For W-band long-range mm-wave wireless transmission systems, nonlinearity issues resulting from photoelectric devices, optical fibers, and wireless power amplifiers can be handled by deep learning equalization algorithms. In addition, the PS technique is considered an effective measure to further increase the capacity of the modulation-constraint channel. However, since the probabilistic distribution of m-QAM varies with the amplitude, there have been difficulties in learning valuable information from the minority class. This limits the benefit of nonlinear equalization. To overcome the imbalanced machine learning problem, we propose a novel two-lane DNN (TLD) equalizer using the random oversampling (ROS) technique in this paper. The combination of PS at the transmitter and ROS at the receiver improved the overall performance of the W-band wireless transmission system, and our 4.6-km ROF delivery experiment verified its effectiveness for the W-band mm-wave PS-16QAM system. Based on our proposed equalization scheme, we achieved single-channel 10-Gbaud W-band PS-16QAM wireless transmission over a 100 m optical fiber link and a 4.6 km wireless air-free distance. The results show that compared with the typical TLD without ROS, the TLD-ROS can improve the receiver‘s sensitivity by 1 dB. Furthermore, a reduction of 45.6% in complexity was achieved, and we were able to reduce training samples by 15.5%. Considering the actual wireless physical layer and its requirements, there is much to be gained from the joint use of deep learning and balanced data pre-processing techniques.

For W-band long-range mm-wave wireless transmission systems, nonlinearity issues resulting from photoelectric devices, optical fiber, and wireless power amplifiers can be handled by deep learning equalization algorithms. Besides, the PS technique is considered an effective measure to further increase the capacity of the modulation-constraint channel. However, since the proba-bilistic distribution of m-QAM varies with the amplitude, there have been difficulties in learning valuable information from the minority class. This limits the gain of nonlinear equalization. To overcome the imbalanced machine learning problem, we propose a novel two-lane DNN (TLD) equalizer with the random over-sampling (ROS) technique in this paper. The combination of PS at the transmitter and ROS at the receiver improves the overall performance of the W-band wireless transmission system, and our 4.6-km ROF delivery experiment verifies its effectiveness for the W-band mm-wave PS-16QAM system. Based on our proposed equalization scheme, we realize single-channel 10-Gbaud W-band PS-16QAM wireless transmission over 100 m optical fiber link and 4.6-km wireless air-free distance. The results show that compared with the typical TLD without ROS, the TLD-ROS can improve the receiver sensitivity by 1dB. Furthermore, a reduction of 45.6% in complexity is realized, and training samples can be reduced by 15.5%. Considering the actual wireless physical layer with its requirements, there is much to be gained from the joint use of deep learning and balanced data pre-processing techniques.

Autonomous mobile robots require robust traversability perception to navigate safely in diverse outdoor environments. However, traditional deep learning approaches are data-hungry, requiring large-scale manual annotations, and struggle to adapt quickly to unseen environments. This paper introduces TARTS (Training-free Adaptive Reference-guided Traversability Segmentation), a novel framework combining one-shot prototype initialization with trajectory-guided online adaptation for terrain segmentation. Using a single reference image of desired traversable terrain, TARTS establishes an initial prototype from pre-trained DINO Vision Transformer (ViT) features. The system performs segmentation through superpixel-based feature aggregation and valley-emphasis Otsu thresholding while continuously refining the prototype via Exponential Moving Average (EMA) updates driven by automated footprint supervision from the robot’s traversed trajectory. Extensive experiments on our introduced Reference-guided Traversability Segmentation Dataset (RTSD) and the challenging Off-Road Freespace Detection (ORFD) benchmark demonstrate strong performance, achieving 94.5% IoU on RTSD and 94.1% IoU on ORFD, outperforming state-of-the-art supervised methods that require multi-modal inputs and dedicated training. The framework maintains efficient performance (17–24 FPS) on embedded platforms, enabling practical deployment with only a reference image as initialization.