Search Results for author:
Found 58 papers, 17 papers with code
On the Robustness of Safe Reinforcement Learning under Observational Perturbations
Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints.
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition (ASR) model, which unifies models for different deployment scenarios.
MHMS: Multimodal Hierarchical Multimedia Summarization
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
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.
PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression
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.
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
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.
Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training
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.
A Hybrid Physics Machine Learning Approach for Macroscopic Traffic State Estimation
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
Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.
Optimal Transport based Data Augmentation for Heart Disease Diagnosis and Prediction
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.
Joint transmit and reflective beamforming for IRS-assisted integrated sensing and communication
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
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
Generating safety-critical scenarios, which are crucial yet difficult to collect, provides an effective way to evaluate the robustness of autonomous driving systems.
Accelerated Policy Evaluation: Learning Adversarial Environments with Adaptive Importance Sampling
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
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.
Semantically Adversarial Driving Scenario Generation with Explicit Knowledge Integration
Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve the robustness.
Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving
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.
Personalized Keyphrase Detection using Speaker and Environment Information
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.
Functional optimal transport: map estimation and domain adaptation for functional data
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.
Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
The algorithm is evaluated in realistic safety-critical environments with non-stationary disturbances.
SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments
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.
Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method
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
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
Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance.
MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments
Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications.
Deep Probabilistic Accelerated Evaluation: A Robust Certifiable Rare-Event Simulation Methodology for Black-Box Safety-Critical Systems
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
We propose a transition prior to account for the temporal dependencies in streaming data and update the mixture online via sequential variational inference.
Robust Unsupervised Learning of Temporal Dynamic Interactions
These distance metrics can serve as an objective for assessing the stability of an interaction learning algorithm.
Dynamic Sparsity Neural Networks for Automatic Speech Recognition
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.
Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments
We also test the proposed algorithm in traffic scenarios that require coordination of all autonomous vehicles to show the practical value of delay-awareness.
Delay-Aware Model-Based Reinforcement Learning for Continuous Control
Action delays degrade the performance of reinforcement learning in many real-world systems.
A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
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
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.
Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process
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.
Recurrent Attentive Neural Process for Sequential Data
Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs.
Multi-Vehicle Interaction Scenarios Generation with Interpretable Traffic Primitives and Gaussian Process Regression
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.
CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios
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.
Active Learning for Risk-Sensitive Inverse Reinforcement Learning
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.
A General Framework of Learning Multi-Vehicle Interaction Patterns from Videos
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.
Modeling Multi-Vehicle Interaction Scenarios Using Gaussian Random Field
We then use this model to reproduce the high-dimensional driving scenarios in a finitely tractable form.
Evaluation Uncertainty in Data-Driven Self-Driving Testing
These Monte Carlo samples are generated from stochastic input models constructed based on real-world data.
Streaming End-to-end Speech Recognition For Mobile Devices
End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition.
A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters
Generating multi-vehicle trajectories from existing limited data can provide rich resources for autonomous vehicle development and testing.
Deep context: end-to-end contextual speech recognition
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.
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.
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).
An Accelerated Approach to Safely and Efficiently Test Pre-Production Autonomous Vehicles on Public Streets
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.
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.
Extraction of V2V Encountering Scenarios from Naturalistic Driving Database
To overcome this problem, we extract naturalistic V2V encounters data from the database, and then separate the primary vehicle encounter category by clustering.
Learning and Inferring a Driver's Braking Action in Car-Following Scenarios
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
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
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.
Driving Style Analysis Using Primitive Driving Patterns With Bayesian Nonparametric Approaches
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.
How Much Data is Enough? A Statistical Approach with Case Study on Longitudinal Driving Behavior
For projects that cost millions of dollars, it is critical to determine the right amount of data needed.
The Impact of Road Configuration in V2V-based Cooperative Localization: Mathematical Analysis and Real-world Evaluation
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
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
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
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.
