Search

For driving safely and comfortably, the long-term trajectory prediction of surrounding vehicles is essential for autonomous vehicles. For handling the uncertain nature of trajectory prediction, deep-learning-based approaches have been proposed previously. An on-road vehicle must obey road geometry, i.e., it should run within the constraint of the road shape. Herein, we present a novel road-aware trajectory prediction method which leverages the use of high-definition maps with a deep learning network. We developed a data-efficient learning framework for the trajectory prediction network in the curvilinear coordinate system of the road and a lane assignment for the surrounding vehicles. Then, we proposed a novel output-constrained sequence-to-sequence trajectory prediction network to incorporate the structural constraints of the road. Our method uses these structural constraints as prior knowledge for the prediction network. It is not only used as an input to the trajectory prediction network, but is also included in the constrained loss function of the maneuver recognition network. Accordingly, the proposed method can predict a feasible and realistic intention of the driver and trajectory. Our method has been evaluated using a real traffic dataset, and the results thus obtained show that it is data-efficient and can predict reasonable trajectories at merging sections.

Many studies using a laser scanner have been conducted in order to study the environment of vehicles in real time. The method to find the driving area using a two-dimensional lidar sensor is divided into a forward-looking lidar sensor and a downward-looking lidar sensor based on the installation method. A downward-looking lidar sensor looks at the ground, enabling it to recognize kerbs and ditches which are lower than the installation position of the sensor. However, a downward-looking lidar sensor requires pre-processing to find the road boundary. The existing sensor models cannot generate an occupancy grid map without support, as the driving area recognized through a downward-looking lidar sensor forms a circular sector shape from the sensor installation position to the road boundary. This paper proposes a road sensor model that is capable of modelling an occupancy grid. We also propose a method to generate an occupancy grid map more suitable for autonomous vehicles by presenting the occupancy grid map in curvilinear space. The proposed method was validated by an experiment at Hanyang University campus and the quantitative results obtained from that experiment. We also compared this method with three conventional sensor model methods. The experimental results show that our method performs better than the conventional methods do in terms of both visual qualities and metric qualities.

This paper proposes a geometric approach for forward kinematics analysis of a 3-SPS/S redundant motion mechanism using conformal geometric algebra (CGA). The forward kinematics of a parallel kinematic mechanism is generally very complicated and difficult to analyze. The proposed geometric method is useful because it provides simple, fast, and complete solutions to the problem and helps determine the relationship between the joints and end-effector without an iterative process. Thus, we introduce a geometric approach using CGA in an intuitive, stepwise fashion. We also use an extra sensor to provide more positional information, thereby allowing a unique solution to be selected geometrically from among the multiple solutions found using the geometric approach. In the mechanism considered herein, three identical legs linked by prismatic actuators are attached to a moving platform and to the base by two passive spherical joints. A passive leg is present at the center of the mechanism; it connects the center of the base to the platform, constraining the platform’s movement. The added components constrain the movement of the platform, making it possible to analyze the mechanism using a geometric approach. Herein we present performance comparisons that validate use of the proposed approach in real-time applications and demonstrate its low computational load.

We propose a 3-SPS/S redundant motion mechanism with kinematic redundancy in this paper. The proposed mechanism with redundancy enables redundant motion as it works like pan/tilt systems to reduce the unnecessary degree of freedom for the yaw and pitch motions in the configuration space. By reducing one degree of freedom, this robot has self-motion that causes the inverse kinematics to have infinite solutions, so that the proposed research performs an optimization process for obtaining the optimal solution using geometric approaches. This optimal solution provides the fastest response among the infinite solutions by minimizing each link movement to the target orientation. In addition, we perform a geometric singularity analysis due to limited link length and avoidance using conformal geometric algebra for the feasibility and correctness of the inverse kinematics.

A new method for supervoxel segmentation based on a weighted graph in complex urban environment is proposed. The proposed algorithm is designed to minimise the cost of the shortest path in the weighted graph with consideration of characteristics of the sensor for complex urban environment. We collected point clouds in a complex urban environment to evaluate the proposed method. The performance of the proposed algorithm was evaluated using boundary recall and under-segmentation errors.

This paper presents methods of localization of mobile systems using recent Radio Frequency Identification (RFID) technology. We consider an indoor environment where RFID tags are implanted along the wall or in objects in the room. If the absolute position and orientation of a tag are read by an RF reader, a mobile system can estimate its location using the information saved in the tags. A reader-tag model is obtained through experiments in order to derive relative positions and orientations between an antenna and an RFID tag. To estimate the location, we propose two estimation methods. One uses a single RFID tag and the other uses multi-RFID tags. Experimental results show that the proposed methods can provide good performance for mobile system localization in an indoor environment.

Vision-based lane-sensing systems require accurate and robust sensing performance in lane detection. Besides, there exists trade-off between the computational burden and processor cost, which should be considered for implementing the systems in passenger cars. In this paper, a stereo vision-based lane detection system considering sensor configuration aspects such as field of view (FOV), span pixels, resolution, etc is developed. An inverse perspective mapping method is formulated based on the relative correspondence between the left and right cameras so that the 3D road geometry can be reconstructed in a robust manner. The selection rule of the sensor configuration and specifications is investigated for a standard highway. Based on the selected sensor configurations, it is shown that sensing region range on the camera image coordinate can be determined for the best lane-sensing performance. The proposed system is implemented on a passenger car and its real-time sensing performance is verified experimentally.