arXiv subjects

Yuhang Chen

Publications and source records attributed to Yuhang Chen.

46 records · Page 3Linked to original sources

arXiv2021

ComOpT: Combination and Optimization for Testing Autonomous Driving Systems

ComOpT is an open-source research tool for coverage-driven testing of autonomous driving systems, focusing on planning and control. Starting with (i) a meta-model characterizing discrete conditions to be considered and (ii) constraints specifying the impossibility of certain combinations, ComOpT first generates constraint-feasible abstract scenarios while maximally increasing the coverage of k-way combinatorial testing. Each abstract scenario can be viewed as a conceptual equivalence class, which is then instantiated into multiple concrete scenarios by (1) randomly picking one local map that fulfills the specified geographical condition, and (2) assigning all actors accordingly with parameters within the range. Finally, ComOpT evaluates each concrete scenario against a set of KPIs and performs local scenario variation via spawning a new agent that might lead to a collision at designated points. We use ComOpT to test the Apollo~6 autonomous driving software stack. ComOpT can generate highly diversified scenarios with limited test budgets while uncovering problematic situations such as inabilities to make simple right turns, uncomfortable accelerations, and dangerous driving patterns. ComOpT participated in the 2021 IEEE AI Autonomous Vehicle Testing Challenge and won first place among more than 110 contending teams.

cs.RO↗

arXiv2021

ThunderRW: An In-Memory Graph Random Walk Engine (Complete Version)

As random walk is a powerful tool in many graph processing, mining and learning applications, this paper proposes an efficient in-memory random walk engine named ThunderRW. Compared with existing parallel systems on improving the performance of a single graph operation, ThunderRW supports massive parallel random walks. The core design of ThunderRW is motivated by our profiling results: common RW algorithms have as high as 73.1% CPU pipeline slots stalled due to irregular memory access, which suffers significantly more memory stalls than the conventional graph workloads such as BFS and SSSP. To improve the memory efficiency, we first design a generic step-centric programming model named Gather-Move-Update to abstract different RW algorithms. Based on the programming model, we develop the step interleaving technique to hide memory access latency by switching the executions of different random walk queries. In our experiments, we use four representative RW algorithms including PPR, DeepWalk, Node2Vec and MetaPath to demonstrate the efficiency and programming flexibility of ThunderRW. Experimental results show that ThunderRW outperforms state-of-the-art approaches by an order of magnitude, and the step interleaving technique significantly reduces the CPU pipeline stall from 73.1% to 15.0%.

cs.DB↗

arXiv2021

Hybrid Spherical- and Planar-Wave Channel Modeling and DCNN-powered Estimation for Terahertz Ultra-massive MIMO Systems

The Terahertz band is envisioned to meet the demanding 100 Gbps data rates for 6G wireless communications. Aiming at combating the distance limitation problem with low hardware-cost, ultra-massive MIMO with hybrid beamforming is promising. However, relationships among wavelength, array size and antenna spacing give rise to the inaccuracy of planar-wave channel model (PWM), while an enlarged channel matrix dimension leads to excessive parameters of applying spherical-wave channel model (SWM). Moreover, due to the adoption of hybrid beamforming, channel estimation (CE) needs to recover high-dimensional channels from severely compressed channel observation. In this paper, a hybrid spherical- and planar-wave channel model (HSPM) is investigated and proved to be accurate and efficient by adopting PWM within subarray and SWM among subarray. Furthermore, a two-phase HSPM CE mechanism is developed. A deep convolutional-neural-network (DCNN) is designed in the first phase for parameter estimation of reference subarrays, while geometric relationships of the remaining channel parameters between reference subarrays are leveraged to complete CE in the second phase. Extensive numerical results demonstrate the HSPM is accurate at various communication distances, array sizes and carrier frequencies.The DCNN converges fast and achieves high accuracy with 5.2 dB improved normalized-mean-square-error compared to literature methods, and owns substantially low complexity.

cs.IT↗

arXiv2021

Joint Inter-path and Intra-path Multiplexing for Terahertz Widely-spaced Multi-subarray Hybrid Beamforming Systems

Terahertz (THz) communications with multi-GHz bandwidth are envisioned as a key technology for 6G systems. Ultra-massive (UM) MIMO with hybrid beamforming architectures are widely investigated to provide a high array gain to overcome the huge propagation loss. However, most of the existing hybrid beamforming architectures can only utilize the multiplexing offered by the multipath components, i.e., inter-path multiplexing, which is very limited due to the spatially sparse THz channel. In this paper, a widely-spaced multi-subarray (WSMS) hybrid beamforming architecture is proposed, which improves the multiplexing gain by exploiting a new type of intra-path multiplexing provided by the spherical-wave propagation among k widely-spaced subarrays, in addition to the inter-path multiplexing. The resulting multiplexing gain of WSMS architecture is k times of the existing architectures. To harness WSMS hybrid beamforming, a novel design problem is formulated by optimizing the number of subarrays, subarray spacing, and hybrid beamforming matrices to maximize the spectral efficiency, which is decomposed into two subproblems. An optimal closed-form solution is derived for the first hybrid beamforming subproblem, while a dominant-line-of-sight-relaxation algorithm is proposed for the second array configuration subproblem. Extensive simulation results demonstrate that the WSMS architecture and proposed algorithms substantially enhance the spectral efficiency and energy efficiency.

cs.IT↗

arXiv2021

Monitoring Object Detection Abnormalities via Data-Label and Post-Algorithm Abstractions

