Yongxiang Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Yongxiang Wu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Shuguo Wang
State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China
2 shared publications- Baodeng Hou
State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, China
1 shared publication - Fuhai Zhang
The State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China
1 shared publication - Gaoxu Wang
National Key Laboratory of Water Disaster Prevention, Nanjing Hydraulic Research Institute, Nanjing, China
1 shared publication - Guodong Liu
State Key Laboratory of Hydraulics and Mountain River Engineering, Sichuan University, Chengdu, China
1 shared publication - Jialei Li
State Key Laboratory of Urban and Regional Ecology, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing, 100085, China
1 shared publication
Latest Publications
- 1 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (3) , 2683-2693
Information-Theoretic Exploration for Adaptive Robotic Grasping in Clutter Based on Real-Time Pixel-Level Grasp Detection
Robust robotic grasping in clutter still remains a challenging problem despite its great practical value. This article presents an information-theoretic exploration approach that aims to improve the grasp estimation quality in a complex environment. First, a lightweight grasp detector that is composed of inverted residual blocks and a pyramid pooling module is proposed to make more accurate pixelwise predictions in real time, which are then projected to the workspace. To measure the uncertainty of estimations in the workspace, a two-dimensional grasp entropy (2D-GE) is defined, and the Gaussian process is applied to regress the variation of the information gain that is approximated by 2D-GEs. Finally, guided by the information gain, depth cost, and distance cost, our approach is able to actively collect and fuse estimations from multiple informative viewpoints through the exploration that finally converges to a refined best grasp, resulting improved grasping performance with a higher success rate and environmental adaptability in clutter. Simulation and robotic experiment are both performed to demonstrate the effectiveness of our method and compare it to baselines.
- 1 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (3) , 2683-2693
Information-Theoretic Exploration for Adaptive Robotic Grasping in Clutter Based on Real-Time Pixel-Level Grasp Detection
Robust robotic grasping in clutter still remains a challenging problem despite its great practical value. This article presents an information-theoretic exploration approach that aims to improve the grasp estimation quality in a complex environment. First, a lightweight grasp detector that is composed of inverted residual blocks and a pyramid pooling module is proposed to make more accurate pixelwise predictions in real time, which are then projected to the workspace. To measure the uncertainty of estimations in the workspace, a two-dimensional grasp entropy (2D-GE) is defined, and the Gaussian process is applied to regress the variation of the information gain that is approximated by 2D-GEs. Finally, guided by the information gain, depth cost, and distance cost, our approach is able to actively collect and fuse estimations from multiple informative viewpoints through the exploration that finally converges to a refined best grasp, resulting improved grasping performance with a higher success rate and environmental adaptability in clutter. Simulation and robotic experiment are both performed to demonstrate the effectiveness of our method and compare it to baselines.
- 21 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 69 (12) , 13171-13181
Real-Time Robotic Multigrasp Detection Using Anchor-Free Fully Convolutional Grasp Detector
Robotic grasping is essential for intelligent manufacturing. This article presents a novel anchor-free grasp detector based on fully convolutional network for detecting multiple valid grasps from RGB-D images in real time. Grasp detection is formulated as a closest horizontal or vertical rectangle regression task and a grasp angle classification task. By directing predicting grasps at feature points, our method eliminates the predefined anchors that commonly used in prior methods, and thus anchor-related hyperparameters and complex computations are avoided. For suppressing ambiguous and low-quality training samples, a new sample assignment strategy that combines center-sampling and regression weights is proposed. Our method achieves a state-of-the-art accuracy of 99.4% on Cornell and 96.2% on Jacquard dataset, and real-time speed of 104 frames per second, with approximately 2× fewer parameters and 8× less training time compared to previous one-stage detector. Moreover, an efficient multiscale feature fusion module is integrated to improve the performance of multigrasp detection by 25%. In real-world robotic grasping of novel objects, our method achieves a grasp success rate of 91.3% for single object and 83.3% for multiple objects with only 26 ms used for the whole planning. The results demonstrate that our method is robust for potential industrial applications.
