Advanced deep learning technology has made great progress in generic object detection of autonomous driving, yet it is still challenging to detect small road hazards in a long distance owing to lack of large-scale small-object datasets and dedicated methods. This work addresses the challenge from two aspects. Firstly, a self-collected long-distance road object dataset (TJ-LDRO) is introduced, which consists of 109,337 images and is the largest dataset so far for the small road object detection research. Secondly, a vanishing-point-guided context-aware network (VCANet) is proposed, which utilizes the vanishing point prediction block and the context-aware center detection block to obtain semantic information. The multi-scale feature fusion pipeline and the upsampling block in VCANet are introduced to enhance the region of interest (ROI) feature. The experimental results with TJ-LDRO dataset show that the proposed method achieves better performance than the representative generic object detection methods. This work fills a critical capability gap in small road hazards detection for high-speed autonomous vehicles.

A major source of electric vehicle energy loss is the vibration energy dissipated by the shock absorbers under irregular road excitation, which is particularly severe when active wheel systems are employed because their greater unsprung mass leads to greater shocks and vibrations. Therefore, a tubular linear energy harvester (TLEH) with a large stroke and low electromagnetic force ripple is designed to convert this vibration energy into electricity. The proposed TLEH employs a slotted external mover with three-phase winding coils and an internal stator with PMs to increase the stroke, adopts a fractional slot-per-pole configuration to reduce its size and improve the winding factor, and realizes significantly reduced cogging force by optimizing the incremental length of the armature core. A finite element model of the TLEH is first verified against a theoretical model and then used to investigate the influences of various road excitation frequencies and amplitudes on the electromotive force (EMF) waveforms and generated power, the efficiency and damping force according to load condition, and the energy recovery and nonlinear electromagnetic force characteristics of the TLEH. A resistance controller is then designed to realize a self-damping electromagnetic suspension. The results indicate that the EMF and the generated power waveforms depend on the excitation frequency and amplitude, the efficiency increases and the damping coefficient decreases with the increasing load resistance.

Universal challenge lies in torque feedback accuracy for steer-by-wire systems, especially on uneven and low-friction road. Therefore, this paper proposes a fusion method based on Kalman filter that combines a dynamics-reconstruction method and disturbance observer-based method. The dynamics- reconstruction method is designed according to the vehicle dynamics and used as the prediction model of the Kalman filter. While the disturbance observer-based method is performed as an observer model of the Kalman filter. The performance of all three methods is comprehensively evaluated in a hardware-in-the-loop system. Experimental results show that the proposed fusion method outperforms dynamics reconstruction method and disturbance observer-based method. Specifically, compared with the dynamics-reconstruction method, the root mean square error is reduced by 36.58% at the maximum on the flat road. Compared with the disturbance observer-based method, the root mean square error is reduced by 39.11% at the maximum on different-friction and uneven road.

This paper proposes a hierarchical sizing method and a power distribution strategy of a hybrid energy storage system for plug-in hybrid electric vehicles (PHEVs), aiming to reduce both the energy consumption and battery degradation cost. As the optimal size matching is significant to multi-energy systems like PHEV with both battery and supercapacitor (SC), this hybrid system is adopted herein. First, the hierarchical optimization is conducted, when the optimal power of the internal combustion engine is calculated based on dynamic programming, and a wavelet transformer is introduced to distribute the power between the battery and the SC. Then, the fuel economy and battery degradation are evaluated to return feedback value to each sizing point within the hybrid energy storage system sizing space, obtaining the optimal sizes for the battery and the SC by comparing all the values in the whole sizing space. Finally, an all-hardware test platform is established with a fully active power conversion topology, on which the real-time control capability of the wavelet transformer method and the size matching between the battery and the SC are verified in both short and long time spans.