LZLin Zhang

Lin Zhang

*This is an algorithmically generated author record based on publicly available information.

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


Lin Zhang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Terrain-Coupled Hierarchical Optimization for Multirobot Deployment With a Global Reachability–Cost Atlas

    by Tianwei Niu, Shengshan Ma, Runjiao Bao, Lin Zhang, Haoyu Yuan, Liang Wang, Shoukun Wang

    Autonomous multi-robot deployment (MRD) aims to determine feasible and task-effective deployment poses for robots to accomplish cooperative missions. When applied to unstructured outdoor environments, MRD must contend with irregular terrain geometry, uneven contact surfaces, and terrain-dependent traversability, challenging purely geometric MRD methods. This work proposes a hierarchical MRD framework that unifies terrain-coupled feasibility modeling and execution-aware optimization into a coherent deployment process. An upper-stage nonlinear programming, constrained by a signed-distance field derived from a multi-layer terrain assessment map (MTAM), enforces strict geometric deployment feasibility and yields high-quality candidate fleet configurations. A lower-stage multi-objective evolutionary optimizer then refines fleet poses using a global reachability-cost atlas (GRCA) that precomputes reachability and minimal traversal cost of each robot to every map cell, enabling constant-time candidate evaluation. Terrain coupling is achieved by embedding terrain-risk layers of the MTAM into the optimization objectives, guiding pose refinement toward stable and traversable regions. Extensive simulations and field trials on vibroseis fleet demonstrate system-level integration within a seismic source excitation pipeline, achieving task-level geometric accuracy, stable terrain contact at deployment poses, and real-time onboard optimization with an average latency below 10 s.

  • Proprioception-Guided Framework for Terrain Roughness Assessment and Bayesian RRG Planning

    by Tianwei Niu, Haoyu Yuan, Shengshan Ma, Lin Zhang, Shoukun Wang, Junzheng Wang

    Irregular and unpredictable terrains in unstructured environments, including mountains, deserts, rural areas and construction sites, remain a fundamental obstacle to reliable autonomous navigation. The primary difficulty lies in enabling vehicles to accurately understand the risks posed by complex terrains and traverse along flat paths. To address these challenges, this paper presents a terrain-aware path planning framework that couples proprioceptive-sensitive roughness assessment with an improved rapidly-exploring random graph (RRG). From first principles, we design a multi-scale frequency-domain analysis network (MFDAN) that learns terrain roughness from vehicle proprioceptive responses, isolating the frequency bands most responsible for jolts. These bands underpin a terrain roughness map aligned with the vehicle’s dynamic response to the terrain. Building on this map, we introduce a Bayesian learning RRG planner that integrates roughness gradients for high-yield expansion and online Bayesian updating to bias exploration toward safer and more promising directions. The proposed framework is extensively validated in diverse Gazebo simulations and against state-of-the-art baselines, demonstrating significant reductions in jolt level, planning failures, and computation time. Finally, real-world deployment on a 40-ton vibroseis truck in unstructured field environments confirms the practicality and robustness of the framework.


  • Continuous-Space Multi-Agent Path Finding via Enhanced Prioritized Search With Ackermann Kinematic Constraints

    by Tianyuan Zhang, Lin Zhang, Qiyu Cai, Shoukun Wang, Junzheng Wang

    Multi-Agent Path Finding (MAPF) in complex environments remains challenging due to high computational complexity, frequent conflicts, and realistic motion constraints. Most existing methods focus on discrete spaces or idealized omnidirectional models, often neglecting or partially considering nonholonomic constraints, which limits their applicability to real-world robotic systems. This letter proposes a hierarchical continuous-space MAPF framework explicitly designed for Ackermann-steered robots, balancing computational efficiency, global coordination, and motion feasibility. In the path search layer, a spatiotemporal hybrid A* algorithm with an adaptive dynamic weighting factor improves the trade-off between computational cost and path quality, while a homotopy-group clustering mechanism provides structured agent grouping for conflict resolution. In the conflict resolution layer, a partial-order priority reconstruction and flexible priority-based dynamic adjustment strategy effectively reduce search space and conflict density. The trajectory optimization layer integrates a decentralized sequential quadratic programming method to ensure trajectory feasibility and smoothness. Comprehensive experiments, including ablation, comparative, and scalability studies, demonstrate that the proposed method achieves lower runtime, reduced execution cost, and better coordination than existing MAPF approaches, while maintaining strong scalability in high-density environments.

