arXiv subjects

Qi Sun

Publications and source records attributed to Qi Sun.

At least 163 records · Page 9Linked to original sources

arXiv2022

Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview

Object pose detection and tracking has recently attracted increasing attention due to its wide applications in many areas, such as autonomous driving, robotics, and augmented reality. Among methods for object pose detection and tracking, deep learning is the most promising one that has shown better performance than others. However, survey study about the latest development of deep learning-based methods is lacking. Therefore, this study presents a comprehensive review of recent progress in object pose detection and tracking that belongs to the deep learning technical route. To achieve a more thorough introduction, the scope of this study is limited to methods taking monocular RGB/RGBD data as input and covering three kinds of major tasks: instance-level monocular object pose detection, category-level monocular object pose detection, and monocular object pose tracking. In our work, metrics, datasets, and methods of both detection and tracking are presented in detail. Comparative results of current state-of-the-art methods on several publicly available datasets are also presented, together with insightful observations and inspiring future research directions.

cs.CV↗

arXiv2022

Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints

This paper presents a constrained adaptive dynamic programming (CADP) algorithm to solve general nonlinear nonaffine optimal control problems with known dynamics. Unlike previous ADP algorithms, it can directly deal with problems with state constraints. Firstly, a constrained generalized policy iteration (CGPI) framework is developed to handle state constraints by transforming the traditional policy improvement process into a constrained policy optimization problem. Next, we propose an actor-critic variant of CGPI, called CADP, in which both policy and value functions are approximated by multi-layer neural networks to directly map the system states to control inputs and value function, respectively. CADP linearizes the constrained optimization problem locally into a quadratically constrained linear programming problem, and then obtains the optimal update of the policy network by solving its dual problem. A trust region constraint is added to prevent excessive policy update, thus ensuring linearization accuracy. We determine the feasibility of the policy optimization problem by calculating the minimum trust region boundary and update the policy using two recovery rules when infeasible. The vehicle control problem in the path-tracking task is used to demonstrate the effectiveness of this proposed method.

eess.SY↗

arXiv2022

Instant Reality: Gaze-Contingent Perceptual Optimization for 3D Virtual Reality Streaming

Media streaming has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed sequentially, 3D applications such as gaming require streaming 3D assets to facilitate client-side interactions such as object manipulation and viewpoint movement. Compared to audio and video streaming, 3D streaming often requires larger data sizes and yet lower latency to ensure sufficient rendering quality, resolution, and latency for perceptual comfort. Thus, streaming 3D assets can be even more challenging than streaming audios/videos, and existing solutions often suffer from long loading time or limited quality. To address this critical and timely issue, we propose a perceptually-optimized progressive 3D streaming method for spatial quality and temporal consistency in immersive interactions. Based on the human visual mechanisms in the frequency domain, our model selects and schedules the streaming dataset for optimal spatial-temporal quality. We also train a neural network for our model to accelerate this decision process for real-time client-server applications. We evaluate our method via subjective studies and objective analysis under varying network conditions (from 3G to 5G) and client devices (HMD and traditional displays), and demonstrate better visual quality and temporal consistency than alternative solutions.

cs.HC↗

arXiv2021

Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks

Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradient to update model parameters, which becomes time-consuming as the network goes deeper. To break the algorithmic locking and exploit synchronous module parallelism in both the forward and backward modes, auxiliary-variable methods have attracted much interest lately but suffer from significant communication overhead and lack of data augmentation. In this work, a novel joint learning framework for training realistic ResNets across multiple compute devices is established by trading off the storage and recomputation of external auxiliary variables. More specifically, the input data of each independent processor is generated from its low-capacity auxiliary network (AuxNet), which permits the use of data augmentation and realizes forward unlocking. The backward passes are then executed in parallel, each with a local loss function that originates from the penalty or augmented Lagrangian (AL) methods. Finally, the proposed AuxNet is employed to reproduce the updated auxiliary variables through an end-to-end training process. We demonstrate the effectiveness of our methods on ResNets and WideResNets across CIFAR-10, CIFAR-100, and ImageNet datasets, achieving speedup over the traditional layer-serial training method while maintaining comparable testing accuracy.

cs.LG↗

arXiv2021

Gaze-Contingent Retinal Speckle Suppression for Perceptually-Matched Foveated Holographic Displays

