arXiv subjects

Ding Zhao

Publications and source records attributed to Ding Zhao.

At least 181 records · Page 10Linked to original sources

arXiv2018

Synthesis of Different Autonomous Vehicles Test Approaches

Currently, the most prevalent way to evaluate an autonomous vehicle is to directly test it on the public road. However, because of recent accidents caused by autonomous vehicles, it becomes controversial about whether on-road tests should be the best approach. Alternatively, people use test tracks or simulation to assess the safety of autonomous vehicles. These approaches are time-efficient and less costly, however, their credibility varies. In this paper, we propose to use a co-Kriging model to synthesize the results from different evaluation approaches, which allows us to fully utilize the information and provides an accurate, affordable, and safe way to assess a design of an autonomous vehicle.

stat.AP↗

arXiv2018

Energy Efficiency and Emission Testing for Connected and Automated Vehicles Using Real-World Driving Data

By using the onboard sensing and external connectivity technology, connected and automated vehicles (CAV) could lead to improved energy efficiency, better routing, and lower traffic congestion. With the rapid development of the technology and adaptation of CAV, it is more critical to develop the universal evaluation method and the testing standard which could evaluate the impacts on energy consumption and environmental pollution of CAV fairly, especially under the various traffic conditions. In this paper, we proposed a new method and framework to evaluate the energy efficiency and emission of the vehicle based on the unsupervised learning methods. Both the real-world driving data of the evaluated vehicle and the large naturalistic driving dataset are used to perform the driving primitive analysis and coupling. Then the linear weighted estimation method could be used to calculate the testing result of the evaluated vehicle. The results show that this method can successfully identify the typical driving primitives. The couples of the driving primitives from the evaluated vehicle and the typical driving primitives from the large real-world driving dataset coincide with each other very well. This new method could enhance the standard development of the energy efficiency and emission testing of CAV and other off-cycle credits.

cs.OH↗

arXiv2018

An "Xcity" Optimization Approach to Designing Proving Grounds for Connected and Autonomous Vehicles

Proving ground, or on-track testing has been an essential part of testing and validation process for connected and autonomous vehicles (CAV). Several world-class CAV proving grounds, such as Mcity at the University of Michigan and The Castle of Waymo, have already been built, and many more are currently under construction. In this paper, we propose the first optimization approach to CAV proving ground designing and refer to any such CAV-centric design problem as "Xcity" to emphasize the enormous investment, the multi-dimensional spatial consideration, and the immense construction effort emerging globally. Inspired by the recent progress on traffic encounter clustering, we further define "road assets" as fundamental building blocks and formulate the whole design process into nonlinear optimization problems. We have shown that such framework can be utilized to adaptively generate CAV proving ground designs with optimized capability and flexibility and can further be extended to evaluate an existing "Xcity" design.

cs.RO↗

arXiv2018

Deep context: end-to-end contextual speech recognition

In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Listen, Attend and Spell (CLAS) jointly- optimizes the ASR components along with embeddings of the context n-grams. During inference, the CLAS system can be presented with context phrases which might contain out-of- vocabulary (OOV) terms not seen during training. We com- pare our proposed system to a more traditional contextualiza- tion approach, which performs shallow-fusion between inde- pendently trained LAS and contextual n-gram models during beam search. Across a number of tasks, we find that the pro- posed CLAS system outperforms the baseline method by as much as 68% relative WER, indicating the advantage of joint optimization over individually trained components. Index Terms: speech recognition, sequence-to-sequence models, listen attend and spell, LAS, attention, embedded speech recognition.

eess.AS↗

arXiv2018

Dynamic control of anapole states with phase-change alloys

High-index dielectric nanoparticles supporting a distinct series of Mie resonances have enabled a new class of optical antennas with unprecedented functionalities. The great wealth of multipolar responses and their delicate interplay have not only spurred practical developments but also brought new insight into fundamental physics such as the recent observation of nonradiating anapole states in the optical regime. However, how to make such a colorful resonance palette actively tunable and even switchable among different elemental multipoles is still elusive. Here, for the first time, we demonstrate both theoretically and experimentally that a structured phase-change alloy Ge$_2$Sb$_2$Te$_5$ (GST) can support a diverse set of multipolar Mie resonances with active tunability and switchability. By harnessing the dramatic optical contrast (Δn > 2) and the intermediate phases of the GST material, we realize continuous switching between a scattering bright state (electric dipole mode) and a dark state (anapole mode) in a broadband range (Δλ > 600 nm). Dynamic control of higher-order anapoles and resulting multimodal switching effects are also systematically investigated, which naturally make the structured GST serve as a multispectral optical switch with high extinction contrasts (> 6 dB) and multi-level control capabilities. With all these findings, our study provides an entirely new design principle for realizing active nanophotonic devices.