- 21 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 69 (12) , 13171-13181
Real-Time Robotic Multigrasp Detection Using Anchor-Free Fully Convolutional Grasp Detector
Robotic grasping is essential for intelligent manufacturing. This article presents a novel anchor-free grasp detector based on fully convolutional network for detecting multiple valid grasps from RGB-D images in real time. Grasp detection is formulated as a closest horizontal or vertical rectangle regression task and a grasp angle classification task. By directing predicting grasps at feature points, our method eliminates the predefined anchors that commonly used in prior methods, and thus anchor-related hyperparameters and complex computations are avoided. For suppressing ambiguous and low-quality training samples, a new sample assignment strategy that combines center-sampling and regression weights is proposed. Our method achieves a state-of-the-art accuracy of 99.4% on Cornell and 96.2% on Jacquard dataset, and real-time speed of 104 frames per second, with approximately 2× fewer parameters and 8× less training time compared to previous one-stage detector. Moreover, an efficient multiscale feature fusion module is integrated to improve the performance of multigrasp detection by 25%. In real-world robotic grasping of novel objects, our method achieves a grasp success rate of 91.3% for single object and 83.3% for multiple objects with only 26 ms used for the whole planning. The results demonstrate that our method is robust for potential industrial applications.
- 9 August 2021
- Published by Cambridge University Press (CUP) in Robotica
- Vol. 40 (4) , 1125-1150
Global motion planning and redundancy resolution for large objects manipulation by dual redundant robots with closed kinematics
The multi-arm robotic systems consisting of redundant robots are able to conduct more complex and coordinated tasks, such as manipulating large or heavy objects. The challenges of the motion planning and control for such systems mainly arise from the closed-chain constraint and redundancy resolution problem. The closed-chain constraint reduces the configuration space to lower-dimensional subsets, making it difficult for sampling feasible configurations and planning path connecting them. A global motion planner is proposed in this paper for the closed-chain systems, and motions in different disconnected manifolds are efficiently bridged by two type regrasping moves. The regrasping moves are automatically chosen by the planner based on cost-saving principle, which greatly improve the success rate and efficiency. Furthermore, to obtain the optional inverse kinematic solutions satisfying joint physical limits (e.g., joint position, velocity, acceleration limits) in the planning, the redundancy resolution problem for dual redundant robots is converted into a unified quadratic programming problem based on the combination of two diff erent-level optimizing criteria, i.e. the minimization velocity norm (MVN) and infinity norm torque-minimization (INTM). The Dual-MVN-INTM scheme guarantees smooth velocity, acceleration profiles, and zero final velocity at the end of motion. Finally, the planning results of three complex closed-chain manipulation task using two Franka Emika Panda robots and two Kinova Jaco2 robots in both simulation and experiment demonstrate the effectiveness and efficiency of the proposed method.
- 9 August 2021
- Published by Cambridge University Press (CUP) in Robotica
- Vol. 40 (4) , 1125-1150
Global motion planning and redundancy resolution for large objects manipulation by dual redundant robots with closed kinematics
The multi-arm robotic systems consisting of redundant robots are able to conduct more complex and coordinated tasks, such as manipulating large or heavy objects. The challenges of the motion planning and control for such systems mainly arise from the closed-chain constraint and redundancy resolution problem. The closed-chain constraint reduces the configuration space to lower-dimensional subsets, making it difficult for sampling feasible configurations and planning path connecting them. A global motion planner is proposed in this paper for the closed-chain systems, and motions in different disconnected manifolds are efficiently bridged by two type regrasping moves. The regrasping moves are automatically chosen by the planner based on cost-saving principle, which greatly improve the success rate and efficiency. Furthermore, to obtain the optional inverse kinematic solutions satisfying joint physical limits (e.g., joint position, velocity, acceleration limits) in the planning, the redundancy resolution problem for dual redundant robots is converted into a unified quadratic programming problem based on the combination of two diff erent-level optimizing criteria, i.e. the minimization velocity norm (MVN) and infinity norm torque-minimization (INTM). The Dual-MVN-INTM scheme guarantees smooth velocity, acceleration profiles, and zero final velocity at the end of motion. Finally, the planning results of three complex closed-chain manipulation task using two Franka Emika Panda robots and two Kinova Jaco2 robots in both simulation and experiment demonstrate the effectiveness and efficiency of the proposed method.