Computer-generated holographic (CGH) displays show great potential and are emerging as the next-generation displays for augmented and virtual reality, and automotive heads-up displays. One of the critical problems harming the wide adoption of such displays is the presence of speckle noise inherent to holography, that compromises its quality by introducing perceptible artifacts. Although speckle noise suppression has been an active research area, the previous works have not considered the perceptual characteristics of the Human Visual System (HVS), which receives the final displayed imagery. However, it is well studied that the sensitivity of the HVS is not uniform across the visual field, which has led to gaze-contingent rendering schemes for maximizing the perceptual quality in various computer-generated imagery. Inspired by this, we present the first method that reduces the "perceived speckle noise" by integrating foveal and peripheral vision characteristics of the HVS, along with the retinal point spread function, into the phase hologram computation. Specifically, we introduce the anatomical and statistical retinal receptor distribution into our computational hologram optimization, which places a higher priority on reducing the perceived foveal speckle noise while being adaptable to any individual's optical aberration on the retina. Our method demonstrates superior perceptual quality on our emulated holographic display. Our evaluations with objective measurements and subjective studies demonstrate a significant reduction of the human perceived noise.

cs.HC↗

arXiv2021

A finite element method for two-phase flow with material viscous interface

This paper studies a model of two-phase flow with an immersed material viscous interface and a finite element method for numerical solution of the resulting system of PDEs. The interaction between the bulk and surface media is characterized by no-penetration and slip with friction interface conditions. The system is shown to be dissipative and a model stationary problem is proved to be well-posed. The finite element method applied in this paper belongs to a family of unfitted discretizations. The performance of the method when model and discretization parameters vary is assessed. Moreover, an iterative procedure based on the splitting of the system into bulk and surface problems is introduced and studied numerically.

math.NA↗

arXiv2021

Direct and indirect reinforcement learning

Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. In this paper, we classify RL into direct and indirect RL according to how they seek the optimal policy of the Markov decision process problem. The former solves the optimal policy by directly maximizing an objective function using gradient descent methods, in which the objective function is usually the expectation of accumulative future rewards. The latter indirectly finds the optimal policy by solving the Bellman equation, which is the sufficient and necessary condition from Bellman's principle of optimality. We study policy gradient forms of direct and indirect RL and show that both of them can derive the actor-critic architecture and can be unified into a policy gradient with the approximate value function and the stationary state distribution, revealing the equivalence of direct and indirect RL. We employ a Gridworld task to verify the influence of different forms of policy gradient, suggesting their differences and relationships experimentally. Finally, we classify current mainstream RL algorithms using the direct and indirect taxonomy, together with other ones including value-based and policy-based, model-based and model-free.

cs.LG↗

arXiv2021

Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence

Decision and control are core functionalities of high-level automated vehicles. Current mainstream methods, such as functionality decomposition and end-to-end reinforcement learning (RL), either suffer high time complexity or poor interpretability and adaptability on real-world autonomous driving tasks. In this paper, we present an interpretable and computationally efficient framework called integrated decision and control (IDC) for automated vehicles, which decomposes the driving task into static path planning and dynamic optimal tracking that are structured hierarchically. First, the static path planning generates several candidate paths only considering static traffic elements. Then, the dynamic optimal tracking is designed to track the optimal path while considering the dynamic obstacles. To that end, we formulate a constrained optimal control problem (OCP) for each candidate path, optimize them separately and follow the one with the best tracking performance. To unload the heavy online computation, we propose a model-based reinforcement learning (RL) algorithm that can be served as an approximate constrained OCP solver. Specifically, the OCPs for all paths are considered together to construct a single complete RL problem and then solved offline in the form of value and policy networks, for real-time online path selecting and tracking respectively. We verify our framework in both simulations and the real world. Results show that compared with baseline methods IDC has an order of magnitude higher online computing efficiency, as well as better driving performance including traffic efficiency and safety. In addition, it yields great interpretability and adaptability among different driving tasks. The effectiveness of the proposed method is also demonstrated in real road tests with complicated traffic conditions.

cs.LG↗

arXiv2021

Learning to Reconstruct 3D Manhattan Wireframes from a Single Image

In this paper, we propose a method to obtain a compact and accurate 3D wireframe representation from a single image by effectively exploiting global structural regularities. Our method trains a convolutional neural network to simultaneously detect salient junctions and straight lines, as well as predict their 3D depth and vanishing points. Compared with the state-of-the-art learning-based wireframe detection methods, our network is simpler and more unified, leading to better 2D wireframe detection. With global structural priors from parallelism, our method further reconstructs a full 3D wireframe model, a compact vector representation suitable for a variety of high-level vision tasks such as AR and CAD. We conduct extensive evaluations on a large synthetic dataset of urban scenes as well as real images. Our code and datasets have been made public at https://github.com/zhou13/shapeunity.