While object detection modules are essential functionalities for any autonomous vehicle, the performance of such modules that are implemented using deep neural networks can be, in many cases, unreliable. In this paper, we develop abstraction-based monitoring as a logical framework for filtering potentially erroneous detection results. Concretely, we consider two types of abstraction, namely data-label abstraction and post-algorithm abstraction. Operated on the training dataset, the construction of data-label abstraction iterates each input, aggregates region-wise information over its associated labels, and stores the vector under a finite history length. Post-algorithm abstraction builds an abstract transformer for the tracking algorithm. Elements being associated together by the abstract transformer can be checked against consistency over their original values. We have implemented the overall framework to a research prototype and validated it using publicly available object detection datasets.

cs.AI↗

arXiv2021

PathEnum: Towards Real-Time Hop-Constrained s-t Path Enumeration

We study the hop-constrained s-t path enumeration (HcPE) problem, which takes a graph $G$, two distinct vertices $s,t$ and a hop constraint $k$ as input, and outputs all paths from $s$ to $t$ whose length is at most $k$. The state-of-the-art algorithms suffer from severe performance issues caused by the costly pruning operations during enumeration for the workloads with the large search space. Consequently, these algorithms hardly meet the real-time constraints of many online applications. In this paper, we propose PathEnum, an efficient index-based algorithm towards real-time HcPE. For an input query, PathEnum first builds a light-weight index aiming to reduce the number of edges involved in the enumeration, and develops efficient index-based approaches for enumeration, one based on depth-first search and the other based on joins. We further develop a query optimizer based on a join-based cost model to optimize the search order. We conduct experiments with 15 real-world graphs. Our experiment results show that PathEnum outperforms the state-of-the-art approaches by orders of magnitude in terms of the query time, throughput and response time.

cs.DB↗

arXiv2020

Training Deep Neural Networks for Wireless Sensor Networks Using Loosely and Weakly Labeled Images

Although deep learning has achieved remarkable successes over the past years, few reports have been published about applying deep neural networks to Wireless Sensor Networks (WSNs) for image targets recognition where data, energy, computation resources are limited. In this work, a Cost-Effective Domain Generalization (CEDG) algorithm has been proposed to train an efficient network with minimum labor requirements. CEDG transfers networks from a publicly available source domain to an application-specific target domain through an automatically allocated synthetic domain. The target domain is isolated from parameters tuning and used for model selection and testing only. The target domain is significantly different from the source domain because it has new target categories and is consisted of low-quality images that are out of focus, low in resolution, low in illumination, low in photographing angle. The trained network has about 7M (ResNet-20 is about 41M) multiplications per prediction that is small enough to allow a digital signal processor chip to do real-time recognitions in our WSN. The category-level averaged error on the unseen and unbalanced target domain has been decreased by 41.12%.

cs.CV↗

arXiv2020

HaoCL: Harnessing Large-scale Heterogeneous Processors Made Easy

The pervasive adoption of Deep Learning (DL) and Graph Processing (GP) makes it a de facto requirement to build large-scale clusters of heterogeneous accelerators including GPUs and FPGAs. The OpenCL programming framework can be used on the individual nodes of such clusters but is not intended for deployment in a distributed manner. Fortunately, the original OpenCL semantics naturally fit into the programming environment of heterogeneous clusters. In this paper, we propose a heterogeneity-aware OpenCL-like (HaoCL) programming framework to facilitate the programming of a wide range of scientific applications including DL and GP workloads on large-scale heterogeneous clusters. With HaoCL, existing applications can be directly deployed on heterogeneous clusters without any modifications to the original OpenCL source code and without awareness of the underlying hardware topologies and configurations. Our experiments show that HaoCL imposes a negligible overhead in a distributed environment, and provides near-linear speedups on standard benchmarks when computation or data size exceeds the capacity of a single node. The system design and the evaluations are presented in this demo paper.

cs.DC↗

arXiv2019

Towards the Automation of Deep Image Prior

Single image inverse problem is a notoriously challenging ill-posed problem that aims to restore the original image from one of its corrupted versions. Recently, this field has been immensely influenced by the emergence of deep-learning techniques. Deep Image Prior (DIP) offers a new approach that forces the recovered image to be synthesized from a given deep architecture. While DIP is quite an effective unsupervised approach, it is deprecated in real-world applications because of the requirement of human assistance. In this work, we aim to find the best-recovered image without the assistance of humans by adding a stopping criterion, which will reach maximum when the iteration no longer improves the image quality. More specifically, we propose to add a pseudo noise to the corrupted image and measure the pseudo-noise component in the recovered image by the orthogonality between signal and noise. The accuracy of the orthogonal stopping criterion has been demonstrated for several tested problems such as denoising, super-resolution, and inpainting, in which 38 out of 40 experiments are higher than 95%.

cs.CV↗

arXiv2016

Stochastic collocation methods via $L_1$ minimization using randomized quadratures

In this work, we discuss the problem of approximating a multivariate function via $\ell_1$ minimization method, using a random chosen sub-grid of the corresponding tensor grid of Gaussian points. The independent variables of the function are assumed to be random variables, and thus, the framework provides a non-intrusive way to construct the generalized polynomial chaos expansions, stemming from the motivating application of Uncertainty Quantification (UQ). We provide theoretical analysis on the validity of the approach. The framework includes both the bounded measures such as the uniform and the Chebyshev measure, and the unbounded measures which include the Gaussian measure. Several numerical examples are given to confirm the theoretical results.

math.NA↗