arXiv subjects

Ming Liu

Publications and source records attributed to Ming Liu.

At least 433 records · Page 24Linked to original sources

arXiv2019

A Robust Pavement Mapping System Based on Normal-Constrained Stereo Visual Odometry

Pavement condition is crucial for civil infrastructure maintenance. This task usually requires efficient road damage localization, which can be accomplished by the visual odometry system embedded in unmanned aerial vehicles (UAVs). However, the state-of-the-art visual odometry and mapping methods suffer from large drift under the degeneration of the scene structure. To alleviate this issue, we integrate normal constraints into the visual odometry process, which greatly helps to avoid large drift. By parameterizing the normal vector on the tangential plane, the normal factors are coupled with traditional reprojection factors in the pose optimization procedure. The experimental results demonstrate the effectiveness of the proposed system. The overall absolute trajectory error is improved by approximately 20%, which indicates that the estimated trajectory is much more accurate than that obtained using other state-of-the-art methods.

cs.RO↗

arXiv2019

Autonomous UAV Landing System Based on Visual Navigation

In this paper, we present an autonomous unmanned aerial vehicle (UAV) landing system based on visual navigation. We design the landmark as a topological pattern in order to enable the UAV to distinguish the landmark from the environment easily. In addition, a dynamic thresholding method is developed for image binarization to improve detection efficiency. The relative distance in the horizontal plane is calculated according to effective image information, and the relative height is obtained using a linear interpolation method. The landing experiments are performed on a static and a moving platform, respectively. The experimental results illustrate that our proposed landing system performs robustly and accurately.

cs.RO↗

arXiv2019

Real-Time, Environmentally-Robust 3D LiDAR Localization

Localization, or position fixing, is an important problem in robotics research. In this paper, we propose a novel approach for long-term localization in a changing environment using 3D LiDAR. We first create the map of a real environment using GPS and LiDAR. Then, we divide the map into several small parts as the targets for cloud registration, which can not only improve the robustness but also reduce the registration time. PointLocalization allows us to fuse different kinds of odometers, which can optimize the accuracy and frequency of localization results. We evaluate our algorithm on an unmanned ground vehicle (UGV) using LiDAR and a wheel encoder, and obtain the localization results at more than 20 Hz after fusion. The algorithm can also localize the UGV in a 180-degree field of view (FOV). Using an outdated map captured six months ago, this algorithm shows great robustness, and the test results show that it can achieve an accuracy of 10 cm. PointLocalization has been tested for a period of more than six months in a crowded factory and has operated successfully over a distance of more than 2000 km.

cs.RO↗

arXiv2019

Low-Cost GPS-Aided LiDAR State Estimation and Map Building

Using different sensors in an autonomous vehicle (AV) can provide multiple constraints to optimize AV location estimation. In this paper, we present a low-cost GPS-assisted LiDAR state estimation system for AVs. Firstly, we utilize LiDAR to obtain highly precise 3D geometry data. Next, we use an inertial measurement unit (IMU) to correct point cloud misalignment caused by incorrect place recognition. The estimated LiDAR odometry and IMU measurement are then jointly optimized. We use a lost-cost GPS instead of a real-time kinematic (RTK) module to refine the estimated LiDAR-inertial odometry. Our low-cost GPS and LiDAR complement each other, and can provide highly accurate vehicle location information. Moreover, a low-cost GPS is much cheaper than an RTK module, which reduces the overall AV sensor cost. Our experimental results demonstrate that our proposed GPS-aided LiDAR-inertial odometry system performs very accurately. The accuracy achieved when processing a dataset collected in an industrial zone is approximately 0.14 m.

cs.RO↗

arXiv2019

Federated Transfer Reinforcement Learning for Autonomous Driving

Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles. This sequential process is extremely time-consuming and more importantly, knowledge from the fine-tuned model stays local and can not be re-used or leveraged collaboratively. To tackle this problem, we present an online federated RL transfer process for real-time knowledge extraction where all the participant agents make corresponding actions with the knowledge learned by others, even when they are acting in very different environments. To validate the effectiveness of the proposed approach, we constructed a real-life collision avoidance system with Microsoft Airsim simulator and NVIDIA JetsonTX2 car agents, which cooperatively learn from scratch to avoid collisions in indoor environment with obstacle objects. We demonstrate that with the proposed framework, the simulator car agents can transfer knowledge to the RC cars in real-time, with 27% increase in the average distance with obstacles and 42% decrease in the collision counts.

cs.LG↗

arXiv2019

Road Damage Detection Based on Unsupervised Disparity Map Segmentation

This paper presents a novel road damage detection algorithm based on unsupervised disparity map segmentation. Firstly, a disparity map is transformed by minimizing an energy function with respect to stereo rig roll angle and road disparity projection model. Instead of solving this energy minimization problem using non-linear optimization techniques, we directly find its numerical solution. The transformed disparity map is then segmented using Otus's thresholding method, and the damaged road areas can be extracted. The proposed algorithm requires no parameters when detecting road damage. The experimental results illustrate that our proposed algorithm performs both accurately and efficiently. The pixel-level road damage detection accuracy is approximately 97.56%.