cs.CV↗

arXiv2021

Centralized Cooperation for Connected and Automated Vehicles at Intersections by Proximal Policy Optimization

Connected vehicles will change the modes of future transportation management and organization, especially at an intersection without traffic light. Centralized coordination methods globally coordinate vehicles approaching the intersection from all sections by considering their states altogether. However, they need substantial computation resources since they own a centralized controller to optimize the trajectories for all approaching vehicles in real-time. In this paper, we propose a centralized coordination scheme of automated vehicles at an intersection without traffic signals using reinforcement learning (RL) to address low computation efficiency suffered by current centralized coordination methods. We first propose an RL training algorithm, model accelerated proximal policy optimization (MA-PPO), which incorporates a prior model into proximal policy optimization (PPO) algorithm to accelerate the learning process in terms of sample efficiency. Then we present the design of state, action and reward to formulate centralized coordination as an RL problem. Finally, we train a coordinate policy in a simulation setting and compare computing time and traffic efficiency with a coordination scheme based on model predictive control (MPC) method. Results show that our method spends only 1/400 of the computing time of MPC and increase the efficiency of the intersection by 4.5 times.

cs.RO↗

arXiv2021

Decision-Making under On-Ramp merge Scenarios by Distributional Soft Actor-Critic Algorithm

Merging into the highway from the on-ramp is an essential scenario for automated driving. The decision-making under the scenario needs to balance the safety and efficiency performance to optimize a long-term objective, which is challenging due to the dynamic, stochastic, and adversarial characteristics. The Rule-based methods often lead to conservative driving on this task while the learning-based methods have difficulties meeting the safety requirements. In this paper, we propose an RL-based end-to-end decision-making method under a framework of offline training and online correction, called the Shielded Distributional Soft Actor-critic (SDSAC). The SDSAC adopts the policy evaluation with safety consideration and a safety shield parameterized with the barrier function in its offline training and online correction, respectively. These two measures support each other for better safety while not damaging the efficiency performance severely. We verify the SDSAC on an on-ramp merge scenario in simulation. The results show that the SDSAC has the best safety performance compared to baseline algorithms and achieves efficient driving simultaneously.

cs.RO↗

arXiv2021

Recurrent Model Predictive Control

This paper proposes an off-line algorithm, called Recurrent Model Predictive Control (RMPC), to solve general nonlinear finite-horizon optimal control problems. Unlike traditional Model Predictive Control (MPC) algorithms, it can make full use of the current computing resources and adaptively select the longest model prediction horizon. Our algorithm employs a recurrent function to approximate the optimal policy, which maps the system states and reference values directly to the control inputs. The number of prediction steps is equal to the number of recurrent cycles of the learned policy function. With an arbitrary initial policy function, the proposed RMPC algorithm can converge to the optimal policy by directly minimizing the designed loss function. We further prove the convergence and optimality of the RMPC algorithm thorough Bellman optimality principle, and demonstrate its generality and efficiency using two numerical examples.

eess.SY↗

arXiv2021

A Practical Layer-Parallel Training Algorithm for Residual Networks

Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which are time-consuming for deep ResNets. To break the dependencies between modules in both the forward and backward modes, auxiliary-variable methods such as the penalty and augmented Lagrangian (AL) approaches have attracted much interest lately due to their ability to exploit layer-wise parallelism. However, we observe that large communication overhead and lacking data augmentation are two key challenges of these methods, which may lead to low speedup ratio and accuracy drop across multiple compute devices. Inspired by the optimal control formulation of ResNets, we propose a novel serial-parallel hybrid training strategy to enable the use of data augmentation, together with downsampling filters to reduce the communication cost. The proposed strategy first trains the network parameters by solving a succession of independent sub-problems in parallel and then corrects the network parameters through a full serial forward-backward propagation of data. Such a strategy can be applied to most of the existing layer-parallel training methods using auxiliary variables. As an example, we validate the proposed strategy using penalty and AL methods on ResNet and WideResNet across MNIST, CIFAR-10 and CIFAR-100 datasets, achieving significant speedup over the traditional layer-serial training methods while maintaining comparable accuracy.

