Search Results for author: Ding Zhao

Found 58 papers, 17 papers with code

MHMS: Multimodal Hierarchical Multimedia Summarization

no code implementations7 Apr 2022 JieLin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin

Multimedia summarization with multimodal output can play an essential role in real-world applications, i. e., automatically generating cover images and titles for news articles or providing introductions to online videos.

Test Against High-Dimensional Uncertainties: Accelerated Evaluation of Autonomous Vehicles with Deep Importance Sampling

no code implementations4 Apr 2022 Mansur Arief, Zhepeng Cen, Zhenyuan Liu, Zhiyuang Huang, Henry Lam, Bo Li, Ding Zhao

In this work, we present Deep Importance Sampling (Deep IS) framework that utilizes a deep neural network to obtain an efficient IS that is on par with the state-of-the-art, capable of reducing the required sample size 43 times smaller than the naive sampling method to achieve 10% relative error and while producing an estimate that is much less conservative.

Autonomous Vehicles

PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression

1 code implementation19 Mar 2022 Jiacheng Zhu, Gregory Darnell, Agni Kumar, Ding Zhao, Bo Li, XuanLong Nguyen, Shirley You Ren

The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task.

Heart Rate Variability

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

1 code implementation ICLR 2022 Fan Wu, Linyi Li, Chejian Xu, huan zhang, Bhavya Kailkhura, Krishnaram Kenthapadi, Ding Zhao, Bo Li

We leverage COPA to certify three RL environments trained with different algorithms and conclude: (1) The proposed robust aggregation protocols such as temporal aggregation can significantly improve the certifications; (2) Our certification for both per-state action stability and cumulative reward bound are efficient and tight; (3) The certification for different training algorithms and environments are different, implying their intrinsic robustness properties.

Offline RL reinforcement-learning

Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training

no code implementations19 Feb 2022 Peide Huang, Mengdi Xu, Fei Fang, Ding Zhao

In this paper, we introduce a novel hierarchical formulation of robust RL - a general-sum Stackelberg game model called RRL-Stack - to formalize the sequential nature and provide extra flexibility for robust training.

reinforcement-learning

A Hybrid Physics Machine Learning Approach for Macroscopic Traffic State Estimation

no code implementations1 Feb 2022 Zhao Zhang, Ding Zhao, Xianfeng Terry Yang

Full-field traffic state information (i. e., flow, speed, and density) is critical for the successful operation of Intelligent Transportation Systems (ITS) on freeways.

Constrained Variational Policy Optimization for Safe Reinforcement Learning

1 code implementation28 Jan 2022 Zuxin Liu, Zhepeng Cen, Vladislav Isenbaev, Wei Liu, Zhiwei Steven Wu, Bo Li, Ding Zhao

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.

reinforcement-learning Safe Reinforcement Learning

Optimal Transport based Data Augmentation for Heart Disease Diagnosis and Prediction

no code implementations25 Jan 2022 JieLin Qiu, Jiacheng Zhu, Michael Rosenberg, Emerson Liu, Ding Zhao

In this paper, we focus on a new method of data augmentation to solve the data imbalance problem within imbalanced ECG datasets to improve the robustness and accuracy of heart disease detection.

Data Augmentation

Joint transmit and reflective beamforming for IRS-assisted integrated sensing and communication

no code implementations26 Nov 2021 Xianxin Song, Ding Zhao, Haocheng Hua, Tony Xiao Han, Xun Yang, Jie Xu

This paper studies an intelligent reflecting surface (IRS)-assisted integrated sensing and communication (ISAC) system, in which one IRS is deployed to not only assist the wireless communication from a multi-antenna base station (BS) to a single-antenna communication user (CU), but also create virtual line-of-sight (LoS) links for sensing targets at areas with LoS links blocked.

Certifiable Deep Importance Sampling for Rare-Event Simulation of Black-Box Systems

1 code implementation3 Nov 2021 Mansur Arief, Yuanlu Bai, Wenhao Ding, Shengyi He, Zhiyuan Huang, Henry Lam, Ding Zhao

Rare-event simulation techniques, such as importance sampling (IS), constitute powerful tools to speed up challenging estimation of rare catastrophic events.

CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation

no code implementations26 Oct 2021 Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao

Generating safety-critical scenarios, which are crucial yet difficult to collect, provides an effective way to evaluate the robustness of autonomous driving systems.

