Yifan Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yifan Wu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Sheng Guo
Robotics Institute, School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, PR China
3 shared publications Majun Song
Hangzhou Innovation Institute, Beihang University, Hangzhou, Zhejiang, 310051, China
2 shared publications- Peiyi Wang
Department of Mechanical Engineering, National University of Singapore, Singapore
2 shared publications Lianzheng Niu
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
1 shared publicationPeiyi Wang
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
1 shared publicationXiangyang Wang
Robotics Research Center, Beijing Jiaotong University, Beijing, China
1 shared publication
Latest Publications
- 18 October 2023
- Published by Cambridge University Press (CUP) in Robotica
- Vol. 41 (12) , 3746-3771
Design of an optimized gait planning generator for a quadruped robot using the decision tree and random forest workspace model
Real-time gait trajectory planning is challenging for legged robots walking on unknown terrain. In this paper, to realize a more efficient and faster motion control of a quadrupedal robot, we propose an optimized gait planning generator (GPG) based on the decision tree (DT) and random forest (RF) model of the robot leg workspace. First, the framework of this embedded GPG and some of the modules associated with it are illustrated. Aiming at the leg workspace model described by DT and RF used in GPG, this paper introduces in detail how to collect the original data needed for training the model and puts forward an Interpolation Labeling with Dilation and Erosion (ILDE) data processing algorithm. After the DT and RF models are trained, we preliminarily evaluate their performance. We then present how these models can be used to predict the location relation between a spatial point and the leg workspace based on its distributional features. The DT model takes only 0.00011 s to process a sample, while the RF model can give the prediction probability. As a complement, the PID inverse kinematic model used in GPG is also mentioned. Finally, the optimized GPG is tested during a real-time single-leg trajectory planning experiment and an unknown terrain recognition simulation of a virtual quadrupedal robot. According to the test results, the GPG shows a remarkable rapidity for processing large-scale data in the gait trajectory planning tasks, and the results can prove it has an application value for quadruped robot control.
- 18 October 2023
- Published by Cambridge University Press (CUP) in Robotica
- Vol. 41 (12) , 3746-3771
Design of an optimized gait planning generator for a quadruped robot using the decision tree and random forest workspace model
Real-time gait trajectory planning is challenging for legged robots walking on unknown terrain. In this paper, to realize a more efficient and faster motion control of a quadrupedal robot, we propose an optimized gait planning generator (GPG) based on the decision tree (DT) and random forest (RF) model of the robot leg workspace. First, the framework of this embedded GPG and some of the modules associated with it are illustrated. Aiming at the leg workspace model described by DT and RF used in GPG, this paper introduces in detail how to collect the original data needed for training the model and puts forward an Interpolation Labeling with Dilation and Erosion (ILDE) data processing algorithm. After the DT and RF models are trained, we preliminarily evaluate their performance. We then present how these models can be used to predict the location relation between a spatial point and the leg workspace based on its distributional features. The DT model takes only 0.00011 s to process a sample, while the RF model can give the prediction probability. As a complement, the PID inverse kinematic model used in GPG is also mentioned. Finally, the optimized GPG is tested during a real-time single-leg trajectory planning experiment and an unknown terrain recognition simulation of a virtual quadrupedal robot. According to the test results, the GPG shows a remarkable rapidity for processing large-scale data in the gait trajectory planning tasks, and the results can prove it has an application value for quadruped robot control.
