Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework in which machine-generated pseudo-labels on a large unlabeled dataset are used in combination with a small manually-labeled dataset for training. In this work, we address the problem of improving pseudo-label quality through leveraging long- term temporal information captured in driving scenes. More specifically, we leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data to further enhance the student model training. Our approach improves pseudo-label quality in two distinct manners: first, we suppress false positive pseudo-labels through establishing consistency across multiple frames of motion forecasting outputs. Second, we compensate for false negative detections by directly inserting predicted object tracks into the pseudo-labeled scene. Experiments on the nuScenes dataset demonstrate the effectiveness of our approach, improving the performance of standard semi-supervised approaches in a variety of settings.

Leveraging multi-modal fusion, especially between camera and LiDAR, has become essential for building accurate and robust 3D object detection systems for autonomous vehicles. Until recently, point decorating approaches, in which point clouds are augmented with camera features, have been the dominant approach in the field. However, these approaches fail to utilize the higher resolution images from cameras. Recent works projecting camera features to the bird's-eye-view (BEV) space for fusion have also been proposed, however they require projecting millions of pixels, most of which only contain background information. In this work, we propose a novel approach Center Feature Fusion (CFF), in which we leverage center-based detection networks in both the camera and LiDAR streams to identify relevant object locations. We then use the center-based detection to identify the locations of pixel features relevant to object locations, a small fraction of the total number in the image. These are then projected and fused in the BEV frame. On the nuScenes dataset, we outperform the LiDAR-only baseline by 4.9% mAP while fusing up to 100x fewer features than other fusion methods.

Micromachining technology opens up many new opportunities for optical and optoelectronic systems. It offers unprecedented capabilities in extending the functionality of optical devices and the miniaturization of optical systems. Movable structures, microactuators, and microoptical elements can be monolithically integrated on the same substrate using batch processing technologies. In this paper, we review the recent advances in this fast-emerging field. The basic bulk- and surface-micromachining technologies applicable to optical systems are reviewed. The free-space microoptical bench and the concept of optical prealignment are introduced. Examples of micromachined optical devices are described, including optical switches with low loss and high contract ratio, low-cost modulators, micromechanical scanners, and the XYZ micropositioners with large travel distance and fine positioning accuracy. Monolithically integrated systems such as single-chip optical disk pickup heads and a femtosecond autocorrelator have also been demonstrated.