Autonomous Driving Scene Generation

Accelerated Policy Evaluation: Learning Adversarial Environments with Adaptive Importance Sampling

1 code implementation19 Jun 2021 Mengdi Xu, Peide Huang, Fengpei Li, Jiacheng Zhu, Xuewei Qi, Kentaro Oguchi, Zhiyuan Huang, Henry Lam, Ding Zhao

The evaluation of rare but high-stakes events remains one of the main difficulties in obtaining reliable policies from intelligent agents, especially in large or continuous state/action spaces where limited scalability enforces the use of a prohibitively large number of testing iterations.

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

2 code implementations ICLR 2022 Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li

We then develop a local smoothing algorithm for policies derived from Q-functions to guarantee the robustness of actions taken along the trajectory; we also develop a global smoothing algorithm for certifying the lower bound of a finite-horizon cumulative reward, as well as a novel local smoothing algorithm to perform adaptive search in order to obtain tighter reward certification.

Atari Games Autonomous Vehicles +1

Semantically Adversarial Driving Scenario Generation with Explicit Knowledge Integration

no code implementations8 Jun 2021 Wenhao Ding, Haohong Lin, Bo Li, Kim Ji Eun, Ding Zhao

Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve the robustness.

Autonomous Driving Point Cloud Segmentation +1

Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving

1 code implementation CVPR 2022 Hanjiang Hu, Zuxin Liu, Sharad Chitlangia, Akhil Agnihotri, Ding Zhao

To this end, we introduce an easy-to-compute information-theoretic surrogate metric to quantitatively and fast evaluate LiDAR placement for 3D detection of different types of objects.

3D Object Detection Autonomous Driving +1

Personalized Keyphrase Detection using Speaker and Environment Information

no code implementations28 Apr 2021 Rajeev Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ding Zhao, Yiteng, Huang, Arun Narayanan, Ian McGraw

In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary.

Automatic Speech Recognition Speaker Separation +1

Functional optimal transport: map estimation and domain adaptation for functional data

1 code implementation7 Feb 2021 Jiacheng Zhu, Aritra Guha, Dat Do, Mengdi Xu, XuanLong Nguyen, Ding Zhao

We introduce a formulation of optimal transport problem for distributions on function spaces, where the stochastic map between functional domains can be partially represented in terms of an (infinite-dimensional) Hilbert-Schmidt operator mapping a Hilbert space of functions to another.

Domain Adaptation Transfer Learning

SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments

1 code implementation9 Nov 2020 Hanjiang Hu, Baoquan Yang, Zhijian Qiao, Ding Zhao, Hesheng Wang

Different environments pose a great challenge on the outdoor robust visual perception for long-term autonomous driving and the generalization of learning-based algorithms on different environmental effects is still an open problem.

Autonomous Driving Depth Estimation +3

Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method

1 code implementation15 Oct 2020 Zuxin Liu, Hongyi Zhou, Baiming Chen, Sicheng Zhong, Martial Hebert, Ding Zhao

We propose a model-based approach to enable RL agents to effectively explore the environment with unknown system dynamics and environment constraints given a significantly small number of violation budgets.

Model-based Reinforcement Learning reinforcement-learning +1

Rare-Event Simulation for Neural Network and Random Forest Predictors

no code implementations10 Oct 2020 Yuanlu Bai, Zhiyuan Huang, Henry Lam, Ding Zhao

We study rare-event simulation for a class of problems where the target hitting sets of interest are defined via modern machine learning tools such as neural networks and random forests.

Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

no code implementations16 Sep 2020 Wenhao Ding, Baiming Chen, Bo Li, Kim Ji Eun, Ding Zhao

Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance.

Decision Making

MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments

no code implementations30 Jul 2020 Zuxin Liu, Baiming Chen, Hongyi Zhou, Guru Koushik, Martial Hebert, Ding Zhao

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications.

reinforcement-learning

Deep Probabilistic Accelerated Evaluation: A Robust Certifiable Rare-Event Simulation Methodology for Black-Box Safety-Critical Systems

2 code implementations28 Jun 2020 Mansur Arief, Zhiyuan Huang, Guru Koushik Senthil Kumar, Yuanlu Bai, Shengyi He, Wenhao Ding, Henry Lam, Ding Zhao

Evaluating the reliability of intelligent physical systems against rare safety-critical events poses a huge testing burden for real-world applications.

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

1 code implementation NeurIPS 2020 Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen, Ding Zhao

We propose a transition prior to account for the temporal dependencies in streaming data and update the mixture online via sequential variational inference.

