The tracking accuracy of speed plays a significant role in the autonomous vehicle's control and safety management. In this study, we presented a novel method called self‐adaptive proportional integral derivative (PID) of radial basis function neural network (RBFNN‐PID) which is shown with improved longitudinal speed tracking accuracy for autonomous vehicles. A forward simulation model of longitudinal speed control for autonomous vehicles is established based on the driver model of self‐adaptive RBFNN‐PID and the vehicle dynamics model. Based on that, we used the traditional PID and fuzzy control methods as benchmarks to demonstrate the edge of the self‐adaptive RBFNN‐PID control under the new European driving cycle. Simulation results show the RBFNN‐PID method is significantly more precise than the comparing groups, with a reduced error in the range of [−0.369, 0.203] m/s. The vehicle performance gives better ride comfort as well. In all, self‐adaptive RBFNN‐PID is proven to be effective in longitudinal speed control of autonomous vehicles and significantly outperforms the other two methods.

This paper presents a two-layer controller for accurate and robust lateral path tracking control of highly automated vehicles. The upper-layer controller, which produces the front wheel steering angle, is implemented with a Linear Time-Varying MPC (LTV-MPC) whose prediction and control horizon are both optimized offline with particle swarm optimization (PSO) under varying working conditions. A constraint on the slip angle is imposed to prevent lateral forces from saturation to guarantee vehicle stability. The lower layer is a radial basis function neural network proportion-integral-derivative (RBFNN-PID) controller that generates electric current control signals executable by the steering motor to rapidly track the target steering angle. The nonlinear characteristics of the steering system are modeled and are identified on-line with the RBFNN so that the PID controller’s control parameters can be adjusted adaptively. The results of CarSim-Matlab/Simulink joint simulations show that the proposed hierarchical controller achieves a good level of path tracking accuracy while maintaining vehicle stability throughout the path tracking process, and is robust to dynamic changes in vehicle velocities and road adhesion coefficients.

This paper presents a shared steering control framework for lane keeping and obstacle avoidance based on multi-objective model predictive control. One of the control objectives is to track the reference trajectory, which is updated continuously by the trajectory planning module; whereas the other is to track the driver’s current steering command, so as to consider the driver’s intention. By adding the two control objectives to the cost function of an MPC shared controller, a smooth combination of the commands of the driver and the automation can be achieved through the optimization. The authority of the driver and the automation is allocated by adjusting the weights of the objective terms in the cost function, which is determined by the proposed situation assessment method considering the longitudinal and lateral risks simultaneously. The results of the CarSim-Matlab/Simulink joint simulations show that the proposed shared controller can assist the driver to complete the tasks of lane keeping and obstacle avoidance smoothly while maintaining a good level of vehicle stability.

Cross-modal fusion methods enhance 3D object detection by leveraging multimodal complementarity. However, current methods, which seek to establish point-wise or RoIwise cross-modal correspondence, have their own limitations. The point-wise methods struggle with weak alignment and inaccurate depth estimation. The RoI-wise methods, which adopt RoI as the basis of sampling features and fusion features, produce ambiguous object-level features. In light of this, this paper introduces OFFNet, a 3D detector implementing cross-modal object-level feature fusion (COFF) discriminatively. To combine spatial information from peripheral LiDAR features and unambiguous semantics from foreground image features, our approach operates fusion in two stages. The first stage unifies multimodal features into homogeneous representations in the point cloud space to facilitate cross-modal feature interaction. For this purpose, a point enhancement module (PEM) is designed to generate two sets of keypoints. A set of original keypoints are sampled from foreground LiDAR points to aggregate multi-dimensional LiDAR features in COFF procedure. Meanwhile, a set of pseudo keypoints, generated by shifting the foreground keypoints towards objects’ geometric center, are used as sampling points to aggregate foreground image features. In the second stage, we obtain robust object-level features by hierarchically fusing LiDAR and image features specific to each instance. Coarse 3D candidate boxes are gridded and segmented into external and internal layers. The external layer aggregates LiDAR features from adjacent original keypoints, while the internal layer aggregates image features from neighboring pseudo keypoints. Experiments on the KITTI and nuScenes benchmark demonstrate OFFNet’s state-of-the-art performance, particularly excelling in the challenging ’Cyclist’ category.

Rebar tying is a time-consuming and laborintensive process that involves repetitive bending and hand motions to secure rebar with wire, often leading to muscular and skeletal injuries. To address these challenges, rebar tying robots have been developed to automate the process. However, existing studies primarily focus on tying point localization for horizontal rebar mesh, neglecting the 6 Degrees of Freedom (DoF) pose estimation necessary for tying complex reinforcement skeletons where rebar may be arranged in various spatial orientations. Therefore, this study proposes a 6-DoF rebar pose estimation method based on keypoint detection and point cloud registration. A deep learning-based keypoint detection algorithm is employed to extract point cloud data from each rebar intersection. Additionally, to tackle challenges posed by texture-less and selfoccluding features of rebar point clouds, a coarse registration method utilizing geometric features and a fine registration method based on adaptive displacement correction is introduced to ensure accuracy and stability in rebar pose estimation. The proposed method enables the robot to autonomously understand the relative spatial relationship between itself and the tying objects, facilitating precise tying across a broader range of reinforcement skeletons, thereby significantly reducing the demand for manual labor.