arXiv subjects

Miao Li

Publications and source records attributed to Miao Li.

At least 109 records · Page 6Linked to original sources

arXiv2022

Improving Robotic Grasping Ability Through Deep Shape Generation

Data-driven approaches have become a dominant paradigm for robotic grasp planning. However, the performance of these approaches is enormously influenced by the quality of the available training data. In this paper, we propose a framework to generate object shapes to improve the grasping dataset quality, thus enhancing the grasping ability of a pre-designed learning-based grasp planning network. In this framework, the object shapes are embedded into a low-dimensional feature space using an AutoEncoder (encoder-decoder) based structure network. The rarity and graspness scores are defined for each object shape using outlier detection and grasp-quality criteria. Subsequently, new object shapes are generated in feature space that leverages the original high rarity and graspness score objects' features, which can be employed to augment the grasping dataset. Finally, the results obtained from the simulation and real-world experiments demonstrate that the grasping ability of the learning-based grasp planning network can be effectively improved with the generated object shapes.

cs.RO↗

arXiv2022

Dense Nested Attention Network for Infrared Small Target Detection

Single-frame infrared small target (SIRST) detection aims at separating small targets from clutter backgrounds. With the advances of deep learning, CNN-based methods have yielded promising results in generic object detection due to their powerful modeling capability. However, existing CNN-based methods cannot be directly applied for infrared small targets since pooling layers in their networks could lead to the loss of targets in deep layers. To handle this problem, we propose a dense nested attention network (DNANet) in this paper. Specifically, we design a dense nested interactive module (DNIM) to achieve progressive interaction among high-level and low-level features. With the repeated interaction in DNIM, infrared small targets in deep layers can be maintained. Based on DNIM, we further propose a cascaded channel and spatial attention module (CSAM) to adaptively enhance multi-level features. With our DNANet, contextual information of small targets can be well incorporated and fully exploited by repeated fusion and enhancement. Moreover, we develop an infrared small target dataset (namely, NUDT-SIRST) and propose a set of evaluation metrics to conduct comprehensive performance evaluation. Experiments on both public and our self-developed datasets demonstrate the effectiveness of our method. Compared to other state-of-the-art methods, our method achieves better performance in terms of probability of detection (Pd), false-alarm rate (Fa), and intersection of union (IoU).

cs.CV↗

arXiv2022

Photons generated by gravitional waves in the near-zone of a neutron star

When a gravitational wave or a graviton travels through an electric or magnetic background, it could convert into a photon with some probability. In this paper, a dipole magnetic field is considered as this kind of background in both the Minkowski spacetime and the curved spacetime in the near-zone of a neutron star. In the former case, we find that the graviton traveling vertically rather than parallel to the background magnetic field could be more effectively converted into an electromagnetic radiation field. In the latter case, we focus on the situation, in which the graviton travels along the radial direction near a neutron star. The radius of a neutron star is about ten kilometers, so the gravitational wave with long wavelength or low frequency may bypass neutron stars by diffraction. For high frequency gravitational wave, the conversion probability is proportional to the distance square as that in the static electric or magnetic background case. The smaller the inclination angle between the dipole field and the neutron star north pole is, the larger magnetic amplitude will be. The term that described curved spacetime will slightly enhance this kind of probability. We estimate that this value is about the order of $\sim 10^{-14}- 10^{-10}$. Therefore, it is expectable that this kind of conversion process may have a potential to open a window for observing high frequency gravitational waves.

gr-qc↗

arXiv2022

Motion Mappings for Continuous Bilateral Teleoperation

Mapping operator motions to a robot is a key problem in teleoperation. Due to differences between workspaces, such as object locations, it is particularly challenging to derive smooth motion mappings that fulfill different goals (e.g. picking objects with different poses on the two sides or passing through key points). Indeed, most state-of-the-art methods rely on mode switches, leading to a discontinuous, low-transparency experience. In this paper, we propose a unified formulation for position, orientation and velocity mappings based on the poses of objects of interest in the operator and robot workspaces. We apply it in the context of bilateral teleoperation. Two possible implementations to achieve the proposed mappings are studied: an iterative approach based on locally-weighted translations and rotations, and a neural network approach. Evaluations are conducted both in simulation and using two torque-controlled Franka Emika Panda robots. Our results show that, despite longer training times, the neural network approach provides faster mapping evaluations and lower interaction forces for the operator, which are crucial for continuous, real-time teleoperation.

