestrian walkways. Moreover, curb detection and localization systems enable the autonomous vehicle to recognize the surrounding environment and the lane in which the vehicle is driving. Most existing curb detection and localization systems use multichannel light detection and ranging (lidar) as a primary sensor. However, although lidar demonstrates high performance, it is too expensive to be used for commercial vehicles. In this paper, we use ultrasonic sensors to implement a practical, low-cost curb detection and localization system. To compensate for the relatively lower performance of ultrasonic sensors as compared to other higher-cost sensors, we used multiple ultrasonic sensors and applied a series of novel processing algorithms that overcome the limitations of a single ultrasonic sensor and conventional algorithms. The proposed algorithms consisted of a ground reflection elimination filter, a measurement reliability calculation, and distance estimation algorithms corresponding to the reliability of the obtained measurements. The performance of the proposed processing algorithms was demonstrated by a field test under four representative curb scenarios. The availability of reliable distance estimates from the proposed methods with three ultrasonic sensors was significantly higher than that from the other methods, e.g., 92.08% vs. 66.34%, when the test vehicle passed a trapezoidal-shaped road shoulder. When four ultrasonic sensors were used, 96.04% availability and 13.50 cm accuracy (root mean square error) were achieved.
Highlights
Since Google obtained the first license for an autonomous vehicle from the state of Nevada in2012 [1], several other companies have made remarkable progress in autonomous vehicle technology.For instance, in 2015, Audi announced that their prototype had successfully driven itself from SiliconValley to Las Vegas [2]
Our curb detection and localization system were tested under the four representative driving scenarios
We can apply typical algorithms checking and majority voting if at least three sensors provide raw measurements. This is a good such as consistency checking and majority voting if at least three sensors provide raw starting point, but it was shown that these methods provided reliable distance estimates to the curbs measurements
Summary
Since Google obtained the first license for an autonomous vehicle from the state of Nevada in. The performance of the vision sensor [33,34] can be impeded by environmental factors such as light and weather conditions [35,36,37] Because of these factors, detecting a driving lane is not a simple task for autonomous vehicles. This blind spot is not critical to detecting most nearby obstacles such as other vehicles or pedestrians, but it can become problematic in certain situations such as close approaches to curbs For these reasons, the commercialization of curb detection and localization systems with a multichannel lidar constitutes a difficult task. Because the data acquisition rate is low, the distance information becomes sparse so that even critical features of target objects might be missed This problem decreases the detection performance of ultrasonic sensors.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have