Yiming Li

Yiming Li

Auto-generated profile, based on publicly available information

Yiming Li

Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 November 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
HLHan Li
Han Li
Peng ChenPeng Chen
Peng Chen
GYGuizhen Yu
Guizhen Yu
Bin ZhouBin Zhou
Bin Zhou
YLYiming Li
Yiming Li
YLYaping Liao
Yaping Liao
Trajectory planning for autonomous driving is challenging in unstructured scenarios such as mining sites. Existing studies mainly resort to a heuristic search-based planner to find a feasible trajectory. In the case of the narrow area, the heuristic function of the planner suffers from over-expansion problems, which may result in heavy computation burden and memory usage as well as potential failure. Therefore, a novel trajectory planning approach, namely learning and optimization-based trajectory planning (LOTP), is proposed, which is featured by a hierarchical structure consisting of two modules: (1) path searching, (2) speed profile generation. Firstly, a path searching method based on deep learning and Monte-Carlo tree search is proposed to generate a coarse path connecting starting and terminal points. Then, the path is smoothed using path optimization and provided to the speed-planning module as the reference. Next, a speed planning method based on quadratic optimization is developed, which allows to seek maximum driving comfort and energy saving. Last, extensive simulation experiments were conducted in the real environment of mining sites. The results verified that LOTP enhances the computational efficiency and success rate of path planning and helps generate an optimal speed profile. Furthermore, LOTP exhibits desirable potential for the practical application of autonomous driving at mining sites. Source implementation will be released as an open-source code.

1 September 2025 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
YLYiming Li
Yiming Li
Peng ChenPeng Chen
Peng Chen
HLHan Li
Han Li
GXGuoyan Xu
Guoyan Xu
CWChuang Wang
Chuang Wang
Parking trajectory planning in loading/dumping areas of open-pit mines presents unique challenges compared to standard parking scenarios for passenger vehicles. These include irregular workspaces, kinematic constraints of heavy trucks, and customized trajectory requirements, which collectively formulate a mixed-integer nonlinear programming (MINLP) problem with non-differentiable logical condition constraints. Mainstream MINLP solvers struggle to directly handle logical conditional constraints involving integer variables and usually fail to meet the real-time requirements of practical applications. This study presents a nearly global optimal trajectory planning method that developed a search-then-optimize framework based on the divide-and-conquer strategy, separating the difficulties into distinct stages. A multiple-priority-queue search-based method is introduced in the search stage, leveraging its gradient-free nature to tackle non-differentiable variables and generate an initial solution near the global optimal solution. In the numerical optimization stage, the problem is reformulated as a fully differentiable NLP, refining the initial trajectory to enhance quality. Extensive simulations and real-vehicle tests confirm that this method effectively addresses the above difficulties, producing efficient and trackable trajectories.

14 April 2023
Verified
Conference Paper
Open access
YLYi Ming Li
Yi Ming Li
GXGuo Yan Xu
Guo Yan Xu
HLHan Li
Han Li
Bin ZhouBin Zhou
Bin Zhou
Peng ChenPeng Chen
Peng Chen
GYGuizhen Yu
Guizhen Yu
Autonomous driving technology has been widely used in mining areas, and how to get a safe, smooth and easy-to-track path has gradually become the focus of research. Currently, most planners are oriented to structured roads and perform poorly in unstructured road scenarios. Due to the irregular and variable boundary geometry of the mining scene, the commonly used solution is to decouple the trajectory planning problem into path planning and the speed planning problem. In other words, the planning module first performs path planning and then finds the corresponding speed profile as the final result, which creates a path tracking task for the control module. This decoupling method may lose the optimality of the trajectory due to the problem of the matching degree between the path solution and the speed solution. In this paper, we present a trajectory planning method based on the idea of optimal control problem (OCP). Firstly, the hybrid A* method is used to obtain rough paths and convert them into rough trajectories based on the assumption of constant speed in the mining area. Then, an optimal control problem (OCP) is established by taking the state quantity and control quantity of the vehicle as the optimization objective, and it is discretized into a nonlinear problem (NLP). In order to solve the problem efficiently, the vehicle kinematic constraints are considered as the penalty term in the objective function. The non-convex collision avoidance constraints are transformed into convex terms by constructing a corridor. At the same time, a soft collision avoidance constraint is set as a penalty term to avoid the loss of path smoothness due to too conservative hard constraints. Finally, the proposed method is validated in two typical mining scenarios: loading and road driving areas. The results show that the proposed method enables finding a trajectory within the safety margin, and considerably improves the curvature and its rate.