Yunlai Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yunlai Wang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Hui Li
School of Mechatronical Engineering, National Key Lab of Autonomous Intelligent Unmanned System, Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Beijing Institute of Technology, Beijing, China
2 shared publications - Xiao Huang
School of Mechatronical Engineering, National Key Lab of Autonomous Intelligent Unmanned System, Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Beijing Institute of Technology, Beijing, China
2 shared publications - Xuechao Chen
Beijing Institute of Technology
2 shared publications - Zhihong Jiang
School of Mechatronical Engineering, National Key Lab of Autonomous Intelligent Unmanned System, Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Beijing Institute of Technology, Beijing, China
2 shared publications - Yan Zhao
Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology, Beijing, China
1 shared publication
Latest Publications
- 7 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (5) , 5001-5011
A Convergence Guaranteed Multiple-Shooting DDP Method for Optimization-Based Robot Motion Planning
Optimization-based motion planning plays a pivotal role in addressing high-dimensional robotic manipulation tasks. This article studies the multiple-shooting differential dynamic programming (MS-DDP) method to solve high-dimensional constrained problems with Markovian and non-Markovian processes. To tackle the non-Markovian shortest-path problem (SPP) in robot manipulation, we propose a fully multiple shooting strategy to handle the dependence between states. This strategy can solve the SPP efficiently by utilizing state augmentation at each time step to reformulate it into the Markovian process format. Moreover, we theoretically prove the quadratic convergence of the MS-DDP, providing a theoretical guarantee for the optimality of the planned trajectory. Experiments are conducted to demonstrate the optimality and efficiency of the MS-DDP method on the benchmarks of robot motion planning tasks. The real-world experimental results on a dual-arm robot validate its superiority in solving the high-dimensional shortest-path problem with complex constraints.
- 7 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (5) , 5001-5011
A Convergence Guaranteed Multiple-Shooting DDP Method for Optimization-Based Robot Motion Planning
Optimization-based motion planning plays a pivotal role in addressing high-dimensional robotic manipulation tasks. This article studies the multiple-shooting differential dynamic programming (MS-DDP) method to solve high-dimensional constrained problems with Markovian and non-Markovian processes. To tackle the non-Markovian shortest-path problem (SPP) in robot manipulation, we propose a fully multiple shooting strategy to handle the dependence between states. This strategy can solve the SPP efficiently by utilizing state augmentation at each time step to reformulate it into the Markovian process format. Moreover, we theoretically prove the quadratic convergence of the MS-DDP, providing a theoretical guarantee for the optimality of the planned trajectory. Experiments are conducted to demonstrate the optimality and efficiency of the MS-DDP method on the benchmarks of robot motion planning tasks. The real-world experimental results on a dual-arm robot validate its superiority in solving the high-dimensional shortest-path problem with complex constraints.
- 25 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (3) , 2350-2361
A Fast Coordinated Motion Planning Method for Dual-Arm Robot Based on Parallel Constrained DDP
Safe and efficient coordinated motion planning is crucial for the dual-arm robot's manipulation in the constrained environment. This article studies a fast optimization-based coordinated motion planning method for dual-arm robots based on a parallel differential dynamic programming (DDP) solver. First, the proposed method models the unstructured environment using swept sphere volumes and turns the safety and task constraints, including collision avoidance, path constraints, and closed kinematics constraints, into mathematical equalities and inequalities in an optimization problem. Second, to efficiently solve this high-dimensional and multiconstraint optimization problem, a parallel constrained differential dynamic programming (PC-DDP) solver is developed based on a new multiple shooting strategy. It utilizes the augmented Lagrangian method to handle various constraints and achieves high solving efficiency using the parallelization strategy with an approximation and the serial correction of the value function. Simulations and experiments of opening doors and transferring the box are conducted on the robot with dual 7-DOF manipulators. The results show that the proposed method works well in the motion planning of coordinated manipulations in constrained environments and that the PC-DDP is much faster than other DDP variants and large-scale optimization solvers.
- 25 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (3) , 2350-2361
A Fast Coordinated Motion Planning Method for Dual-Arm Robot Based on Parallel Constrained DDP
Safe and efficient coordinated motion planning is crucial for the dual-arm robot's manipulation in the constrained environment. This article studies a fast optimization-based coordinated motion planning method for dual-arm robots based on a parallel differential dynamic programming (DDP) solver. First, the proposed method models the unstructured environment using swept sphere volumes and turns the safety and task constraints, including collision avoidance, path constraints, and closed kinematics constraints, into mathematical equalities and inequalities in an optimization problem. Second, to efficiently solve this high-dimensional and multiconstraint optimization problem, a parallel constrained differential dynamic programming (PC-DDP) solver is developed based on a new multiple shooting strategy. It utilizes the augmented Lagrangian method to handle various constraints and achieves high solving efficiency using the parallelization strategy with an approximation and the serial correction of the value function. Simulations and experiments of opening doors and transferring the box are conducted on the robot with dual 7-DOF manipulators. The results show that the proposed method works well in the motion planning of coordinated manipulations in constrained environments and that the PC-DDP is much faster than other DDP variants and large-scale optimization solvers.