Yunhui Liu
YOU?
Author Swipe
View article: Whole-Body Control Framework for Humanoid Robots with Heavy Limbs: A Model-Based Approach
Whole-Body Control Framework for Humanoid Robots with Heavy Limbs: A Model-Based Approach Open
Humanoid robots often face significant balance issues due to the motion of their heavy limbs. These challenges are particularly pronounced when attempting dynamic motion or operating in environments with irregular terrain. To address this …
View article: Norm Augmented Graph AutoEncoders for Link Prediction
Norm Augmented Graph AutoEncoders for Link Prediction Open
Link Prediction (LP) is a crucial problem in graph-structured data. Graph Neural Networks (GNNs) have gained prominence in LP, with Graph AutoEncoders (GAEs) being a notable representation. However, our empirical findings reveal that GAEs'…
View article: GeoManip: Geometric Constraints as General Interfaces for Robot Manipulation
GeoManip: Geometric Constraints as General Interfaces for Robot Manipulation Open
We present GeoManip, a framework to enable generalist robots to leverage essential conditions derived from object and part relationships, as geometric constraints, for robot manipulation. For example, cutting the carrot requires adhering t…
View article: Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains
Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains Open
Heterogeneous Text-Attributed Graphs (HTAGs), where different types of entities are not only associated with texts but also connected by diverse relationships, have gained widespread popularity and application across various domains. Howev…
View article: A Dexterous and Compliant (DexCo) Hand Based on Soft Hydraulic Actuation for Human-Inspired Fine In-Hand Manipulation
A Dexterous and Compliant (DexCo) Hand Based on Soft Hydraulic Actuation for Human-Inspired Fine In-Hand Manipulation Open
View article: Genomic insights into Neolithic founding paternal lineages around the Qinghai-Xizang Plateau using integrated YanHuang resource
Genomic insights into Neolithic founding paternal lineages around the Qinghai-Xizang Plateau using integrated YanHuang resource Open
View article: Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference
Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference Open
Heterogeneous Graph Neural Networks (HGNNs) have achieved promising results in various heterogeneous graph learning tasks, owing to their superiority in capturing the intricate relationships and diverse relational semantics inherent in het…
View article: Online Omnidirectional Jumping Trajectory Planning for Quadrupedal Robots on Uneven Terrains
Online Omnidirectional Jumping Trajectory Planning for Quadrupedal Robots on Uneven Terrains Open
Natural terrain complexity often necessitates agile movements like jumping in animals to improve traversal efficiency. To enable similar capabilities in quadruped robots, complex real-time jumping maneuvers are required. Current research d…
View article: Design and Optimization of an Origami Gripper for Versatile Grasping and Manipulation
Design and Optimization of an Origami Gripper for Versatile Grasping and Manipulation Open
Robotic grasping and manipulation demand the ability to handle a multitude of objects with different shapes, sizes, quantities, surface smoothness, vulnerability, and stiffness, which is challenging without prior knowledge about object pro…
View article: Traversability-Aware Legged Navigation by Learning from Real-World Visual Data
Traversability-Aware Legged Navigation by Learning from Real-World Visual Data Open
The enhanced mobility brought by legged locomotion empowers quadrupedal robots to navigate through complex and unstructured environments. However, optimizing agile locomotion while accounting for the varying energy costs of traversing diff…
View article: Adapting Segment Anything Model for Unseen Object Instance Segmentation
Adapting Segment Anything Model for Unseen Object Instance Segmentation Open
Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments. Previous approaches require full supervision on large-scale tabletop datasets for effective pretraining. In this paper, we …
View article: Embodiment-Agnostic Action Planning via Object-Part Scene Flow
Embodiment-Agnostic Action Planning via Object-Part Scene Flow Open
Observing that the key for robotic action planning is to understand the target-object motion when its associated part is manipulated by the end effector, we propose to generate the 3D object-part scene flow and extract its transformations …
View article: Data‐Driven Modeling and High‐Precision Tracking Control of a Soft Continuum Manipulator: Enabling Robotic Sorting of Multiwire Cables
Data‐Driven Modeling and High‐Precision Tracking Control of a Soft Continuum Manipulator: Enabling Robotic Sorting of Multiwire Cables Open
As a new class of robots, soft continuum manipulators have attracted attention due to their flexibility and compliance. However, these characteristics create challenges for precise modeling and control. This study proposes a hybrid offline…
View article: Enhancing Vectorized Map Perception with Historical Rasterized Maps
Enhancing Vectorized Map Perception with Historical Rasterized Maps Open
In autonomous driving, there is growing interest in end-to-end online vectorized map perception in bird's-eye-view (BEV) space, with an expectation that it could replace traditional high-cost offline high-definition (HD) maps. However, the…
View article: Scale-aware monocular reconstruction via robot kinematics and visual data in neural radiance fields
Scale-aware monocular reconstruction via robot kinematics and visual data in neural radiance fields Open
