Search

Many production vehicles are now equipped with both cameras and radar in order to provide various driver-assistance systems (DAS) with position information of surrounding objects. These sensors, however, cannot provide position information accurate enough to realize highly automated driving functions and other advanced driver-assistance systems (ADAS). Sensor fusion methods were proposed to overcome these limitations, but they tend to show limited detection performance gain in terms of accuracy and robustness. In this study, we propose a camera-radar sensor fusion framework for robust vehicle localization based on vehicle part (rear corner) detection and localization. The main idea of the proposed method is to reinforce the azimuth angle accuracy of the radar information by detecting and localizing the rear corner part of the target vehicle from an image. This part-based fusion approach enables accurate vehicle localization as well as robust performance with respect to occlusions. For efficient part detection, several candidate points are generated around the initial radar point. Then, a widely adopted deep learning approach is used to detect and localize the left and right corners of target vehicles. The corner detection network outputs their reliability score based on the localization uncertainty of the center point in corner parts. Using these position reliability scores along with a particle filter, the most probable rear corner positions are estimated. Estimated positions (pixel coordinate) are translated into angular data, and the surrounding vehicle is localized with respect to the ego-vehicle by combining the angular data of the rear corner and the radar's range data in the lateral and longitudinal direction. The experimental test results show that the proposed method provides significantly better localization performance in the lateral direction, with greatly reduced maximum errors (radar: 3.02m, proposed method: 0.66m) and root mean squared errors (radar: 0.57m, proposed method: 0.18m).

Despite development efforts toward autonomous vehicle technologies, the number of collisions and driver interventions of autonomous vehicles tested in California seems to be reaching a plateau. One of the main reasons for this is the lack of defensive driving functionality; i.e. emergency collision avoidance when other human drivers make mistakes. In this paper, a collision avoidance/mitigation system (CAMS) is proposed to rapidly evaluate risks associated with all surrounding vehicles and to maneuver the vehicle into a safer region when faced with critically dangerous situations. First, a risk assessment module, namely, predictive occupancy map (POM), is proposed to compute potential risks associated with surrounding vehicles based on relative position, velocity, and acceleration. Then, the safest trajectory with the lowest risk level is selected among the 12 local trajectories through the POM. To ensure stable and successful collision avoidance of the ego-vehicle, the lateral and longitudinal acceleration profiles are planned while considering the vehicle stability limit. The performance of the proposed algorithm is validated based on side and rear-end collision scenarios, which are difficult to predict and to monitor. The simulation results show that the proposed CAMS via POM detect a collision risk 1.4 s before the crash, and avoids the collision successfully.

In practice, many autonomous vehicle developers put a tremendous amount of time and efforts in tuning and calibrating the path tracking controllers in order to achieve robust tracking performance and smooth steering actions over a wide range of vehicle speed and road curvature changes. This design process becomes tiresome when the target vehicle changes frequently. In this study, a model-based Linear Quadratic Gaussian (LQG) Control with adaptive Q-matrix is proposed to efficiently and systematically design the path tracking controller for any given target vehicle while effectively handling the noise and error problems arise from the localization and path planning algorithms. The regulator, in turn, is automatically designed, without additional efforts for tuning at various speeds. The performance of the proposed algorithm is validated based on KAIST autonomous vehicle. The experimental results show that the proposed LQG with adaptive Q-matrix has tracking performance in both low (15kph) and high (45kph) speed driving conditions better than those of other conventional tracking methods like the Stanley and Pure-pursuit methods.

Despite the advantages of flywheel energy storage, including low cost, a long life-cycle, and high reliability, the flywheel hybrid vehicle (FHV) has not yet been mass-produced because it usually uses two transmissions, one for the engine and the other for the flywheel, which leads to cost, packaging, and complexity concerns. In this paper, a novel power-split flywheel hybrid powertrain (PS-FHV) that uses only one transmission is proposed to mitigate these issues. The proposed PS-FHV includes one continuously variable transmission (CVT) and three planetary gear-sets integrated with a flywheel, to provide full hybrid functionality at any speed, which leads to high fuel economy and fast acceleration performance. To prove and verify the PS-FHV operation, the system was modeled and analyzed using a lever analogy to demonstrate that the system is capable of performing power distribution and regulation control, which are required for hybrid driving modes. Using the derived model, PS-FHV driving was simulated to assess the feasibility of the proposed system and estimate its performance. The simulation results confirm that the PS-FHV is a feasible system and that, compared to hybrid electric vehicles (HEVs), it provides comparable fuel economy and better acceleration performance.