Continual Learning Decision Making +5

Robust Unsupervised Learning of Temporal Dynamic Interactions

no code implementations18 Jun 2020 Aritra Guha, Rayleigh Lei, Jiacheng Zhu, XuanLong Nguyen, Ding Zhao

These distance metrics can serve as an objective for assessing the stability of an interaction learning algorithm.

Representation Learning

Dynamic Sparsity Neural Networks for Automatic Speech Recognition

no code implementations16 May 2020 Zhaofeng Wu, Ding Zhao, Qiao Liang, Jiahui Yu, Anmol Gulati, Ruoming Pang

In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints.

Automatic Speech Recognition

Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments

1 code implementation11 May 2020 Baiming Chen, Mengdi Xu, Zuxin Liu, Liang Li, Ding Zhao

We also test the proposed algorithm in traffic scenarios that require coordination of all autonomous vehicles to show the practical value of delay-awareness.

Autonomous Vehicles Multi-agent Reinforcement Learning +1

A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency

no code implementations28 Mar 2020 Tara N. Sainath, Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Bruguier, Shuo-Yiin Chang, Wei Li, Raziel Alvarez, Zhifeng Chen, Chung-Cheng Chiu, David Garcia, Alex Gruenstein, Ke Hu, Minho Jin, Anjuli Kannan, Qiao Liang, Ian McGraw, Cal Peyser, Rohit Prabhavalkar, Golan Pundak, David Rybach, Yuan Shangguan, Yash Sheth, Trevor Strohman, Mirko Visontai, Yonghui Wu, Yu Zhang, Ding Zhao

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i. e., word error rate (WER), and latency, i. e., the time the hypothesis is finalized after the user stops speaking.

Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method

no code implementations2 Mar 2020 Wenhao Ding, Baiming Chen, Minjun Xu, Ding Zhao

We then train the generative model as an agent (or a generator) to investigate the risky distribution parameters for a given driving algorithm being evaluated.

Autonomous Driving

Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process

no code implementations17 Oct 2019 Jiacheng Zhu, Shenghao Qin, Wenshuo Wang, Ding Zhao

Constructed by incorporating NPs with recurrent neural networks (RNNs), the ARNP model predicts the distribution of a target vehicle trajectory conditioned on the observed long-term sequential data of all surrounding vehicles.

Autonomous Vehicles Meta-Learning +1

Recurrent Attentive Neural Process for Sequential Data

no code implementations17 Oct 2019 Shenghao Qin, Jiacheng Zhu, Jimmy Qin, Wenshuo Wang, Ding Zhao

Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs.

Autonomous Driving

Multi-Vehicle Interaction Scenarios Generation with Interpretable Traffic Primitives and Gaussian Process Regression

no code implementations8 Oct 2019 Weiyang Zhang, Wenshuo Wang, Ding Zhao

The experimental results demonstrate that our proposed method can generate a bunch of human-like multi-vehicle interaction trajectories that can fit different road conditions remaining the key interaction patterns of agents in the provided scenarios, which is import to the development of autonomous vehicles.

Autonomous Vehicles Decision Making +1

CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios

1 code implementation17 Sep 2019 Wenhao Ding, Mengdi Xu, Ding Zhao

However, most of the data is collected in safe scenarios leading to the duplication of trajectories which are easy to be handled by currently developed algorithms.

Autonomous Driving Trajectory Prediction

Active Learning for Risk-Sensitive Inverse Reinforcement Learning

no code implementations14 Sep 2019 Rui Chen, Wenshuo Wang, Zirui Zhao, Ding Zhao

One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution.

Active Learning reinforcement-learning

A General Framework of Learning Multi-Vehicle Interaction Patterns from Videos

no code implementations17 Jul 2019 Chengyuan Zhang, Jiacheng Zhu, Wenshuo Wang, Ding Zhao

Semantic learning and understanding of multi-vehicle interaction patterns in a cluttered driving environment are essential but challenging for autonomous vehicles to make proper decisions.

Autonomous Vehicles

Evaluation Uncertainty in Data-Driven Self-Driving Testing

no code implementations19 Apr 2019 Zhiyuan Huang, Mansur Arief, Henry Lam, Ding Zhao

These Monte Carlo samples are generated from stochastic input models constructed based on real-world data.

Autonomous Vehicles

A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters

no code implementations15 Sep 2018 Wenhao Ding, Wenshuo Wang, Ding Zhao

Generating multi-vehicle trajectories from existing limited data can provide rich resources for autonomous vehicle development and testing.