cs.RO↗

arXiv2022

Robot Cooking with Stir-fry: Bimanual Non-prehensile Manipulation of Semi-fluid Objects

This letter describes an approach to achieve well-known Chinese cooking art stir-fry on a bimanual robot system. Stir-fry requires a sequence of highly dynamic coordinated movements, which is usually difficult to learn for a chef, let alone transfer to robots. In this letter, we define a canonical stir-fry movement, and then propose a decoupled framework for learning this deformable object manipulation from human demonstration. First, the dual arms of the robot are decoupled into different roles (a leader and follower) and learned with classical and neural network-based methods separately, then the bimanual task is transformed into a coordination problem. To obtain general bimanual coordination, we secondly propose a Graph and Transformer based model -- Structured-Transformer, to capture the spatio-temporal relationship between dual-arm movements. Finally, by adding visual feedback of content deformation, our framework can adjust the movements automatically to achieve the desired stir-fry effect. We verify the framework by a simulator and deploy it on a real bimanual Panda robot system. The experimental results validate our framework can realize the bimanual robot stir-fry motion and have the potential to extend to other deformable objects with bimanual coordination.

cs.RO↗

arXiv2022

A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning

In the last few years, the interest in knowledge bases has grown exponentially in both the research community and the industry due to their essential role in AI applications. Entity alignment is an important task for enriching knowledge bases. This paper provides a comprehensive tutorial-type survey on representative entity alignment techniques that use the new approach of representation learning. We present a framework for capturing the key characteristics of these techniques, propose two datasets to address the limitation of existing benchmark datasets, and conduct extensive experiments using the proposed datasets. The framework gives a clear picture of how the techniques work. The experiments yield important results about the empirical performance of the techniques and how various factors affect the performance. One important observation not stressed by previous work is that techniques making good use of attribute triples and relation predicates as features stand out as winners.

cs.AI↗

arXiv2022

Adiabatic accretion onto black holes in Einstein-Maxwell-scalar theory

We study the adiabatic accretion process of ordinary baryonic gas onto spherically symmetric black holes in Einstein-Maxwell-scalar theory, with two parameters $α$ and $β$ in the coupling term. Especially, we demonstrate the range of the transonic points in terms of the charge-to-mass ratio squared and the dimensionless coordinate radius, in two important classes of black holes as examples. Further, we find that the two coupling parameters give modifications to the mass accretion rate at different orders of the sound speed at infinity. We also present their different effects on the temperature ratios of the accreted gas.

gr-qc↗

arXiv2022

The DUVET Survey: Resolved Maps of Star Formation Driven Outflows in a Compact, Starbursting Disk Galaxy

We study star formation driven outflows in a $z\sim0.02$ starbursting disk galaxy, IRAS08339+6517, using spatially resolved measurements from the Keck Cosmic Web Imager (KCWI). We develop a new method incorporating a multi-step process to determine whether an outflow should be fit in each spaxel, and then subsequently decompose the emission line into multiple components. We detect outflows ranging in velocity, $v_{\rm out}$, from $100-600$ km s$^{-1}$ across a range of star formation rate surface densities, $Σ_{\rm SFR}$, from $\sim$0.01-10 M$_\odot$ yr$^{-1}$ kpc$^{-2}$ in resolution elements of a few hundred parsec. Outflows are detected in $\sim100\%$ of all spaxels within the half-light radius, and $\sim70\%$ within $r_{90}$, suggestive of a high covering fraction for this starbursting disk galaxy. Around $2/3$ of the total outflowing mass originates from the star forming ring, which corresponds to $<10\%$ of the total area of the galaxy. We find that the relationship between $v_{\rm out}$ and the $Σ_{\rm SFR}$, as well as between the mass loading factor, $η$, and the $Σ_{\rm SFR}$, are consistent with trends expected from energy-driven feedback models. We study the resolution effects on this relationship and find stronger correlations above a re-binned size-scale of $\sim500$ pc. Conversely, we do not find statistically significant consistency with the prediction from momentum-driven winds.