- 3 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 6375-6382
Design and Analysis of a Novel Variable Stiffness Continuum Robot With Built-in Winding-Styled Ropes
Continuum robots driven by rods have a wide range of applications, such as detection and maintenance tasks in unstructured environments. However, their inherent nature of flexibility also limits their function. Thus, variable stiffness mechanisms for continuum robots have consistently attracted the attention of researchers in recent years. In this letter, a winding-styled rope inspired by snakes’ behavior is first built into the constraint disk of a rod-driven continuum robot. Combined with shape memory alloy (SMA) spring, the winding ropes perform a variable stiffness or ‘lock’ function by adjusting the friction between the ropes and rods. A maximum static friction is up to 2 times the spring tension according to the test results. Based on the fitting relationship between SMA spring tension and friction, the established kinetostatics model can predict the manipulator configuration. Furthermore, comparative experiments proved that the stiffness change is mainly caused by the proposed mechanism. By controlling the temperature of SMA, the variable stiffness of the manipulator is achieved. The C-shape has a maximum stiffness of 0.03505 N/mm and that this shape has a maximum stiffness increase of 300%.
- 3 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 6375-6382
Design and Analysis of a Novel Variable Stiffness Continuum Robot With Built-in Winding-Styled Ropes
Continuum robots driven by rods have a wide range of applications, such as detection and maintenance tasks in unstructured environments. However, their inherent nature of flexibility also limits their function. Thus, variable stiffness mechanisms for continuum robots have consistently attracted the attention of researchers in recent years. In this letter, a winding-styled rope inspired by snakes’ behavior is first built into the constraint disk of a rod-driven continuum robot. Combined with shape memory alloy (SMA) spring, the winding ropes perform a variable stiffness or ‘lock’ function by adjusting the friction between the ropes and rods. A maximum static friction is up to 2 times the spring tension according to the test results. Based on the fitting relationship between SMA spring tension and friction, the established kinetostatics model can predict the manipulator configuration. Furthermore, comparative experiments proved that the stiffness change is mainly caused by the proposed mechanism. By controlling the temperature of SMA, the variable stiffness of the manipulator is achieved. The C-shape has a maximum stiffness of 0.03505 N/mm and that this shape has a maximum stiffness increase of 300%.
- 26 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 157-162
Gait-based Design and Human-machine Simulation of a Powered Hybrid Transfemoral Prosthetic Mechanism
To restore the knee and ankle locomotion for transfemoral amputees, a series-parallel knee-ankle prosthetic mechanism is proposed, which is composed of a parallel mechanism and an ankle-foot prosthetic mechanism. The designed parallel mechanism can replace the knee flexion-extension and ankle varus-valgus, and an ankle-foot prosthetic mechanism, which developed in author’s previous work, has the motion of plantarflexion-dorsiflexion. Besides, the kinematic and mechanical performances of the parallel mechanism clearly indicated its feasibility as the prosthesis. Furthermore, a wearable elastic clutched device is designed to provide power and moment for the flexion of the prosthetic knee, which can effectively reduce the peak power of motors. Combined with the compression springs in prismatic pairs, the prosthetic mechanism has the energy circulation ability. The results show that the prosthetic mechanism can meet the movement of transfemoral amputees and also has sufficient carrying capacity. The knee moment of the prosthetic mechanism is similar to the human’s and shows good dynamic performance.
- 26 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 157-162
Gait-based Design and Human-machine Simulation of a Powered Hybrid Transfemoral Prosthetic Mechanism
To restore the knee and ankle locomotion for transfemoral amputees, a series-parallel knee-ankle prosthetic mechanism is proposed, which is composed of a parallel mechanism and an ankle-foot prosthetic mechanism. The designed parallel mechanism can replace the knee flexion-extension and ankle varus-valgus, and an ankle-foot prosthetic mechanism, which developed in author’s previous work, has the motion of plantarflexion-dorsiflexion. Besides, the kinematic and mechanical performances of the parallel mechanism clearly indicated its feasibility as the prosthesis. Furthermore, a wearable elastic clutched device is designed to provide power and moment for the flexion of the prosthetic knee, which can effectively reduce the peak power of motors. Combined with the compression springs in prismatic pairs, the prosthetic mechanism has the energy circulation ability. The results show that the prosthetic mechanism can meet the movement of transfemoral amputees and also has sufficient carrying capacity. The knee moment of the prosthetic mechanism is similar to the human’s and shows good dynamic performance.