ZWZining Wang

Zining Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zining Wang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

    by Chenfeng Xu, Bichen Wu, Zining Wang, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka

    LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the \textit{de facto} method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it. Despite the similarity between regular RGB and LiDAR images, we discover that the feature distribution of LiDAR images changes drastically at different image locations. Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image. As a result, the capacity of the network is under-utilized and the segmentation performance decreases. To fix this, we propose Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image. SAC can be computed efficiently since it can be implemented as a series of element-wise multiplications, im2col, and standard convolution. It is a general framework such that several previous methods can be seen as special cases of SAC. Using SAC, we build SqueezeSegV3 for LiDAR point-cloud segmentation and outperform all previous published methods by at least 3.7% mIoU on the SemanticKITTI benchmark with comparable inference speed.


  • Neural-Network-Based Iterative Learning Control for Multiple Tasks

    by Dailin Zhang, Zining Wang, Tomizuka Masayoshi

    Iterative learning control (ILC) can synthesize the feedforward control signal for the trajectory tracking control of a repetitive task, even when the system has strong nonlinear dynamics. This makes ILC be one of the most popular methods for trajectory tracking control. Restriction on a repetitive task, however, limits its application to multiple trajectories. This article proposes a neural-network-based ILC (NN-ILC) to deal with nonrepetitive tasks very effectively. A position-based ILC is designed to compensate the tracking error, based on which the multiple outputs of the ILC (ILC outputs) for multiple tasks are expressed as a function of the reference position, velocity, and acceleration. The proposed NN-ILC divides the ILC outputs of multiple tasks into two parts: the linear and nonlinear portions. The first part is expressed by a linear function, which is the linear portion of the function of the ILC outputs. The second part is expressed by a nonlinear function, which is estimated by complementary neural networks including a general neural network and a switching neural network. Finally, the two parts are combined and the ILC outputs of multiple tasks are expressed as a neural-network-based function. Two advantages of the proposed NN-ILC are emphasized. First, the ILC outputs of multiple tasks are compressed into a function by the proposed method, and thus, the memories can be saved. Second, in terms of generalizability, the neural-network-based function of the ILC outputs can easily predict position compensation for multiple tasks without extra iterative learning processes. Experimental results on a robot arm show that the proposed NN-ILC method can easily realize the ILC of multiple tasks. It can save memory comparing with the method of storing the data of multiple tasks and can predict the ILC output of any task, which can accelerate the iterative learning process.


  • Open Access

    Towards Better Performance and More Explainable Uncertainty for 3D Object Detection of Autonomous Vehicles

    by Hujie Pan, Zining Wang, Wei Zhan, Masayoshi Tomizuka

    In this paper, we propose a novel form of the loss function to increase the performance of LiDAR-based 3d object detection and obtain more explainable and convincing uncertainty for the prediction. The loss function was designed using corner transformation and uncertainty modeling. With the new loss function, the performance of our method on the val split of KITTI dataset shows up to a 15% increase in terms of Average Precision (AP) comparing with the baseline using simple L1 Loss. In the study of the characteristics of predicted uncertainties, we find that generally more accurate prediction of the bounding box is usually accompanied by lower uncertainty. The distribution of corner uncertainties agrees on the distribution of the point cloud in the bounding box, which means the corner with denser observed points has lower uncertainty. Moreover, our method also learns the constraint from the cuboid geometry of the bounding box in uncertainty prediction. Finally, we propose an efficient Bayesian updating method to recover the uncertainty for the original parameters of the bounding boxes which can help to provide probabilistic results for the planning module.


  • Open Access

    Inferring Spatial Uncertainty in Object Detection

    by Zining Wang, Di Feng, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, Wei Zhan

    The availability of real-world datasets is the prerequisite for developing object detection methods for autonomous driving. While ambiguity exists in object labels due to error-prone annotation process or sensor observation noises, current object detection datasets only provide deterministic annotations without considering their uncertainty. This precludes an in-depth evaluation among different object detection methods, especially for those that explicitly model predictive probability. In this work, we propose a generative model to estimate bounding box label uncertainties from LiDAR point clouds, and define a new representation of the probabilistic bounding box through spatial distribution. Comprehensive experiments show that the proposed model represents uncertainties commonly seen in driving scenarios. Based on the spatial distribution, we further propose an extension of IoU, called the Jaccard IoU (JIoU), as a new evaluation metric that incorporates label uncertainty. Experiments on the KITTI and the Waymo Open Datasets show that JIoU is superior to IoU when evaluating probabilistic object detectors.

  • Open Access

    Fusing Bird View LIDAR Point Cloud and Front View Camera Image for Deep Object Detection

    by Zining Wang, Wei Zhan, Masayoshi Tomizuka

    We propose a new method for fusing a LIDAR point cloud and camera-captured images in the deep convolutional neural network (CNN). The proposed method constructs a new layer called non-homogeneous pooling layer to transform features between bird view map and front view map. The sparse LIDAR point cloud is used to construct the mapping between the two maps. The pooling layer allows efficient fusion of the bird view and front view features at any stage of the network. This is favorable for the 3D-object detection using camera-LIDAR fusion in autonomous driving scenarios. A corresponding deep CNN is designed and tested on the KITTI bird view object detection dataset, which produces 3D bounding boxes from the bird view map. The fusion method shows particular benefit for detection of pedestrians in the bird view compared to other fusion-based object detection networks.


  • Robust Iterative Learning Control for Vibration Suppression of Industrial Robot Manipulators

    by Cong Wang, Minghui Zheng, Zining Wang, Cheng Peng, Masayoshi Tomizuka

    Vibration suppression is of fundamental importance to the performance of industrial robot manipulators. Cost constraints, however, limit the design options of servo and sensing systems. The resulting low drive-train stiffness and lack of direct load-side measurement make it difficult to reduce the vibration of the robot's end-effector and hinder the application of robot manipulators to many demanding industrial applications. This paper proposes a few ideas of iterative learning control (ILC) for vibration suppression of industrial robot manipulators. Compared to the state-of-the-art techniques such as the dual-stage ILC method and the two-part Gaussian process regression (GPR) method, the proposed method adopts a two degrees-of-freedom (2DOF) structure and gives a very lean formulation as well as improved effects. Moreover, in regards to the system variations brought by the nonlinear dynamics of robot manipulators, two robust formulations are developed and analyzed. The proposed methods are explained using simulation studies and validated using an actual industrial robot manipulator.