astro-ph.GA↗

arXiv2021

X-ray Spectra of Circumgalactic Medium Around Star-Forming Galaxies: Connecting Simulations to Observations

The hot component of the circum-galactic medium (CGM) around star forming galaxies is detected as diffuse X-ray emission. The X-ray spectra from the CGM depend on the temperature and metallicity of the emitting plasma, providing important information about the feeding and feedback of the galaxy. The observed spectra are commonly fitted using simple 1-Temperature (1-T) or 2-T models. However, the actual temperature distribution of the gas can be complex because of the interaction between galactic outflows and halo gas. Here we demonstrate this by analysing 3-D hydrodynamical simulations of the CGM with a realistic outflow model. We investigate the physical properties of the simulated hot CGM, which shows a broad distribution in density, temperature, and metallicity. By constructing and fitting the simulated spectra, we show that, while the 1-T and 2-T models are able to fit the synthesized spectra reasonably well, the inferred temperature(s) does not bear much physical meaning. Instead, we propose a log-normal distribution as a more physical model. The log-normal model better fits the simulated spectra while reproducing the gas temperature distribution. We also show that when the star formation rate is high, the spectra inside the bi-conical outflows are distinct from that outside, as outflows are generally hotter and more metal-enriched. Finally, we produce mock spectra for future missions with the eV-level spectral resolution, such as Athena, Lynx, HUBS and XRISM.

astro-ph.GA↗

arXiv2021

Learning Ultrasound Scanning Skills from Human Demonstrations

Recently, the robotic ultrasound system has become an emerging topic owing to the widespread use of medical ultrasound. However, it is still a challenging task to model and to transfer the ultrasound skill from an ultrasound physician. In this paper, we propose a learning-based framework to acquire ultrasound scanning skills from human demonstrations. First, the ultrasound scanning skills are encapsulated into a high-dimensional multi-modal model in terms of interactions among ultrasound images, the probe pose and the contact force. The parameters of the model are learned using the data collected from skilled sonographers' demonstrations. Second, a sampling-based strategy is proposed with the learned model to adjust the extracorporeal ultrasound scanning process to guide a newbie sonographer or a robot arm. Finally, the robustness of the proposed framework is validated with the experiments on real data from sonographers.

cs.AI↗

arXiv2021

Learning Robotic Ultrasound Scanning Skills via Human Demonstrations and Guided Explorations

Medical ultrasound has become a routine examination approach nowadays and is widely adopted for different medical applications, so it is desired to have a robotic ultrasound system to perform the ultrasound scanning autonomously. However, the ultrasound scanning skill is considerably complex, which highly depends on the experience of the ultrasound physician. In this paper, we propose a learning-based approach to learn the robotic ultrasound scanning skills from human demonstrations. First, the robotic ultrasound scanning skill is encapsulated into a high-dimensional multi-modal model, which takes the ultrasound images, the pose/position of the probe and the contact force into account. Second, we leverage the power of imitation learning to train the multi-modal model with the training data collected from the demonstrations of experienced ultrasound physicians. Finally, a post-optimization procedure with guided explorations is proposed to further improve the performance of the learned model. Robotic experiments are conducted to validate the advantages of our proposed framework and the learned models.

cs.RO↗

arXiv2021

Learning Friction Model for Magnet-actuated Tethered Capsule Robot

The potential diagnostic applications of magnet-actuated capsules have been greatly increased in recent years. For most of these potential applications, accurate position control of the capsule have been highly demanding. However, the friction between the robot and the environment as well as the drag force from the tether play a significant role during the motion control of the capsule. Moreover, these forces especially the friction force are typically hard to model beforehand. In this paper, we first designed a magnet-actuated tethered capsule robot, where the driving magnet is mounted on the end of a robotic arm. Then, we proposed a learning-based approach to model the friction force between the capsule and the environment, with the goal of increasing the control accuracy of the whole system. Finally, several real robot experiments are demonstrated to showcase the effectiveness of our proposed approach.

cs.RO↗

arXiv2021

Learning Based Adaptive Force Control of Robotic Manipulation Based on Real-Time Object Stiffness Detection