- Open Access
- 15 June 2021
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 8 (6)
A Nationwide Analysis of Water Scarcity and Cloud Seeding Demand Levels From Analyzing Water Utilization Data, Agricultural Drought Maps, and Local Conditions in China Mainland
China has lots of funds, materials, and human resources in cloud seeding operations to help with water shortage problems across the country. But there is little guide about when and where the operations would obtain better benefits. To fill this gap, the modified Water Utilization Level (WUL) map of China mainland was plotted with the acquirable water utilization data on sub‐watershed scales in this study. Then the agricultural drought levels map of different counties were integrated with the modified WUL Map under preset rules to generate an integrated water scarcity map. Lastly, the cloud seeding demand maps of different seasons were drawn by integrating the agricultural drought seasons map of different counties with the integrated water scarcity map and the modified WUL map. Results showed that the middle north of China should have the highest priorities for cloud seeding operations during spring and summer, and some regions at the south during winter and spring, a few scattered regions at the northwest during spring and summer and a few regions at the middle of southeast China during summer and autumn should also have high priorities of cloud seeding operations. This research can help rain enhancement operations to obtain better effects on easing water scarcity problems and deepen the cooperation of water resources department and weather modification department in China. The designed intersecting rules of different maps in this paper also might inspire other relevant researches.
- 15 June 2021
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 8 (6)
Open AccessA Nationwide Analysis of Water Scarcity and Cloud Seeding Demand Levels From Analyzing Water Utilization Data, Agricultural Drought Maps, and Local Conditions in China Mainland
China has lots of funds, materials, and human resources in cloud seeding operations to help with water shortage problems across the country. But there is little guide about when and where the operations would obtain better benefits. To fill this gap, the modified Water Utilization Level (WUL) map of China mainland was plotted with the acquirable water utilization data on sub‐watershed scales in this study. Then the agricultural drought levels map of different counties were integrated with the modified WUL Map under preset rules to generate an integrated water scarcity map. Lastly, the cloud seeding demand maps of different seasons were drawn by integrating the agricultural drought seasons map of different counties with the integrated water scarcity map and the modified WUL map. Results showed that the middle north of China should have the highest priorities for cloud seeding operations during spring and summer, and some regions at the south during winter and spring, a few scattered regions at the northwest during spring and summer and a few regions at the middle of southeast China during summer and autumn should also have high priorities of cloud seeding operations. This research can help rain enhancement operations to obtain better effects on easing water scarcity problems and deepen the cooperation of water resources department and weather modification department in China. The designed intersecting rules of different maps in this paper also might inspire other relevant researches.
