This paper presents a hierarchical trajectory planning based on the integration of a sampling and an optimization method for urban autonomous driving. To manage a complex driving environment, the upper behavioral trajectory planner searches the macro-scale trajectory to determine the behavior of an autonomous car by using environment models, such as traffic control device and objects. This planner infers reasonable behavior and provides it to the motion trajectory planner. For planning the behavioral trajectory, the sampling-based approach is used due to its advantage of a free-form cost function for discrete models of the driving environments and simplification of the searching area. The lower motion trajectory planner determines the micro-scale trajectory based on the results of the upper trajectory planning with the environment model. The lower planner strongly considers vehicle dynamics within the planned behavior of the behavioral trajectory. Therefore, the planning space of the lower planner can be limited, allowing for improvement of the efficiency of the numerical optimization of the lower planner to find the best trajectory. For the motion trajectory planning, the numerical optimization is applied due to its advantages of a mathematical model for the continuous elements of the driving environments and low computation to converge minima in the convex function. The proposed algorithms of the sampling-based behavioral and optimization-based motion trajectory were evaluated through experiments in various scenarios of an urban area.

A safe trajectory planning for on-road autonomous driving is a challenging problem owing to the variety and complexity of driving environments. The problem should involve the consideration of numerous aspects such as road geometry, lane-structured roads, traffic regulations, traffic participants, and vehicle physical limitations. Furthermore, dynamically changing movements of surrounding vehicles make the problem more challenging. It requires the planner's ability to react to the changes in the driving environments in real time. To solve this problem, sampling and numerical optimization-based trajectory planners were introduced. However, these methods have their own limitations in generating a safe trajectory in these dynamic scenarios. To overcome these issues, this paper proposes a hybrid trajectory planning scheme to integrate the strength of the sampling and optimization methods. With the sampling method for a lateral movement, the planner can deal with various trajectories with multiple maneuvers. This helps the planner to generate a reactive trajectory in a dynamically changing environment. The numerical optimization of a longitudinal movement enables the planner to adapt to diverse situations without restriction of predefined patterns for specific driving purposes. The proposed method was implemented with an embedded optimization coder and C++ environment. Based on this, its performance was evaluated through simulation and real driving tests in various on-road dynamic scenarios.

Car-following control is a fundamental application of autonomous driving. This control has multiple objectives, including tracking a safe distance to a preceding vehicle and enhancing driving comfort. Model Predictive Control (MPC) is a powerful method due to its intuitiveness and capability to cover multiple objectives. MPC determines the relative importance of objectives through a set of weight factors, depending on which, the controller’s behavior changes even if the traffic situations are the same. However, determining the optimal weight is not a trivial problem because there is no benchmark to evaluate the performance of the weight, and searching for weight factors with repeated driving experiments is time-consuming. To solve this problem, we proposed an automatic tuning method to determine the weights of the MPC based on personal driving data. Personal driving data under naturalistic driving conditions provide car-following situations and driver’s behaviors. These data can generate a reference model to represent the driver’s driving style. Based on this model, the proposed method defined the automatic tuning problem as an optimization problem that minimizes the difference between the reference and the controller’s response using the optimal weight factors. This optimization problem was solved using the Particle Swarm Optimization algorithm. The proposed method was implemented with an embedded optimization coder in an offline fashion. Its performance was evaluated using personal driving data. From this, the proposed method can reduce the effort and time required for an engineer to find the optimal weight factors.

In automated parking systems, a path planner generates a path to reach the vacant parking space detected by a perception system. To generate a safe parking path, accurate detection performance is required. However, the perception system always includes perception uncertainty, such as detection errors due to sensor noise and imperfect algorithms. If the parking path planner generates the parking path under uncertainty, problems may arise that cause the vehicle to collide due to the automated parking system. To avoid these problems, it is a challenging problem to generate the parking path from the erroneous parking space. To solve this conundrum, it is important to estimate the perception uncertainty and adapt the detection error in the planning process. This paper proposes a robust parking path planning that combines an error-adaptive sampling of generating possible path candidates with a utility-based method of making an optimal decision under uncertainty. By integrating the sampling-based method and the utility-based method, the proposed algorithm continuously generates an adaptable path considering the detection errors. As a result, the proposed algorithm ensures that the vehicle is safely located in the true position and orientation of the parking space under perception uncertainty.

Autonomous driving helps drivers avoid paying attention to keeping to a lane or keeping a distance from the vehicle ahead. However, the autonomous driving is limited by the need to park upon the completion of driving. In this sense, automated valet parking (AVP) system is one of the promising technologies for enabling drivers to free themselves from the burden of parking. Nevertheless, the driver must continuously monitor the automated system in the current automation level. The main reason for monitoring the automation system is due to the limited sensor range and occlusions. For safety reasons, the current field of view must be taken into account, as well as to ensure comfort and to avoid unexpected and harsh reactions. Unfortunately, due to parked vehicles and structures, the field of view in a parking lot is not sufficient for considering new obstacles coming out of occluded areas. To solve this problem, we propose a method that estimates the risks for unobservable obstacles by considering worst-case assumptions. With this method, we can ensure to not act overcautiously while moving safe. As a result, the proposed method can be a proactive approach to consider the limited visibility encountered in a parking lot. In the proposed method, occlusion can be efficiently reflected in the planning process. The potential of the proposed method is evaluated in a variety of simulations.

There are multifarious stationary vehicles in urban driving environments. Autonomous vehicles need to make appropriate overtaking maneuver decisions to navigate through the stationary vehicles. In literature, overtaking maneuver decision problems have been addressed in the perspective of either discretionary lane-change or parked vehicle classification. While the former approaches are prone to generating undesired overtaking maneuvers in urban traffic scenarios, the latter approaches induce deadlock situations behind a stationary vehicle which is not distinctly classified as a parked vehicle. To overcome the limitations, we analyzed the significant decision factors in the traffic scenes and designed a Deep Neural Network (DNN) model to make human-like overtaking maneuver decisions. The significant traffic-related and intention-related decision factors were harmoniously extracted in the traffic scene interpretation process and were utilized as the inputs of the model to generate overtaking maneuver decisions in the same manner with the human driver. The overall validation results convinced that the extracted decision factors contributed to increasing the learning performance of the model, and consequently, the proposed decision-making system enabled the autonomous vehicles to generate more human-like overtaking maneuver decisions in various urban traffic scenarios.