Jose Guivant

Karan Narula, Jose Guivant

Compressed Estimation approaches, such as the Generalised Compressed Kalman Filter (GCKF), reduce the computational cost and complexity of high dimensional and high frequency data assimilation problems; usually without sacrificing optimality. Configured using adequate cores, such as the Unscented Kalman Filter (UKF), the GCKF could also treat certain non-linear cases. However, the application of a compressed estimation process is limited to a class of problems which inherently allow the estimation process to be divided, at certain intervals of time, in a subset of lower dimensional problems. This limitation prohibits applying the compressing techniques for estimating densely coupled high dimensional processes. However, those limitations can be overcome by applying proper techniques. In this paper, the concept of subsystem switching, and information exchange architecture, namely Exploiting Local Statistical Dependency (ELSD), has been derived and explored, for allowing compressed estimators to mimic optimal full Gaussian estimators. The performances of the methods have been verified through its application in solving usual types of linear Stochastic Partial Differential Equations (SPDEs). The computational advantages of using the proposed techniques have also been highlighted with recommendation of its usage over the full filter when dealing with high dimensional and high frequency data assimilation.

Xuesong Li, Xinge Zhu, Yuexin Ma et al.

In this paper, we propose an algorithm for registering sequential bounding boxes with point cloud streams. Unlike popular point cloud registration techniques, the alignment of the point cloud and the bounding box can rely on the properties of the bounding box, such as size, shape, and temporal information, which provides substantial support and performance gains. Motivated by this, we propose a new approach to tackle this problem. Specifically, we model the registration process through an overall objective function that includes the final goal and all constraints. We then optimize the function using gradient descent. Our experiments show that the proposed method performs remarkably well with a 40\% improvement in IoU and demonstrates more robust registration between point cloud streams and sequential bounding boxes

Hong Liang Cheah, Mohammad Deghat, Jose Guivant

This paper addresses bearing-only algorithms for solving the Fermat-Weber Location Problem (FWLP) with a unicycle agent. Unlike existing FWLP solutions for single- or double-integrator agents, our approach accounts for the nonholonomic constraints of wheeled robots. We first develop a bearing-only control law for the case with stationary beacons. Next, we consider saturated control inputs and propose a corresponding bearing-only control law. Finally, we address moving beacons with constant velocities and develop a control law that enables the unicycle agent to track the moving Fermat-Weber point. Both simulations and experiments are provided to demonstrate the effectiveness of the proposed methods.

Xuesong Li, Jose Guivant

Interacting with the environment, such as object detection and tracking, is a crucial ability of mobile robots. Besides high accuracy, efficiency in terms of processing effort and energy consumption are also desirable. To satisfy both requirements, we propose a detection framework based on simultaneous classification and tracking in the point stream. In this framework, a tracker performs data association in sequences of the point cloud, guiding the detector to avoid redundant processing (i.e. classifying already-known objects). For objects whose classification is not sufficiently certain, a fusion model is designed to fuse selected key observations that provide different perspectives across the tracking span. Therefore, performance (accuracy and efficiency of detection) can be enhanced. This method is particularly suitable for detecting and tracking moving objects, a process that would require expensive computations if solved using conventional procedures. Experiments were conducted on the benchmark dataset, and the results showed that the proposed method outperforms original tracking-by-detection approaches in both efficiency and accuracy.

Xuesong Li, Jose Guivant, Subhan Khan

The task of detecting 3D objects is important to various robotic applications. The existing deep learning-based detection techniques have achieved impressive performance. However, these techniques are limited to run with a graphics processing unit (GPU) in a real-time environment. To achieve real-time 3D object detection with limited computational resources for robots, we propose an efficient detection method consisting of 3D proposal generation and classification. The proposal generation is mainly based on point segmentation, while the proposal classification is performed by a lightweight convolution neural network (CNN) model. To validate our method, KITTI datasets are utilized. The experimental results demonstrate the capability of proposed real-time 3D object detection method from the point cloud with a competitive performance of object recall and classification.

Xuesong Li, Jose Guivant, Ngaiming Kwok et al.

The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature extraction methods. To address this issue, this study proposes a 3D backbone network to acquire comprehensive 3D feature maps for 3D object detection. It primarily consists of sparse 3D convolutional neural network operations in the point cloud. The 3D backbone network can inherently learn 3D features from the raw data without compressing the point cloud into multiple 2D images. The sparse 3D convolutional neural network takes full advantage of the sparsity in the 3D point cloud to accelerate computation and save memory, which makes the 3D backbone network feasible in a real-world application. Empirical experiments were conducted on the KITTI benchmark and comparable results were obtained with respect to the state-of-the-art performance for 3D object detection.