cs.CV↗

arXiv2019

Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze

Safe and efficient crowd navigation for mobile robot is a crucial yet challenging task. Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies. However, their performance deteriorates when the crowd size grows. We suggest that this can be addressed by enabling the network to identify and pay attention to the humans in the crowd that are most critical to navigation. We propose a novel network utilizing a graph representation to learn the policy. We first train a graph convolutional network based on human gaze data that accurately predicts human attention to different agents in the crowd. Then we incorporate the learned attention into a graph-based reinforcement learning architecture. The proposed attention mechanism enables the assignment of meaningful weightings to the neighbors of the robot, and has the additional benefit of interpretability. Experiments on real-world dense pedestrian datasets with various crowd sizes demonstrate that our model outperforms state-of-art methods by 18.4% in task accomplishment and by 16.4% in time efficiency.

cs.RO↗

arXiv2019

Fast Symbolic 3D Registration Solution

3D registration has always been performed invoking singular value decomposition (SVD) or eigenvalue decomposition (EIG) in real engineering practices. However, these numerical algorithms suffer from uncertainty of convergence in many cases. A novel fast symbolic solution is proposed in this paper by following our recent publication in this journal. The equivalence analysis shows that our previous solver can be converted to deal with the 3D registration problem. Rather, the computation procedure is studied for further simplification of computing without complex-number support. Experimental results show that the proposed solver does not loose accuracy and robustness but improves the execution speed to a large extent by almost %50 to %80, on both personal computer and embedded processor.

cs.CV↗

arXiv2019

Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data

Humans are capable of learning a new behavior by observing others perform the skill. Robots can also implement this by imitation learning. Furthermore, if with external guidance, humans will master the new behavior more efficiently. So how can robots implement this? To address the issue, we present Federated Imitation Learning (FIL) in the paper. Firstly, a knowledge fusion algorithm deployed on the cloud for fusing knowledge from local robots is presented. Then, effective transfer learning methods in FIL are introduced. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning. FIL considers information privacy and data heterogeneity when robots share knowledge. It is suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a simplified self-driving task for robots (cars). The experimental results demonstrate that FIL is capable of increasing imitation learning of local robots in cloud robotic systems.

cs.RO↗

arXiv2019

Utilizing Eye Gaze to Enhance the Generalization of Imitation Networks to Unseen Environments

Vision-based autonomous driving through imitation learning mimics the behaviors of human drivers by training on pairs of data of raw driver-view images and actions. However, there are other cues, e.g. gaze behavior, available from human drivers that have yet to be exploited. Previous research has shown that novice human learners can benefit from observing experts' gaze patterns. We show here that deep neural networks can also benefit from this. We demonstrate different approaches to integrating gaze information into imitation networks. Our results show that the integration of gaze information improves the generalization performance of networks to unseen environments.

cs.CV↗

arXiv2019

Gaze Training by Modulated Dropout Improves Imitation Learning

Imitation learning by behavioral cloning is a prevalent method that has achieved some success in vision-based autonomous driving. The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior. Typically, a convolutional neural network learns to predict the steering commands from raw driver-view images by mimicking the behaviors of human drivers. However, there are other cues, such as gaze behavior, available from human drivers that have yet to be exploited. Previous researches have shown that novice human learners can benefit from observing experts' gaze patterns. We present here that deep neural networks can also profit from this. We propose a method, gaze-modulated dropout, for integrating this gaze information into a deep driving network implicitly rather than as an additional input. Our experimental results demonstrate that gaze-modulated dropout enhances the generalization capability of the network to unseen scenes. Prediction error in steering commands is reduced by 23.5% compared to uniform dropout. Running closed loop in the simulator, the gaze-modulated dropout net increased the average distance travelled between infractions by 58.5%. Consistent with these results, the gaze-modulated dropout net shows lower model uncertainty.

cs.CV↗

arXiv2019

A Novel General Compact Model Approach for 7nm Technology Node Circuit Optimization from Device Perspective and Beyond

This work presents a novel general compact model for 7nm technology node devices like FinFETs. As an extension of previous conventional compact model that based on some less accurate elements including one-dimensional Poisson equation for three-dimensional devices and analytical equations for short channel effects, quantum effects and other physical effects, the general compact model combining few TCAD calibrated compact models with statistical methods can eliminate the tedious physical derivations. The general compact model has the advantages of efficient extraction, high accuracy, strong scaling capability and excellent transfer capability. As a demo application, two key design knobs of FinFET and their multiple impacts on RC control ESD power clamp circuit are systematically evaluated with implementation of the newly proposed general compact model, accounting for device design, circuit performance optimization and variation control. The performance of ESD power clamp can be improved extremely. This framework is also suitable for pathfinding researches on 5nm node gate-all-around devices, like nanowire (NW) FETs, nanosheet (NSH) FETs and beyond.

