This work proposes a novel sensor fusion-based, single-frame, multi-class object detection method for road users, including vehicles , pedestrians , and cyclists , in which a deep fusion occurs between the lidar point cloud and the corresponding Doppler contexts, namely the Doppler features, from the radar cube. Based on convolutional neural networks, the method consists of two stages: In the first stage, region proposals are generated from the voxelized lidar point cloud, and relying on these proposals, Doppler contexts are cropped from the radar cube. In the second stage, employing fused features from the lidar and radar, the method achieves object detection and object motion status classification tasks. When evaluated with measurements in inclement conditions, which are generated by a foggification model from real-life measurements, in terms of the intersection over union metric, the proposed method outperforms the lidar-based network by a large margin for vulnerable road users, namely 4.5% and 6.1% improvement for pedestrians and cyclists , respectively. In addition, it achieves 87% F 1 score (81.6% precision and 93.1% recall) for single-frame, object motion status classification.

Nowadays, additive manufacturing provides far-reaching possibilities for use in radio frequency components. In addition to almost unlimited freedom of design as compared to conventional manufacturing, the absence of further assembly steps is a key aspect of 3D printing. In this paper, a 3D printed monolithic antenna for millimeter wave-sensing applications is presented with a full hemispherical coverage. The antenna is designed as an ensemble of a waveguide horn antenna and a differentially fed dipole antenna. The slotted waveguide approach was utilized to improve the manufacturing quality on the waveguide inside. The influence of two optimized antenna elements, a metal plane, and a cut-out window, on the beam pattern is comprehensively investigated. A huge half power beam width of 142∘ in both directions, elevation and azimuth, is presented at 79 GHz and a boresight gain of 4.7 dBi was measured. The beam pattern in the frequency range from 76 to 81 GHz is studied in greater detail, where a half power beam width of at least 112∘ is achieved. Due to the -10 dB matching capability bandwidth of over 28 GHz, the antenna is also suitable for extremely broadband applications with a –5 dB angular width of better than 100∘. Furthermore, the system design describes how to integrate the antenna into hybrid circuit designs and the manufacturing tolerances are examined. The antenna offers attractive possibilities for millimeter wave-sensing applications in the area of assisted living and industrial monitoring, especially whenever blind spots have to be avoided.

Precise road scene understanding is of great essence to autonomous driving. As a widely used method for road scene understanding, occupancy grid mapping is leveraged to detect obstacles and predict drivable road areas. Because of its robustness under harsh conditions, low cost, and large perceptual range, radar sensor is becoming increasingly important to achieve various critical perception tasks. However, for radar-based occupancy grid mapping, current inverse sensor model ISM relies on detection data and is most hand-crafted. In this work, we propose a novel data-driven ISM that employs the range- Doppler matrix as the input. With a systematic evaluation and comparison of our model with classic, hand-crafted ISM and the data-driven, detection-based Occupancy Net using RADIal dataset, we find that data-driven models are far superior to their hand-crafted counterpart. Furthermore, although both data-driven models are on par within near range ( $< 50 \,\mathrm{m}$ ), our model outperforms Occupancy Net by a large margin in far range ( $ [50 \,\mathrm{m},100 \,\mathrm{m}]$ ). Specifically, our model has about a 0.3 and 0.4 improvement in distant range for the intersection over union IoU and $\mathrm{F}_{1}$ score, respectively. In addition, leveraging adjacent occupancy grid map prediction, we propose a radar-based occupancy flow to precisely distinguish moving objects.