Aim Scale-aware 3D reconstruction of the surgical scene from a monocular endoscope is important for automatic navigation systems in robot-assisted surgery. However, traditional multi-view stereo methods purely utilize monocular images, whi…
View article: Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling
Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling Open
Scale-aware monocular depth estimation poses a significant challenge in computer-aided endoscopic navigation. However, existing depth estimation methods that do not consider the geometric priors struggle to learn the absolute scale from tr…
View article: Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning
Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning Open
Contrastive learning is a significant paradigm in graph self-supervised learning. However, it requires negative samples to prevent model collapse and learn discriminative representations. These negative samples inevitably lead to heavy com…
View article: $E^{3}$Gen: Efficient, Expressive and Editable Avatars Generation
$E^{3}$Gen: Efficient, Expressive and Editable Avatars Generation Open
This paper aims to introduce 3D Gaussian for efficient, expressive, and editable digital avatar generation. This task faces two major challenges: (1) The unstructured nature of 3D Gaussian makes it incompatible with current generation pipe…
View article: Simultaneous Estimation of Shape and Force along Highly Deformable Surgical Manipulators Using Sparse FBG Measurement
Simultaneous Estimation of Shape and Force along Highly Deformable Surgical Manipulators Using Sparse FBG Measurement Open
Recently, fiber optic sensors such as fiber Bragg gratings (FBGs) have been widely investigated for shape reconstruction and force estimation of flexible surgical robots. However, most existing approaches need precise model parameters of F…
View article: IPAD: Industrial Process Anomaly Detection Dataset
IPAD: Industrial Process Anomaly Detection Dataset Open
Video anomaly detection (VAD) is a challenging task aiming to recognize anomalies in video frames, and existing large-scale VAD researches primarily focus on road traffic and human activity scenes. In industrial scenes, there are often a v…
View article: Evolutionary history and biological adaptation of Han Chinese people on the Mongolian Plateau
Evolutionary history and biological adaptation of Han Chinese people on the Mongolian Plateau Open
Complex demographic processes and natural selection pressures are critical to resolving patterns of the molecular genetic basis of adaptative traits or complex diseases. Recent ancient genome data allow us to trace how key traits evolved i…
View article: Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization
Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization Open
Clothes-changing person re-identification (CC-ReID) aims to retrieve images of the same person wearing different outfits. Mainstream researches focus on designing advanced model structures and strategies to capture identity information ind…
View article: DBPF: A Framework for Efficient and Robust Dynamic Bin-Picking
DBPF: A Framework for Efficient and Robust Dynamic Bin-Picking Open
Efficiency and reliability are critical in robotic bin-picking as they\ndirectly impact the productivity of automated industrial processes. However,\ntraditional approaches, demanding static objects and fixed collisions, lead to\ndeploymen…
View article: Efficient and Robust Point Cloud Registration via Heuristics-guided Parameter Search
Efficient and Robust Point Cloud Registration via Heuristics-guided Parameter Search Open
Estimating the rigid transformation with 6 degrees of freedom based on a putative 3D correspondence set is a crucial procedure in point cloud registration. Existing correspondence identification methods usually lead to large outlier ratios…
View article: Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking Learning
Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking Learning Open
The development of robotic systems for palletization in logistics scenarios is of paramount importance, addressing critical efficiency and precision demands in supply chain management. This paper investigates the application of Reinforceme…
View article: Neural Markov Random Field for Stereo Matching
Neural Markov Random Field for Stereo Matching Open
Stereo matching is a core task for many computer vision and robotics applications. Despite their dominance in traditional stereo methods, the hand-crafted Markov Random Field (MRF) models lack sufficient modeling accuracy compared to end-t…
View article: Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adaptive-Template Matching
Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adaptive-Template Matching Open
Soft tissue tracking is crucial for computer-assisted interventions. Existing approaches mainly rely on extracting discriminative features from the template and videos to recover corresponding matches. However, it is difficult to adopt the…
View article: Antagonistic Pump With Multiple Pumping Modes for On-Demand Soft Robot Actuation and Control
Antagonistic Pump With Multiple Pumping Modes for On-Demand Soft Robot Actuation and Control Open
Pneumatic soft robots are prized for their flexibility in achieving adaptable deformations and compliance adjustments. However, the conventional pumps used in these systems often rely on simplistic, sensorless, and on–off control mechanism…
View article: Inter-X: Towards Versatile Human-Human Interaction Analysis
Inter-X: Towards Versatile Human-Human Interaction Analysis Open
The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine-grained t…
View article: Projecting future carbon emissions from cement production in developing countries
Projecting future carbon emissions from cement production in developing countries Open