physics.optics↗

arXiv2018

Understanding V2V Driving Scenarios through Traffic Primitives

Semantically understanding complex drivers' encountering behavior, wherein two or multiple vehicles are spatially close to each other, does potentially benefit autonomous car's decision-making design. This paper presents a framework of analyzing various encountering behaviors through decomposing driving encounter data into small building blocks, called driving primitives, using nonparametric Bayesian learning (NPBL) approaches, which offers a flexible way to gain an insight into the complex driving encounters without any prerequisite knowledge. The effectiveness of our proposed primitive-based framework is validated based on 976 naturalistic driving encounters, from which more than 4000 driving primitives are learned using NPBL - a sticky HDP-HMM, combined a hidden Markov model (HMM) with a hierarchical Dirichlet process (HDP). After that, a dynamic time warping method integrated with k-means clustering is then developed to cluster all these extracted driving primitives into groups. Experimental results find that there exist 20 kinds of driving primitives capable of representing the basic components of driving encounters in our database. This primitive-based analysis methodology potentially reveals underlying information of vehicle-vehicle encounters for self-driving applications.

cs.LG↗

arXiv2018

Cluster Naturalistic Driving Encounters Using Deep Unsupervised Learning

Learning knowledge from driving encounters could help self-driving cars make appropriate decisions when driving in complex settings with nearby vehicles engaged. This paper develops an unsupervised classifier to group naturalistic driving encounters into distinguishable clusters by combining an auto-encoder with k-means clustering (AE-kMC). The effectiveness of AE-kMC was validated using the data of 10,000 naturalistic driving encounters which were collected by the University of Michigan, Ann Arbor in the past five years. We compare our developed method with the $k$-means clustering methods and experimental results demonstrate that the AE-kMC method outperforms the original k-means clustering method.

cs.LG↗

arXiv2018

Evaluation of the Energy Efficiency in a Mixed Traffic with Automated Vehicles and Human Controlled Vehicles

The energy efficiency of Connected and Automated Vehicles (CAVs) is significantly influenced by surrounding road users. This paper presents the evaluation of energy efficiency of CAVs in a mixed traffic interacted with human controlled vehicles. To simulate the interaction between the CAVs and the cut-in vehicles controlled by human drivers near the intersection, a lane changing model is proposed to emulate the politeness and patience characteristics of the human driver. The proposed lane changing model is then calibrated based on over 100,000 naturalistic lane changing events collected by the University of Michigan Safety Pilot Model Deployment Program. A case study on simulation of the cut-in scenario is carried out to demonstrate the human driver's lane changing sensitivity under different driving trajectories of a frontal CAV and the influence on the energy consumption of the CAV due to the cut-in vehicle is evaluated. The simulation results indicate that the fuel economy of the CAV can be substantially improved if its surrounding cut-in vehicles can be well handled.

eess.SY↗

arXiv2018

Extracting Traffic Primitives Directly from Naturalistically Logged Data for Self-Driving Applications

Developing an automated vehicle, that can handle complicated driving scenarios and appropriately interact with other road users, requires the ability to semantically learn and understand driving environment, oftentimes, based on analyzing massive amounts of naturalistic driving data. An important paradigm that allows automated vehicles to both learn from human drivers and gain insights is understanding the principal compositions of the entire traffic, termed as traffic primitives. However, the exploding data growth presents a great challenge in extracting primitives from high-dimensional time-series traffic data with various types of road users engaged. Therefore, automatically extracting primitives is becoming one of the cost-efficient ways to help autonomous vehicles understand and predict the complex traffic scenarios. In addition, the extracted primitives from raw data should 1) be appropriate for automated driving applications and also 2) be easily used to generate new traffic scenarios. However, existing literature does not provide a method to automatically learn these primitives from large-scale traffic data. The contribution of this paper has two manifolds. The first one is that we proposed a new framework to generate new traffic scenarios from a handful of limited traffic data. The second one is that we introduce a nonparametric Bayesian learning method -- a sticky hierarchical Dirichlet process hidden Markov model -- to automatically extract primitives from multidimensional traffic data without prior knowledge of the primitive settings. The developed method is then validated using one day of naturalistic driving data. Experiment results show that the nonparametric Bayesian learning method is able to extract primitives from traffic scenarios where both the binary and continuous events coexist.