- Open Access
Study of Machining Process of SiCp/Al Particle Reinforced Metal Matrix Composite Using Finite Element Analysis and Experimental Verification
In this paper, a two-dimensional orthogonal cutting simulation model of SiCp/Al composite was established. The geometry and material constitutive model of the particle, the matrix, and the interface layer have been modeled respectively. In view of the distribution of the particles in the matrix, this paper proposed respectively a two-dimensional particle random distribution to simulate particles randomly distributed in the matrix. Then, the cutting state of SiC reinforced particles was analyzed, the novel approach was adopted the geometric shapes of SiC particles in this study is taken as an oval shape. Three different locations of SiC particle relative to the cutting tool path were simulated to analyze the cutting state such as particle removal. The interface layer was introduced to the case that the particle was on the cutting path to study the influence on the stress and strain transfer. Through the post-processing of simulation results, the influence of interface property on the composite reinforcement effect was studied quantificationally. Finally, the cutting process of SiCp/Al composite material was simulated. This paper studied the influence on the machined surface morphology, chip morphology, stress distribution, and cutting force of many factors of the cutting speed and the cutting thickness. The single factor orthogonal cutting experiment was designed the influence of cutting speed and feed rate on the cutting force. The cutting force results of the experiment and the simulation were compared through the deviation analysis, which verified the simulation model.
Open AccessStudy of Machining Process of SiCp/Al Particle Reinforced Metal Matrix Composite Using Finite Element Analysis and Experimental Verification
In this paper, a two-dimensional orthogonal cutting simulation model of SiCp/Al composite was established. The geometry and material constitutive model of the particle, the matrix, and the interface layer have been modeled respectively. In view of the distribution of the particles in the matrix, this paper proposed respectively a two-dimensional particle random distribution to simulate particles randomly distributed in the matrix. Then, the cutting state of SiC reinforced particles was analyzed, the novel approach was adopted the geometric shapes of SiC particles in this study is taken as an oval shape. Three different locations of SiC particle relative to the cutting tool path were simulated to analyze the cutting state such as particle removal. The interface layer was introduced to the case that the particle was on the cutting path to study the influence on the stress and strain transfer. Through the post-processing of simulation results, the influence of interface property on the composite reinforcement effect was studied quantificationally. Finally, the cutting process of SiCp/Al composite material was simulated. This paper studied the influence on the machined surface morphology, chip morphology, stress distribution, and cutting force of many factors of the cutting speed and the cutting thickness. The single factor orthogonal cutting experiment was designed the influence of cutting speed and feed rate on the cutting force. The cutting force results of the experiment and the simulation were compared through the deviation analysis, which verified the simulation model.
- 1 June 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 304-309
Environmental cumulative effects assessment of cascade hydropower development in the main stream of the upper typical reaches in Minjiang River
The impact brought by hydropower cascade development on the environment is increasingly significant. At the sustainable development request, the traditional environmental impact assessment exposes many shortcomings, while it has defects of its own. Thus the cumulative environmental effects assessment is introduced here. The comparison between traditional and cumulative environmental effects t assessment shows that: the cumulative environmental effects assessment can meet the requirements on sustainable development and also has a great necessity and practical significance in hydropower cascade development in river basin. Combined with the hydropower cascade development in the main stream of the upper typical reaches of Minjiang River, conduct the environmental study on the cumulative evaluation from the water environment, ecological environment and social environment. The results reveal: the cascade development of hydropower in the typical reaches from Lianghekou to Dujiangyan in the main stream of Minjiang River has generated a certain amount of cumulative impact on the environment, especially on water environment.
- 1 June 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 304-309
Environmental cumulative effects assessment of cascade hydropower development in the main stream of the upper typical reaches in Minjiang River
The impact brought by hydropower cascade development on the environment is increasingly significant. At the sustainable development request, the traditional environmental impact assessment exposes many shortcomings, while it has defects of its own. Thus the cumulative environmental effects assessment is introduced here. The comparison between traditional and cumulative environmental effects t assessment shows that: the cumulative environmental effects assessment can meet the requirements on sustainable development and also has a great necessity and practical significance in hydropower cascade development in river basin. Combined with the hydropower cascade development in the main stream of the upper typical reaches of Minjiang River, conduct the environmental study on the cumulative evaluation from the water environment, ecological environment and social environment. The results reveal: the cascade development of hydropower in the typical reaches from Lianghekou to Dujiangyan in the main stream of Minjiang River has generated a certain amount of cumulative impact on the environment, especially on water environment.