  • GMPPO: Guided Model Predictive Path Optimization for Mobile Robots in Obstacle-Constrained Environments

    by Lin Zhang, Wenhao Zhang, Runjiao Bao, Tianwei Niu, Shoukun Wang, Junzheng Wang

    Autonomous navigation of industrial mobile robots in obstacle-constrained environment, such as manufacturing floors, warehouse storage systems, and factory inspection scenarios, poses significant challenges in ensuring path feasibility, safety, and real-time performance. This article proposes a guided model predictive path optimization (GMPPO) framework to address these issues. First, an enhanced convex feasible set algorithm is employed to generate robust initial paths by integrating decoupled dimensionality reduction and a dual-layer fault-tolerant mechanism. Second, based on this reference path, robot geometry, and real-time obstacle information, dynamic safety corridors are constructed to characterize local feasible spaces. Finally, these reference paths and corresponding safety corridors guide a high-fidelity model predictive optimization process, yielding smooth, dynamically feasible, and collision-free trajectories under nonholonomic constraints. Theoretical analysis establishes the resolution completeness and feasibility guarantee of the proposed method. Extensive simulations, real-world robotic experiments, and engineering deployments demonstrate that GMPPO significantly improves planning success rates, trajectory smoothness, and operational safety, while maintaining high computational efficiency and broad applicability.


  • 4WIDS-MAPF: Multiagent Pathfinding for Four-Wheel Independent Drive/Steering Robots

    by Lin Zhang, Tianyuan Zhang, Yichen An, Tianwei Niu, Shoukun Wang, Junzheng Wang

    Modern autonomous systems face significant challenges in coordinating multiple agents within complex environments, especially under nonholonomic constraints and kinodynamic motion planning demands. In particular, four-wheel independent drive/steering (4WIDS) robots, with their multimodal locomotion and nonholonomic kinematics, introduce new complexity to multiagent pathfinding problems in continuous space. This study addresses the critical challenge of generating collision-free, dynamically feasible paths for multi-4WIDS robot systems. We propose a hierarchical multiagent path finding (MAPF) framework that explicitly tackles two core limitations in existing methods: 1) a lack of physically realistic interagent conflict modeling; and 2) the inability to account for motion mode switching costs in kinodynamic path planning. At the upper level, we introduce a continuous-space binary conflict tree for resolving space–time collisions using physical dimensions and motion feasibility. At the lower level, we implement a hybrid A* search over a motion primitive database that considers mode-switch penalties and kinematic constraints. To improve search performance, we introduce two novel mechanisms: 1) a focused search factor for directional exploration and 2) an adaptive heuristic weighting factor to balance optimality and computational speed. Extensive experiments, including benchmark comparisons, ablation studies, and sensitivity analysis, validate the proposed method’s superior performance in interagent conflict resolution, real-time feasibility, and path quality.


  • A Hierarchical Target Vehicle Pose Detection Framework in Ro-Ro Terminal Environment

    by Runjiao Bao, Yongkang Xu, Junfeng Xue, Haoyu Yuan, Lin Zhang, Shoukun Wang

    In light of the urgent need to automate and upgrade roll-on/roll-off (Ro-Ro) transportation methods in ports, many ports have started using transfer Automated Guided Vehicle (AGV) to replace traditional manual operations. Automatic docking is a critical aspect of transportation, which relies heavily on accurately identifying and localizing target vehicles. However, frequent issues such as point cloud feature loss and truncation of point clouds—often due to perception dead zones during the docking process—can significantly hinder existing vehicle recognition methods. This paper introduces a hierarchical vehicle pose detection approach. During the early and mid-stages of docking, we employ two branches for identifying target vehicles to reduce the effects of feature loss and the frequent changes in shape: Voxel R-CNN and an improved search-based optimal bounding box fitting algorithm, which are then combined through result fusion. Additionally, to tackle feature loss caused by point cloud truncation in the late docking phase, we have developed a method to detect wheel poses and calculate the target vehicle pose inversely. Building on this, we established a set of composite evaluation metrics for method switching, ensuring the stability and robustness of the results. Our hierarchical vehicle pose detection method has been successfully implemented in transfer AGVs and applied to port roll-on/roll-off logistics transportation. In datasets collected during actual docking processes, the recognition performance of this framework has surpassed that of the most commonly used 3D object detection methods.


  • Open Access

    Research on a power smoothing control strategy for energy storage hydraulic wind turbines

    by Wei Gao, Yankang Zhang, Lin Zhang, Chao Ai, Lijuan Chen