Driver perception, decision, and control behaviors are easily affected by traffic conditions and driving style, showing the tendency of randomness and personalization. Brake intention and intensity are integrated and control-oriented parameters that are crucial to the development of an intelligent braking system. In this paper, a composite machine learning approach was proposed to predict driver brake intention and intensity with a proper prediction horizon. Various driving data were collected from Controller Area Network (CAN) bus under a real driving condition, which mainly contained urban and rural road types. ReliefF and RReliefF (they don’t have abbreviations) algorithms were employed as feature subset selection methods and applied in a prepossessing step before the training. The rank importance of selected predictors exhibited different trends or even negative trends when predicting brake intention and intensity. A soft clustering algorithm, Fuzzy C-means, was adopted to label the brake intention into categories, namely slight, medium, intensive, and emergency braking. Data sets with misplaced labels were used for training of an ensemble machine learning method, random forest. It was validated that brake intention could be accurately predicted 0.5 s ahead. An open-loop nonlinear autoregressive with external input (NARX) network was capable of learning the long-term dependencies in comparison to the static neural network and was suggested for online recognition and prediction of brake intensity 1 s in advance. As system redundancy and fault tolerance, a close-loop NARX network could be adopted for brake intensity prediction in the case of possible sensor failure and loss of CAN message.

No abstract

This paper presents a 28 GHz GaN enhanced single‐sideband time‐modulated phased array (ESTMPA), based on a monolithic microwave integrated circuit (MMIC), including both a time‐modulated circuit and an RF front‐end module (FEM). The time‐modulated circuit mainly consists of a numerically controlled attenuator to balance the amplitude, compact phase shifters to generate balanced signals, a reconfigurable power divider, and a quadrature power divider. The FEM mainly consists of a low noise amplifier and a power amplifier, featuring codesign of input/output networks. Based on the in‐phase/quadrature (I/Q) composite modulation technique, a stepped modulation waveform, realized by the time‐modulated circuit, is used to enable a weighted array of phases. This helps generate a scanned beam at the first positive sideband and eliminate the undesired sidebands. The final MMIC‐based four‐element ESTMPA shows a relative suppression level of −16 dB at the positive fifth sideband and −13 dB at the zeroth sideband, and a much higher level at the other undesired sidebands. As a result, a wider signal bandwidth and a higher harmonic efficiency are achieved. In addition, the ESTMPA shows a beam sweeping angle from −30° to 30° in far‐field measurement.

No abstract