IEEE Transactions on Intelligent Transportation Systems
Abstract ▾
In the future, the role of the human factor in the driving processes is expected to decrease continuously. At the same time, based on the global trends, the role of computer-supported decision systems and artificial intelligence (AI)-based control solutions increases in relation to driving processes, which carries a significant safety-enhancing potential. To assess the possible social benefits of automated vehicle systems objectively, it is necessary to analyze the possible negative effects in detail as well. Accordingly, the aim of this article is to present a statistical survey of crashes involving automated vehicles today in order to identify and evaluate the factors that are relevant in the crashes. The analyzed data showed that when the autopilot mode was turned off and the human driver made the control decisions, the severity of crashes on straight roads was greater at α = 0.1 significance level than when the vehicle was in autopilot mode and the vehicle system made the control decisions. In addition, if the α significance level is 0.2, then crashes on plain terrain, during the day, or in the speed range of 80-100 km/h are generally less serious for vehicles driven in autopilot mode than for vehicles with autopilot mode turned off. In light of the considerations above, it is also important to emphasize that this paper only investigates crash severity given occurrence but not the probability of occurrence itself.
In this paper, a linear time-varying model predictive controller (LTV-MPC) is proposed for automated vehicle path-following applications. In the field of path following, the application of nonlinear MPCs is becoming more common; however, the major disadvantage of this algorithm is the high computational cost. During this research, the authors propose two methods to reduce the nonlinear terms: one is a novel method to define the path-following problem by transforming the path according to the actual state of the vehicle, while the other one is the application of a successive linearization technique to generate the state–space representation of the vehicle used for state prediction by the MPC. Furthermore, the dynamic effect of the steering system is examined as well by modeling the steering dynamics with a first-order lag. Using the proposed method, the necessary segment of the predefined path is transformed, the linearized model of the vehicle is calculated, and the optimal steering control vector is calculated for a finite horizon at every timestep. The longitudinal dynamics of the vehicle are controlled separately from the lateral dynamics by a PI cruise controller. The performance of the controller is evaluated and the effect of the steering model is examined as well.
The representation of objects in LiDAR point clouds is changed as the height of the mounting position of sensor devices gets increased. Most of the available open datasets for training machine learning based object detectors are generated with vehicle top mounted sensors, thus the detectors trained on such datasets perform weaker when the sensor is observing the scene from a significantly higher viewpoint (e.g. infrastructure sensor). In this paper a novel Automatic Label Injection method is proposed to label the objects in the point cloud of the high-mounted infrastructure LiDAR sensor based on the output of a well performing “trainer” detector deployed at optimal height while considering the uncertainties caused by various factors described in detail throughout the paper. The proposed automatic labeling approach has been validated on a small scale sensor setup in a real-world traffic scenario where accurate differential GNSS reference data where also available for each test vehicle. Furthermore, the concept of a distributed multi-sensor system covering a larger area aimed for automatic dataset generation is also presented. It is shown that a machine learning based detector trained on differential GNSS-based training dataset performs very similarly to the detector retrained on a dataset generated by the proposed Automatic Label Injection technique. According to our results a significant increase in the maximum detection range can be achieved by retraining the detector on viewpoint specific data generated fully automatically by the proposed label injection technique compared to a detector trained on vehicle top mounted sensor data.
Keep in touch
Always be among the firsts to know about new developments and achievements!