cs.CV↗

arXiv2018

Extraction of V2V Encountering Scenarios from Naturalistic Driving Database

It is necessary to thoroughly evaluate the effectiveness and safety of Connected Vehicles (CVs) algorithm before their release and deployment. Current evaluation approach mainly relies on simulation platform with the single-vehicle driving model. The main drawback of it is the lack of network realism. To overcome this problem, we extract naturalistic V2V encounters data from the database, and then separate the primary vehicle encounter category by clustering. A fast mining algorithm is proposed that can be applied to parallel query for further process acceleration. 4,500 encounters are mined from a 275 GB database collected in the Safety Pilot Model Program in Ann Arbor Michigan, USA. K-means and Dynamic Time Warping (DTW) are used in clustering. Results show this method can quickly mine and cluster primary driving scenarios from a large database. Our results separate the car-following, intersection and by-passing, which are the primary category of the vehicle encounter. We anticipate the work in the essay can become a general method to effectively extract vehicle encounters from any existing database that contains vehicular GPS information. What's more, the naturalistic data of different vehicle encounters can be applied in Connected Vehicles evaluation.

cs.LG↗

arXiv2018

An Optimal LiDAR Configuration Approach for Self-Driving Cars

LiDARs plays an important role in self-driving cars and its configuration such as the location placement for each LiDAR can influence object detection performance. This paper aims to investigate an optimal configuration that maximizes the utility of on-hand LiDARs. First, a perception model of LiDAR is built based on its physical attributes. Then a generalized optimization model is developed to find the optimal configuration, including the pitch angle, roll angle, and position of LiDARs. In order to fix the optimization issue with off-the-shelf solvers, we proposed a lattice-based approach by segmenting the LiDAR's range of interest into finite subspaces, thus turning the optimal configuration into a nonlinear optimization problem. A cylinder-based method is also proposed to approximate the objective function, thereby making the nonlinear optimization problem solvable. A series of simulations are conducted to validate our proposed method. This proposed approach to optimal LiDAR configuration can provide a guideline to researchers to maximize the utility of LiDARs.

cs.RO↗

arXiv2018

A Tempt to Unify Heterogeneous Driving Databases using Traffic Primitives

A multitude of publicly-available driving datasets and data platforms have been raised for autonomous vehicles (AV). However, the heterogeneities of databases in size, structure and driving context make existing datasets practically ineffective due to a lack of uniform frameworks and searchable indexes. In order to overcome these limitations on existing public datasets, this paper proposes a data unification framework based on traffic primitives with ability to automatically unify and label heterogeneous traffic data. This is achieved by two steps: 1) Carefully arrange raw multidimensional time series driving data into a relational database and then 2) automatically extract labeled and indexed traffic primitives from traffic data through a Bayesian nonparametric learning method. Finally, we evaluate the effectiveness of our developed framework using the collected real vehicle data.

cs.CV↗

arXiv2018

Interpenetrating Cooperative Localization in Dynamic Connected Vehicle Networks

In this paper, we proposed the Interpenetrating Cooperative Localization (ICL) method to enhance the localization accuracy in dynamic connected vehicle networks. This mechanism makes the information from one group of connected vehicles interpenetrate to other groups without full communication between all nodes, thus improving the utility of information in a low connected vehicle penetration situation. We tested the approach using the dynamic traffic data collected in the Safety Pilot Model Deployment program in Ann Arbor Michigan, USA, with dynamic changing networks due to the traveling of vehicles and packet drops of the Dedicated Short-Range Communication. Results show enhancement of localization accuracy with errors reduced by up to 70 % even in complex dynamic scenarios.

eess.SY↗

arXiv2018

Learning and Inferring a Driver's Braking Action in Car-Following Scenarios

Accurately predicting and inferring a driver's decision to brake is critical for designing warning systems and avoiding collisions. In this paper we focus on predicting a driver's intent to brake in car-following scenarios from a perception-decision-action perspective according to his/her driving history. A learning-based inference method, using onboard data from CAN-Bus, radar and cameras as explanatory variables, is introduced to infer drivers' braking decisions by combining a Gaussian mixture model (GMM) with a hidden Markov model (HMM). The GMM is used to model stochastic relationships among variables, while the HMM is applied to infer drivers' braking actions based on the GMM. Real-case driving data from 49 drivers (more than three years' driving data per driver on average) have been collected from the University of Michigan Safety Pilot Model Deployment database. We compare the GMM-HMM method to a support vector machine (SVM) method and an SVM-Bayesian filtering method. The experimental results are evaluated by employing three performance metrics: accuracy, sensitivity, specificity. The comparison results show that the GMM-HMM obtains the best performance, with an accuracy of 90%, sensitivity of 84%, and specificity of 97%. Thus, we believe that this method has great potential for real-world active safety systems.

