Runda Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Runda Zhang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Runqi Chai
Beijing Institute of Technology
10 shared publications - Yuanqing Xia
Zhongyuan University of Technology
10 shared publications - Senchun Chai
Beijing Institute of Technology
9 shared publications - Kaiyuan Chen
Vanke School of Public Health, Tsinghua University, Beijing, China
3 shared publications - Antonios Tsourdos
Faculty of Engineering and Applied Sciences, Cranfield University, College Road, Bedford MK43 0AL, UK
2 shared publications - Zhida Xing
School of Automation, Beijing Institute of Technology, Beijing, China
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (11) , 25942-25954
Efficient Global Trajectory Planning for AGVs Based on Convex-Concave-Decomposition
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (11) , 25942-25954
Efficient Global Trajectory Planning for AGVs Based on Convex-Concave-Decomposition
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (5) , 5480-5490
Globally Optimal Motion Planning for Mobile Robots via Topology-Aware Divide-and-Conquer
Sampling-based motion planning methods have become widely adopted for motion planning due to their effectiveness in high-dimensional and complex environments. However, existing methods often prioritize planning efficiency and tend to get trapped in local optima. To overcome this limitation, we propose a divide-and-conquer hybrid sampling planning framework (DCH-RRT*), which decomposes the overall planning problem into topology-constrained subspaces for parallel exploration under the guidance of topological structure. DCH-RRT* first constructs a Connectivity Roadmap (CRM) and explores diverse topologies based on CRM to perform topology-aware decomposition, enabling an effective partitioning of the entire configuration space. A hybrid sampling strategy is then introduced to guide efficient exploration and accelerate convergence within the topology-informed, nonuniform sampling space. Theoretical analysis confirms that the proposed framework retains asymptotic optimality, while extensive experiments demonstrate that it consistently achieves high-quality paths with competitive computational efficiency compared to existing methods.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (5) , 5480-5490
Globally Optimal Motion Planning for Mobile Robots via Topology-Aware Divide-and-Conquer
Sampling-based motion planning methods have become widely adopted for motion planning due to their effectiveness in high-dimensional and complex environments. However, existing methods often prioritize planning efficiency and tend to get trapped in local optima. To overcome this limitation, we propose a divide-and-conquer hybrid sampling planning framework (DCH-RRT*), which decomposes the overall planning problem into topology-constrained subspaces for parallel exploration under the guidance of topological structure. DCH-RRT* first constructs a Connectivity Roadmap (CRM) and explores diverse topologies based on CRM to perform topology-aware decomposition, enabling an effective partitioning of the entire configuration space. A hybrid sampling strategy is then introduced to guide efficient exploration and accelerate convergence within the topology-informed, nonuniform sampling space. Theoretical analysis confirms that the proposed framework retains asymptotic optimality, while extensive experiments demonstrate that it consistently achieves high-quality paths with competitive computational efficiency compared to existing methods.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-11
Multi-Stage Optimization for Stable WMR Motion Planning in Slope Environments
In this work, we propose a trajectory planning framework for wheeled mobile robot (WMR) navigation in environments with sloped terrain. The framework adopts a hybrid strategy that combines sampling-based and optimization-based methods to plan stable trajectory for the robot on a known elevation map. It adopts a two-layer hierarchical structure to ensure fast and stable convergence of the planning process. In the first layer, a traversability probabilistic roadmap (T-PRM) is constructed to perform a coarse-level feasible route search, which serves to identify traversable regions and determine the task sequence. In the second layer, the planning problem is formulated as a multi-stage optimal control problem (MOCP), taking into account obstacle constraints, terrain constraints, and kinematic constraints. Notably, the coarse trajectory generated in the first layer defines the connectivity of the MOCP, significantly accelerating the convergence of the optimization. Finally, extensive results demonstrate the effectiveness of the proposed framework.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-11
Multi-Stage Optimization for Stable WMR Motion Planning in Slope Environments
In this work, we propose a trajectory planning framework for wheeled mobile robot (WMR) navigation in environments with sloped terrain. The framework adopts a hybrid strategy that combines sampling-based and optimization-based methods to plan stable trajectory for the robot on a known elevation map. It adopts a two-layer hierarchical structure to ensure fast and stable convergence of the planning process. In the first layer, a traversability probabilistic roadmap (T-PRM) is constructed to perform a coarse-level feasible route search, which serves to identify traversable regions and determine the task sequence. In the second layer, the planning problem is formulated as a multi-stage optimal control problem (MOCP), taking into account obstacle constraints, terrain constraints, and kinematic constraints. Notably, the coarse trajectory generated in the first layer defines the connectivity of the MOCP, significantly accelerating the convergence of the optimization. Finally, extensive results demonstrate the effectiveness of the proposed framework.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (5) , 5462-5469