Autonomous Vehicles Disentanglement

Deep context: end-to-end contextual speech recognition

no code implementations7 Aug 2018 Golan Pundak, Tara N. Sainath, Rohit Prabhavalkar, Anjuli Kannan, Ding Zhao

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.

Automatic Speech Recognition

Understanding V2V Driving Scenarios through Traffic Primitives

no code implementations27 Jul 2018 Wenshuo Wang, Weiyang Zhang, Ding Zhao

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.

Decision Making Dynamic Time Warping

A Tempt to Unify Heterogeneous Driving Databases using Traffic Primitives

no code implementations13 May 2018 Jiacheng Zhu, Wenshuo Wang, Ding Zhao

A multitude of publicly-available driving datasets and data platforms have been raised for autonomous vehicles (AV).

Autonomous Vehicles Time Series

An Accelerated Approach to Safely and Efficiently Test Pre-Production Autonomous Vehicles on Public Streets

no code implementations5 May 2018 Mansur Arief, Peter Glynn, Ding Zhao

Various automobile and mobility companies, for instance Ford, Uber and Waymo, are currently testing their pre-produced autonomous vehicle (AV) fleets on the public roads.

Autonomous Vehicles

Cluster Naturalistic Driving Encounters Using Deep Unsupervised Learning

no code implementations28 Feb 2018 Sisi Li, Wenshuo Wang, Zhaobin Mo, Ding Zhao

Learning knowledge from driving encounters could help self-driving cars make appropriate decisions when driving in complex settings with nearby vehicles engaged.

Self-Driving Cars

Extraction of V2V Encountering Scenarios from Naturalistic Driving Database

no code implementations27 Feb 2018 Zhaobin Mo, Sisi Li, Diange Yang, Ding Zhao

To overcome this problem, we extract naturalistic V2V encounters data from the database, and then separate the primary vehicle encounter category by clustering.

Dynamic Time Warping

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

no code implementations11 Jan 2018 Wenshuo Wang, Junqiang Xi, Ding Zhao

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).

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

no code implementations1 Oct 2017 Zhiyuan Huang, Yaohui Guo, Henry Lam, Ding Zhao

The distribution used in sampling is pivotal to the performance of the method, but building a suitable distribution requires case-by-case analysis.

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

no code implementations11 Sep 2017 Wenshuo Wang, Ding Zhao

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.

Autonomous Vehicles Time Series

Driving Style Analysis Using Primitive Driving Patterns With Bayesian Nonparametric Approaches

no code implementations16 Aug 2017 Wenshuo Wang, Junqiang Xi, Ding Zhao

In order to achieve this, first, a Bayesian nonparametric learning method based on a hidden semi-Markov model (HSMM) is introduced to extract primitive driving patterns from time series driving data without prior knowledge of the number of these patterns.

Time Series

How Much Data is Enough? A Statistical Approach with Case Study on Longitudinal Driving Behavior

no code implementations23 Jun 2017 Wenshuo Wang, Chang Liu, Ding Zhao

For projects that cost millions of dollars, it is critical to determine the right amount of data needed.

Density Estimation

The Impact of Road Configuration in V2V-based Cooperative Localization: Mathematical Analysis and Real-world Evaluation

no code implementations1 May 2017 Macheng Shen, Jing Sun, Ding Zhao

It has been shown, in our previous work, that the GNSS error can be reduced from several meters to sub-meter level by matching the biased GNSS positioning to a digital map with road constraints.

Systems and Control

Optimization of Vehicle Connections in V2V-based Cooperative Localization

no code implementations26 Mar 2017 Macheng Shen, Jing Sun, Ding Zhao

Cooperative map matching (CMM) uses the Global Navigation Satellite System (GNSS) positioning of a group of vehicles to improve the standalone localization accuracy.

Systems and Control

Improving Localization Accuracy in Connected Vehicle Networks Using Rao-Blackwellized Particle Filters: Theory, Simulations, and Experiments

no code implementations19 Feb 2017 Macheng Shen, Ding Zhao, Jing Sun, Huei Peng

A Rao-Blackwellized particle filter (RBPF) is used to jointly estimate the common biases of the pseudo-ranges and the vehicle positions.

Systems and Control

A Learning-Based Approach for Lane Departure Warning Systems with a Personalized Driver Model

no code implementations4 Feb 2017 Wenshuo Wang, Ding Zhao, Junqiang Xi, Wei Han

Second, based on this model, we develop an online model-based prediction algorithm to predict the forthcoming vehicle trajectory and judge whether the driver will demonstrate an LDB or a DCB.

Cannot find the paper you are looking for? You can Submit a new open access paper.