cs.LG↗

arXiv2021

Steadily Learn to Drive with Virtual Memory

Reinforcement learning has shown great potential in developing high-level autonomous driving. However, for high-dimensional tasks, current RL methods suffer from low data efficiency and oscillation in the training process. This paper proposes an algorithm called Learn to drive with Virtual Memory (LVM) to overcome these problems. LVM compresses the high-dimensional information into compact latent states and learns a latent dynamic model to summarize the agent's experience. Various imagined latent trajectories are generated as virtual memory by the latent dynamic model. The policy is learned by propagating gradient through the learned latent model with the imagined latent trajectories and thus leads to high data efficiency. Furthermore, a double critic structure is designed to reduce the oscillation during the training process. The effectiveness of LVM is demonstrated by an image-input autonomous driving task, in which LVM outperforms the existing method in terms of data efficiency, learning stability, and control performance.

cs.LG↗

arXiv2021

An unfitted finite element method for two-phase Stokes problems with slip between phases

We present an isoparametric unfitted finite element approach of the CutFEM or Nitsche-XFEM family for the simulation of two-phase Stokes problems with slip between phases. For the unfitted generalized Taylor--Hood finite element pair $\mathbf{P}_{k+1}-P_k$, $k\ge1$, we show an inf-sup stability property with a stability constant that is independent of the viscosity ratio, slip coefficient, position of the interface with respect to the background mesh and, of course, mesh size. In addition, we prove stability and optimal error estimates that follow from this inf-sup property. We provide numerical results in two and three dimensions to corroborate the theoretical findings and demonstrate the robustness of our approach with respect to the contrast in viscosity, slip coefficient value, and position of the interface relative to the fixed computational mesh.

math.NA↗

arXiv2020

Numerically Stable Dynamic Bicycle Model for Discrete-time Control

Dynamic/kinematic model is of great significance in decision and control of intelligent vehicles. However, due to the singularity of dynamic models at low speed, kinematic models have been the only choice under many driving scenarios. This paper presents a discrete dynamic bicycle model feasible at any low speed utilizing the concept of backward Euler method. We further give a sufficient condition, based on which the numerical stability is proved. Simulation verifies that (1) the proposed model is numerically stable while the forward-Euler discretized dynamic model diverges; (2) the model reduces forecast error by up to 49% compared to the kinematic model. As far as we know, it is the first time that a dynamic bicycle model is qualified for urban driving scenarios involving stop-and-go tasks.

eess.SY↗

arXiv2020

DialogueTRM: Exploring the Intra- and Inter-Modal Emotional Behaviors in the Conversation

Emotion Recognition in Conversations (ERC) is essential for building empathetic human-machine systems. Existing studies on ERC primarily focus on summarizing the context information in a conversation, however, ignoring the differentiated emotional behaviors within and across different modalities. Designing appropriate strategies that fit the differentiated multi-modal emotional behaviors can produce more accurate emotional predictions. Thus, we propose the DialogueTransformer to explore the differentiated emotional behaviors from the intra- and inter-modal perspectives. For intra-modal, we construct a novel Hierarchical Transformer that can easily switch between sequential and feed-forward structures according to the differentiated context preference within each modality. For inter-modal, we constitute a novel Multi-Grained Interactive Fusion that applies both neuron- and vector-grained feature interactions to learn the differentiated contributions across all modalities. Experimental results show that DialogueTRM outperforms the state-of-the-art by a significant margin on three benchmark datasets.

cs.CL↗

arXiv2020

Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic

Reinforcement learning (RL) has achieved remarkable performance in numerous sequential decision making and control tasks. However, a common problem is that learned nearly optimal policy always overfits to the training environment and may not be extended to situations never encountered during training. For practical applications, the randomness of environment usually leads to some devastating events, which should be the focus of safety-critical systems such as autonomous driving. In this paper, we introduce the minimax formulation and distributional framework to improve the generalization ability of RL algorithms and develop the Minimax Distributional Soft Actor-Critic (Minimax DSAC) algorithm. Minimax formulation aims to seek optimal policy considering the most severe variations from environment, in which the protagonist policy maximizes action-value function while the adversary policy tries to minimize it. Distributional framework aims to learn a state-action return distribution, from which we can model the risk of different returns explicitly, thereby formulating a risk-averse protagonist policy and a risk-seeking adversarial policy. We implement our method on the decision-making tasks of autonomous vehicles at intersections and test the trained policy in distinct environments. Results demonstrate that our method can greatly improve the generalization ability of the protagonist agent to different environmental variations.

cs.LG↗