cs.ET↗

arXiv2019

Key Ingredients of Self-Driving Cars

Over the past decade, many research articles have been published in the area of autonomous driving. However, most of them focus only on a specific technological area, such as visual environment perception, vehicle control, etc. Furthermore, due to fast advances in the self-driving car technology, such articles become obsolete very fast. In this paper, we give a brief but comprehensive overview on key ingredients of autonomous cars (ACs), including driving automation levels, AC sensors, AC software, open source datasets, industry leaders, AC applications and existing challenges.

cs.RO↗

arXiv2019

Movable-Object-Aware Visual SLAM via Weakly Supervised Semantic Segmentation

Moving objects can greatly jeopardize the performance of a visual simultaneous localization and mapping (vSLAM) system which relies on the static-world assumption. Motion removal have seen successful on solving this problem. Two main streams of solutions are based on either geometry constraints or deep semantic segmentation neural network. The former rely on static majority assumption, and the latter require labor-intensive pixel-wise annotations. In this paper we propose to adopt a novel weakly-supervised semantic segmentation method. The segmentation mask is obtained from a CNN pre-trained with image-level class labels only. Thus, we leverage the power of deep semantic segmentation CNNs, while avoid requiring expensive annotations for training. We integrate our motion removal approach with the ORB-SLAM2 system. Experimental results on the TUM RGB-D and the KITTI stereo datasets demonstrate our superiority over the state-of-the-art.

cs.RO↗

arXiv2019

Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective

End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the input data. Such kind of policies may bring dramatical damage when applied in the real world. In this paper, we follow the recent real-to-sim pipeline by translating the testing world image back to the training domain when using the trained policy. In the translating process, a stochastic generator is used to generate various images stylized under the training domain randomly or directionally. Based on those translated images, the trained uncertainty-aware imitation learning policy would output both the predicted action and the data uncertainty motivated by the aleatoric loss function. Through the uncertainty-aware imitation learning policy, we can easily choose the safest one with the lowest uncertainty among the generated images. Experiments in the Carla navigation benchmark show that our strategy outperforms previous methods, especially in dynamic environments.

cs.RO↗

arXiv2019

Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues

This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known defects of these cues are coarseness and incompleteness. We use super-pixel to refine them, and fuse the cues extracted from both a color image trained classifier and a gray image trained classifier to compensate for their incompleteness. The conditional random field is adapted to regulate the training process and to refine the outputs further. Besides initializing the segmentation network, the previously trained classifier is also used in the testing phase to suppress the non-existing classes. Experimental results on the PASCAL VOC 2012 dataset illustrate the effectiveness of our method.

cs.CV↗

arXiv2019

A Robust Roll Angle Estimation Algorithm Based on Gradient Descent

This paper presents a robust roll angle estimation algorithm, which is developed from our previously published work, where the roll angle was estimated from a dense disparity map by minimizing a global energy using golden section search algorithm. In this paper, to achieve greater computational efficiency, we utilize gradient descent to optimize the aforementioned global energy. The experimental results illustrate that the proposed roll angle estimation algorithm takes fewer iterations to achieve the same precision as the previous method.

cs.RO↗

arXiv2019

Strain-Based Room-Temperature Non-Volatile MoTe$_2$ Ferroelectric Phase Change Transistor

The primary mechanism of operation of almost all transistors today relies on electric-field effect in a semiconducting channel to tune its conductivity from the conducting 'on'-state to a non-conducting 'off'-state. As transistors continue to scale down to increase computational performance, physical limitations from nanoscale field-effect operation begin to cause undesirable current leakage that is detrimental to the continued advancement of computing. Using a fundamentally different mechanism of operation, we show that through nanoscale strain engineering with thin films and ferroelectrics (FEs) the transition metal dichalcogenide (TMDC) MoTe$_2$ can be reversibly switched with electric-field induced strain between the 1T'-MoTe$_2$ (semimetallic) phase to a semiconducting MoTe$_2$ phase in a field effect transistor geometry. This alternative mechanism for transistor switching sidesteps all the static and dynamic power consumption problems in conventional field-effect transistors (FETs). Using strain, we achieve large non-volatile changes in channel conductivity (G$_{on}$/G$_{off}$~10$^7$ vs. G$_{on}$/G$_{off}$~0.04 in the control device) at room temperature. Ferroelectric devices offer the potential to reach sub-ns nonvolatile strain switching at the attojoule/bit level, having immediate applications in ultra-fast low-power non-volatile logic and memory while also transforming the landscape of computational architectures since conventional power, speed, and volatility considerations for microelectronics may no longer exist.

physics.app-ph↗