An Efficient and Lightweight Multi-Goal Path Planning Based on Enhanced Sampling Planner
In this work, we propose a novel lightweight and efficient multi-goal path planning (MGPP) framework tailored for complex environments with obstacles. The framework adopts a hierarchical architecture consisting of two layers: a visiting order decision layer and an incremental sampling-based planning layer. In the visiting order decision layer, a lightweight feature node graph (FNG) is constructed to capture the connectivity structure of the environment. Based on the FNG, a multi-query strategy is employed to efficiently build the goal-to-goal cost matrix, achieving both computational efficiency and completeness. Given this cost matrix, a near-optimal Hamiltonian path with fixed start and end points is computed to determine the visiting order of the goal set. In the path planning layer, an enhanced sampling-based path planner is developed to perform efficient goal-to-goal path planning. The proposed enhanced sampling method explores multiple homotopy classes of interest, which improves planning efficiency and helps avoid local minima. Finally, extensive simulations and experiments validate the effectiveness and advantages of the proposed method.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (5) , 5462-5469
An Efficient and Lightweight Multi-Goal Path Planning Based on Enhanced Sampling Planner
In this work, we propose a novel lightweight and efficient multi-goal path planning (MGPP) framework tailored for complex environments with obstacles. The framework adopts a hierarchical architecture consisting of two layers: a visiting order decision layer and an incremental sampling-based planning layer. In the visiting order decision layer, a lightweight feature node graph (FNG) is constructed to capture the connectivity structure of the environment. Based on the FNG, a multi-query strategy is employed to efficiently build the goal-to-goal cost matrix, achieving both computational efficiency and completeness. Given this cost matrix, a near-optimal Hamiltonian path with fixed start and end points is computed to determine the visiting order of the goal set. In the path planning layer, an enhanced sampling-based path planner is developed to perform efficient goal-to-goal path planning. The proposed enhanced sampling method explores multiple homotopy classes of interest, which improves planning efficiency and helps avoid local minima. Finally, extensive simulations and experiments validate the effectiveness and advantages of the proposed method.
- 4 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (11) , 11474-11481
Light Reflection-Guided RRT$^{*}$: Efficient Path Planning in Narrow Passages
In complex and constrained environments, robot path planning faces the dual challenges of efficiency and solution quality. This letter presents a Light Reflection Heuristic RRT$^{*}$ algorithm (LRH-RRT$^{*}$), which generates the reference path by simulating light reflections along obstacle boundaries and adaptively adjusts the sampling distribution. A dynamic path pruning strategy is introduced to eliminate redundant nodes, and third-order Bézier curve interpolation is applied to smooth the path while satisfying the dynamic constraints of mobile robots. Experimental results demonstrate that LRH-RRT$^{*}$ improves planning efficiency and path quality in various narrow passage scenarios.
- 4 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (11) , 11474-11481
Light Reflection-Guided RRT$^{*}$: Efficient Path Planning in Narrow Passages
In complex and constrained environments, robot path planning faces the dual challenges of efficiency and solution quality. This letter presents a Light Reflection Heuristic RRT$^{*}$ algorithm (LRH-RRT$^{*}$), which generates the reference path by simulating light reflections along obstacle boundaries and adaptively adjusts the sampling distribution. A dynamic path pruning strategy is introduced to eliminate redundant nodes, and third-order Bézier curve interpolation is applied to smooth the path while satisfying the dynamic constraints of mobile robots. Experimental results demonstrate that LRH-RRT$^{*}$ improves planning efficiency and path quality in various narrow passage scenarios.
- 4 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 298
Learning-based trajectory planning for AGVs in dynamic environment
- 4 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 298
Learning-based trajectory planning for AGVs in dynamic environment
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (1) , 681-692
Efficient and Near-Optimal Global Path Planning for AGVs: A DNN-Based Double Closed-Loop Approach With Guarantee Mechanism
In this article, a novel global path planning approach with rapid convergence properties for autonomous ground vehicles (AGVs) named neural sampling rapidly exploring random tree (NS-RRT*) is proposed. This approach has a three-layer structure to obtain a feasible and near-optimal path. The first layer is the data collection stage. Utilizing the target area adaptive rapidly exploring random tree (TAA-RRT*) algorithm to establish a collection of paths considering the initial noise disturbance. To enhance network generalization, an optimal path backward generation (OPBG) strategy is introduced to augment the dataset size. In the second layer, the deep neural network (DNN) is trained to learn the relationships between the states and the sampling strategies. In the third layer, the trained model is used to guide RRT* sampling, and an efficient guarantee mechanism is also designed to ensure the feasibility of the planning task. The proposed algorithm can assist the RRT* algorithm in efficiently obtaining optimal or near-optimal strategies, significantly enhancing search efficiency. Numerical results and experiments are executed to demonstrate the feasibility and efficiency of the proposed method.