cs.LG↗

arXiv2017

A Versatile Approach to Evaluating and Testing Automated Vehicles based on Kernel Methods

Evaluation and validation of complicated control systems are crucial to guarantee usability and safety. Usually, failure happens in some very rarely encountered situations, but once triggered, the consequence is disastrous. Accelerated Evaluation is a methodology that efficiently tests those rarely-occurring yet critical failures via smartly-sampled test cases. The distribution used in sampling is pivotal to the performance of the method, but building a suitable distribution requires case-by-case analysis. This paper proposes a versatile approach for constructing sampling distribution using kernel method. The approach uses statistical learning tools to approximate the critical event sets and constructs distributions based on the unique properties of Gaussian distributions. We applied the method to evaluate the automated vehicles. Numerical experiments show proposed approach can robustly identify the rare failures and significantly reduce the evaluation time.

cs.LG↗

arXiv2017

A Kinodynamic Aggressive Trajectory Planner For Narrow Passages

Planning a path for a nonholonomic robot is a challenging topic in motion planning and it becomes more difficult when the desired path contains narrow passages. This kind of scenario can arise, for instance, when quadcopters search a collapsed building after a natural disaster. Choosing the quadcopter as the target platform, this paper proposes the Kinodynamic Aggressive Trajectory (KAT) motion planning algorithm, which aims to compute aggressive trajectories for narrow passages under nonholonomic constraints. This type of maneuvers is necessary because the dynamics of quadcopters entail that some narrow passages can only be traversed at high speed. To find the best path, the KAT uses RRT to determine a holonomic path first and then adjusts it to satisfy the nonholonomic constraints. The innovations in this process are: 1) The states of the robot are divided into near-holonomic set and non-holonomic set, which makes the constraints local rather than global; 2) For each of the most confined waypoints in the path, KAT plans forward and backward simultaneously around the waypoint to find a feasible local trajectory traversing the narrow passage. Our approach thus transforms a globally-constrained planning problem into a problem with local constraints, and as a result, the computation becomes tractable. We evaluate KAT by applying it to a quadcopter flying through two inclined holes that require aggressive maneuvers in a simulated environment. The average computation time to successfully find a solution for passing two 50 degree inclined holes is around 32 seconds.

eess.SY↗

arXiv2017

Semi-Interpenetrating Cooperative Localization in Connected Vehicle Networks

We proposed a fusion mechanism for the distributed cooperative map matching (CMM) within the vehicular ad-hoc network. This mechanism makes the information from each node reachable within the network by other nodes without direct communication, thus improving the overall localization accuracy and robustness. Each node runs a Rao-Blackwellized particle filter (RBPF) that processes the Global Navigation Satellite System (GNSS) measurements of its own and its neighbors, followed by a map matching step that reduces or eliminates the GNSS atmospheric error. Then each node fuses its own filtered results with those from its neighbors for a better estimation. In this work, the complicated dynamics and fusion mechanics of these RBPFs are represented by a linear dynamical system. We proposed a distributed optimization framework that explores the model to improve both robustness and accuracy of the distributed CMM. The effectiveness of this distributed optimization framework is illustrated by simulation results on realistic vehicular networks drawn from data, compared with the centralized one and a decentralized one with random fusion weights.

eess.SY↗

arXiv2017

Edge states in self-complementary checkerboard photonic crystals: Zak phase, surface impedance and experimental verification

Edge states of photonic crystals have attracted much attention for the potential applications such as high transmission waveguide bends, spin dependent splitters and one-way photonic circuits. Here, we theoretically discuss and experimentally observe the deterministic edge states in checkerboard photonic crystals. Due to the self-complementarity of checkerboard photonic crystals, a common band gap is structurally protected between two photonic crystals with different unit cells. Deterministic edge states are found inside the common band gap by exploiting the Zak phase analysis and surface impedance calculation. These edge states are also confirmed by a microwave experiment.

physics.optics↗