Force control is essential for medical robots when touching and contacting the patient's body. To increase the stability and efficiency in force control, an Adaption Module could be used to adjust the parameters for different contact situations. We propose an adaptive controller with an Adaption Module which can produce control parameters based on force feedback and real-time stiffness detection. We develop methods for learning the optimal policies by value iteration and using the data generated from those policies to train the Adaptive Module. We test this controller on different zones of a person's arm. All the parameters used in practice are learned from data. The experiments show that the proposed adaptive controller can exert various target forces on different zones of the arm with fast convergence and good stability.

cs.RO↗

arXiv2021

Learning Friction Model for Tethered Capsule Robot

With the potential applications of capsule robots in medical endoscopy, accurate dynamic control of the capsule robot is becoming more and more important. In the scale of a capsule robot, the friction between capsule and the environment plays an essential role in the dynamic model, which is usually difficult to model beforehand. In the paper, a tethered capsule robot system driven by a robot manipulator is built, where a strong magnetic Halbach array is mounted on the robot's end-effector to adjust the state of the capsule. To increase the control accuracy, the friction between capsule and the environment is learned with demonstrated trajectories. With the learned friction model, experimental results demonstrate an improvement of 5.6% in terms of tracking error.

cs.RO↗

arXiv2021

Learning Dynamical System for Grasping Motion

Dynamical System has been widely used for encoding trajectories from human demonstration, which has the inherent adaptability to dynamically changing environments and robustness to perturbations. In this paper we propose a framework to learn a dynamical system that couples position and orientation based on a diffeomorphism. Different from other methods, it can realise the synchronization between positon and orientation during the whole trajectory. Online grasping experiments are carried out to prove its effectiveness and online adaptability.

cs.RO↗

arXiv2021

Data Generation for Learning to Grasp in a Bin-picking Scenario

The rise of deep learning has greatly transformed the pipeline of robotic grasping from model-based approach to data-driven stream. Along this line, a large scale of grasping data either collected from simulation or from real world examples become extremely important. In this paper, we present our recent work on data generation in simulation for a bin-picking scene. 77 objects from the YCB object data sets are used to generate the dataset with PyBullet, where different environment conditions are taken into account including lighting, camera pose, sensor noise and so on. In all, 100K data samples are collected in terms of ground truth segmentation, RGB, 6D pose and point cloud. All the data examples including the source code are made available online.

cs.RO↗

arXiv2021

Unknown Object Segmentation through Domain Adaptation

The ability to segment unknown objects in cluttered scenes has a profound impact on robot grasping. The rise of deep learning has greatly transformed the pipeline of robotic grasping from model-based approach to data-driven stream, which generally requires a large scale of grasping data either collected in simulation or from real-world examples. In this paper, we proposed a sim-to-real framework to transfer the object segmentation model learned in simulation to the real-world. First, data samples are collected in simulation, including RGB, 6D pose, and point cloud. Second, we also present a GAN-based unknown object segmentation method through domain adaptation, which consists of an image translation module and an image segmentation module. The image translation module is used to shorten the reality gap and the segmentation module is responsible for the segmentation mask generation. We used the above method to perform segmentation experiments on unknown objects in a bin-picking scenario. Finally, the experimental result shows that the segmentation model learned in simulation can be used for real-world data segmentation.

cs.RO↗

arXiv2021

Domain-Specific Suppression for Adaptive Object Detection

Domain adaptation methods face performance degradation in object detection, as the complexity of tasks require more about the transferability of the model. We propose a new perspective on how CNN models gain the transferability, viewing the weights of a model as a series of motion patterns. The directions of weights, and the gradients, can be divided into domain-specific and domain-invariant parts, and the goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one. Current UDA object detection methods view the two directions as a whole while optimizing, which will cause domain-invariant direction mismatch even if the output features are perfectly aligned. In this paper, we propose the domain-specific suppression, an exemplary and generalizable constraint to the original convolution gradients in backpropagation to detach the two parts of directions and suppress the domain-specific one. We further validate our theoretical analysis and methods on several domain adaptive object detection tasks, including weather, camera configuration, and synthetic to real-world adaptation. Our experiment results show significant advance over the state-of-the-art methods in the UDA object detection field, performing a promotion of $10.2\sim12.2\%$ mAP on all these domain adaptation scenarios.

cs.CV↗