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (1) , 681-692
Efficient and Near-Optimal Global Path Planning for AGVs: A DNN-Based Double Closed-Loop Approach With Guarantee Mechanism
In this article, a novel global path planning approach with rapid convergence properties for autonomous ground vehicles (AGVs) named neural sampling rapidly exploring random tree (NS-RRT*) is proposed. This approach has a three-layer structure to obtain a feasible and near-optimal path. The first layer is the data collection stage. Utilizing the target area adaptive rapidly exploring random tree (TAA-RRT*) algorithm to establish a collection of paths considering the initial noise disturbance. To enhance network generalization, an optimal path backward generation (OPBG) strategy is introduced to augment the dataset size. In the second layer, the deep neural network (DNN) is trained to learn the relationships between the states and the sampling strategies. In the third layer, the trained model is used to guide RRT* sampling, and an efficient guarantee mechanism is also designed to ensure the feasibility of the planning task. The proposed algorithm can assist the RRT* algorithm in efficiently obtaining optimal or near-optimal strategies, significantly enhancing search efficiency. Numerical results and experiments are executed to demonstrate the feasibility and efficiency of the proposed method.
- 15 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 11 (5) , 1292-1294
A Data-Driven Real-Time Trajectory Planning and Control Methodology for UGVs Using LSTMRDNN
Dear Editor, This letter presents a novel data-driven trajectory planning and control scheme for the unmanned ground vehicles (UGVs). A recent work [1] has demonstrated the effectiveness of approximating the optimal state feedback for a nonlinear unmanned system via deep neural network (DNN). To further the previous research, we construct a long-short term memory recurrent deep neural network (LSTMRDNN) to improve the performance of the data-driven approximation instrument. The proposed strategy is evaluated and verified through theoretical analyses and experiments.
- 15 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 11 (5) , 1292-1294
A Data-Driven Real-Time Trajectory Planning and Control Methodology for UGVs Using LSTMRDNN
Dear Editor, This letter presents a novel data-driven trajectory planning and control scheme for the unmanned ground vehicles (UGVs). A recent work [1] has demonstrated the effectiveness of approximating the optimal state feedback for a nonlinear unmanned system via deep neural network (DNN). To further the previous research, we construct a long-short term memory recurrent deep neural network (LSTMRDNN) to improve the performance of the data-driven approximation instrument. The proposed strategy is evaluated and verified through theoretical analyses and experiments.
- 6 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (2) , 1811-1822
Design and Practical Implementation of a High Efficiency Two-Layer Trajectory Planning Method for AGV
This article proposes a two-layer trajectory optimization method for the autonomous ground vehicle. This two-layer strategy includes an efficient path planning layer and a fast trajectory planning layer. In the first layer, a novel target area adaptive rapidly exploring random tree algorithm (TAA-RRT*) is proposed to search the shortest path. This layer mainly includes a preprocessing and a sampling planning process. In the preprocessing process, the generalized voronoi diagram is used to construct the environment information and find the initial path. Then, the sampled target area (TA) is constructed based on this initial path to provide nonuniform sampling. In the sampling planning process, the improved adaptive RRT* algorithm is used to carry out sampling planning in the TA, and the direct connection strategy is combined to quickly locate the optimal solution. In the trajectory planning layer, combined with the constraints of the unmanned vehicle and the path constraints obtained in the first layer, the speed planning and the trajectory optimization are addressed by solving the optimal control problem. After performing a large number of experiments, the feasibility and effectiveness of the proposed method are verified.
- 6 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (2) , 1811-1822
Design and Practical Implementation of a High Efficiency Two-Layer Trajectory Planning Method for AGV
This article proposes a two-layer trajectory optimization method for the autonomous ground vehicle. This two-layer strategy includes an efficient path planning layer and a fast trajectory planning layer. In the first layer, a novel target area adaptive rapidly exploring random tree algorithm (TAA-RRT*) is proposed to search the shortest path. This layer mainly includes a preprocessing and a sampling planning process. In the preprocessing process, the generalized voronoi diagram is used to construct the environment information and find the initial path. Then, the sampled target area (TA) is constructed based on this initial path to provide nonuniform sampling. In the sampling planning process, the improved adaptive RRT* algorithm is used to carry out sampling planning in the TA, and the direct connection strategy is combined to quickly locate the optimal solution. In the trajectory planning layer, combined with the constraints of the unmanned vehicle and the path constraints obtained in the first layer, the speed planning and the trajectory optimization are addressed by solving the optimal control problem. After performing a large number of experiments, the feasibility and effectiveness of the proposed method are verified.