For autonomous driving, it is important to detect obstacles in all scales accurately for safety consideration. In this paper, we propose a new spatial attention fusion (SAF) method for obstacle detection using mmWave radar and vision sensor, where the sparsity of radar points are considered in the proposed SAF. The proposed fusion method can be embedded in the feature-extraction stage, which leverages the features of mmWave radar and vision sensor effectively. Based on the SAF, an attention weight matrix is generated to fuse the vision features, which is different from the concatenation fusion and element-wise add fusion. Moreover, the proposed SAF can be trained by an end-to-end manner incorporated with the recent deep learning object detection framework. In addition, we build a generation model, which converts radar points to radar images for neural network training. Numerical results suggest that the newly developed fusion method achieves superior performance in public benchmarking. In addition, the source code will be released in the GitHub.

Automatic modulation classification (AMC) is to identify the modulation type of a received signal, which plays a vital role to ensure the physical-layer security for Internet of Things (IoT) networks. Inspired by the great success of deep learning in pattern recognition, the convolutional neural network (CNN) and recurrent neural network (RNN) are introduced into the AMC. In general, there are two popular data formats used by AMC, which are the in-phase/quadrature (I/Q) representation and amplitude/phase (A/P) representation, respectively. However, most of AMC algorithms aim at structure innovations, while the differences and characteristics of I/Q and A/P are ignored to analyze. In this article, lots of popular AMC algorithms are reproduced and evaluated on the same data set, where the I/Q and A/P are used, respectively, for comparison. Based on the experimental results, it is found that: 1) CNN-RNN-like algorithms using A/P as input data are superior to those using I/Q at high signal-to-noise ratio (SNR), while it has an opposite result in low SNR and 2) the features extracted from I/Q and A/P are complementary to each other. Motivated by the aforementioned findings, a multitask learning-based deep neural network (MLDNN) is proposed, which effectively fuses I/Q and A/P. In addition, the MLDNN also has a novel backbone, which is made up of three blocks to extract discriminative features, and they are CNN block, bidirectional gated recurrent unit (BiGRU) block, and a step attention fusion network (SAFN) block. Different from most of CNN-RNN-like algorithms (i.e., they only use the last step outputs of RNN), all step outputs of BiGRU can be effectively utilized by MLDNN with the help of SAFN. Extensive simulations are conducted to verify that the proposed MLDNN achieves superior performance in the public benchmark.

The development of the Internet of Things (IoT) security is comparatively slower than the pace of the IoT innovations. The seamless IoT network operates in an untrusted environment and is exposed to many malicious active attacks. As the process of identifying the modulation format of signals corrupted by noise and fading, automatic modulation classification (AMC) can be viewed as an effective approach to counter physical-layer threats for IoT as it can detect and identify the pilot jamming, deceptive jamming and sybil attacks. Nowadays, data-driven deep learning techniques, which are capable of extracting discriminative features and perform better robustness to channel and noise conditions, have drawn widespread attention. Deep residual network (ResNet) has strong representative ability, which can learn latent information repeatedly from the received signals and improve the classification accuracy. Meanwhile, the gated recurrent unit (GRU), which is capable of exploiting temporal information of the received signal can expand the dimension of the signal features for satisfactory classification performance. Considering the advantages of the above networks, this paper proposes a novel gated recurrent residual neural network (GrrNet) for feature-based AMC, where the amplitude and phase of the received signal are utilized as the inputs of GrrNet. In GrrNet, ResNet extractor module is first designed to extract the highly representative features and then temporal information is obtained by the subsequent GRU module which is capable of processing the representative features with arbitrary length for modulation classification. Moreover, extensive simulations are conducted to verify the classification performance and robustness of the proposed GrrNet and it is shown that GrrNet outperforms other recent deep learning-based AMC methods. Moreover, the influence of the network parameters, symbol length and frequency offset on performance is also explored.

Automatic modulation classification (AMC) aims at identifying the modulation format of the received signal. In this letter, we propose a novel grid constellation matrix (GCM) based AMC method using a contrastive fully convolutional network (CFCN). We use GCMs as the input of the network, which are extracted from the received signals using low-complexity preprocessing. Moreover, a loss function with contrastive loss is designed to train the CFCN, which boosts the discrepancies among different modulations and obtains discriminative representations. Extensive simulations demonstrate that CFCN performs superior classification performance and better robustness to model mismatches with low training time comparing with other recent methods.

Robust channel estimation in time-varying channels is used to guarantee the quality of communication services, especially for Vehicle-to-Everything (V2X) scenarios. To improve the channel estimation accuracy and reduce the pilot overhead, multi-input multi-output (MIMO) radar is deployed to assist millimeter wave (mmWave) channel estimation. In this paper, we propose a MIMO radar aided channel estimation scheme using deep learning (DL) for the uplink mmWave multiuser (MU)-MIMO communications. To allocate pilot resources reasonably, we design a transmission frame structure of joint radar module and communication module, which divides the estimation scheme into two stages, i.e., the arrival/departure (AoA/AoDs) estimation stage and the gain estimation stage. In view of the imperfections of array elements in practice, we propose an AoA/AoDs estimation algorithm based on subspace reconstruction in the AoA/AoDs estimation stage named two-step angle estimation (TSAE) algorithm. In the gain estimation stage, a DL based channel gain estimator is designed. An autoencoder combined with residual structure named residual denoising autoencoder (RDAE) is proposed to eliminate the noise on wireless signals, which is passed into the least square (LS) estimation module to obtain gains. Simulation results demonstrate that the MIMO radar aided and DL-based channel estimator provides the efficient estimation performance of the high-mobility mmWave channel with fewer training resources.

The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. Simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.