RWRunhua Wang

Runhua Wang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Runhua Wang has a total of 37 co-authors. Here are the top co-authors by number of shared publications:

  • Xuebo Zhang

    Institute of Robotics and Automatic Information Systems and Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China

    16 shared publications
  • Shiyong Zhang

    College of Artificial Intelligence, Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China

    7 shared publications
  • Jing Yuan

    College of Artificial Intelligence, Nankai University, Tianjin, China

    5 shared publications
  • Zhixing Song

    College of Artificial Intelligence, Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China

    5 shared publications
  • Youwei Wang

    College of Artificial Intelligence, Institute of Robotics and Automatic Information System, and the Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China

    4 shared publications
  • Lun Li

    Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China

    3 shared publications

Latest Publications

  • Any-Angle and Arbitrary-Geometry SIPP: Multi-Agent Path Finding With Polygonal Shapes

    by Yichen Li, Xuebo Zhang, Runhua Wang, Zhijie Hu, Yaonan Wang

    Multi-Agent Path Finding (MAPF) aims to compute safe, conflict-free paths from start to goal configurations for multiple agents. Modern robotic deployments frequently involve heterogeneous agents with irregular shapes or large payloads, making conventional point or circle based approximations inapplicable for safe and efficient planning. To address this, we propose the Any-Angle and Arbitrary-Geometry Safe Interval Path Planning (AAG-SIPP) algorithm, which plans safe paths for multi-agent systems with arbitrary polygonal shapes, including convex and concave geometries, by allowing any-angle movement between both adjacent and non-adjacent grid cells. As AAG-SIPP operates within a prioritized planning framework, we introduce a Shape Heuristic (SH) strategy to determine the planning sequence of agents based on their geometric complexity, ensuring higher success rate and balanced path lengths. Experimental results show that AAG-SIPP provides a more robust and efficient solution for complex MAPF scenarios, delivering up to a 92.44% reduction in runtime and superior path quality across diverse maps, effectively solving dense warehouse problems that remain difficult for circular-model baselines.

  • Visibility State Space Guided Path Planning for Human-Like Parking of Nonholonomic Mobile Robots

    by Runhua Wang, Xuebo Zhang, Jian Wen

    Existing autonomous parking methods for indoor mobile robots generally adopt visual servoing techniques. However, these methods are prone to losing feature points due to limited field of view (FOV) of the camera, especially in the case of large initial lateral error of the robot. In this paper, a novel visibility state space guided Bi-Rapidly-exploring-Random-Trees path planning (VS-BiRRT) framework is proposed for robust parking of nonholonomic mobile robots, which can guarantee the FOV constraint and produce human-like parking behavior. To efficiently search a feasible parking path, a discrete visibility state space relative to feature points is constructed, inside which all the robot poses satisfy the FOV constraint of the camera. With this space, the planner can conduct heuristic node sampling and fast FOV constraint checking, so as to improve the search efficiency. To avoid redundant edge propagations, a steering function is utilized for the edge expansion, directly drawing the tree toward the newly sampled node as near as possible. In addition, the greedy extension is designed to achieve accurate path connection. Comparative simulations show the superior performance of the proposed method, and real experiments show its validity in challenging parking tasks such as parallel parking.

  • SPTL-LCC: Single-Shot, Pixel-Level, Target-Free, and LiDAR-Type Agnostic LiDAR-Camera Extrinsic Self-Calibration

    by Youwei Wang, Yunze Tong, Runhua Wang, Shiyong Zhang, Zhixing Song, Xuebo Zhang

    The fusion of LiDAR and camera data holds vast application prospects, with calibration as a crucial prerequisite. In this paper, we propose SPTL-LCC, a LiDAR -type agnostic and target-free LiDAR-camera extrinsic calibration framework. The core of SPTL-LCC lies in extracting accurate 3D-2D correspondences in 2D image space using a densified point cloud and an image. To ensure the acquisition of a densified point cloud, a point cloud accumulation evaluation metric is proposed. Building upon this, a multi-stage LiDAR image processing and optimization method based on a virtual camera is proposed. Then, multiple image matching networks are employed to estimate 2D-2D correspondences between the LiDAR images and camera images, resulting in 3D-2D correspondences. A progressive reprojection error minimization algorithm is subsequently proposed to optimize the extrinsic parameters based on these correspondences. SPTL-LCC improves LiDAR image quality in a few iterations, enhancing correspondence estimation accuracy, thus achieving coarse-to-fine calibration. Extensive experiments on four self-recorded datasets show SPTL-LCC outperforms state-of-the-art methods in terms of robustness, accuracy, and practicality, with an average error of less than 0.03 m in translation and 0.4$^{\circ }$ in rotation. Moreover, experiments on the KITTI dataset show SPTL-LCC even achieves comparable performance to end-to-end methods trained on this dataset, which exhibit poor generalization. Our code and datasets are open-source: https://github.com/NKU-MobFly-Robotics/SPTG-LCC.


  • Environment-Adaptive Motion Planning via Reinforcement Learning-Based Trajectory Optimization

    by Zhejin Zhu, Runhua Wang, Yisong Wang, Yaonan Wang, Xuebo Zhang

    This paper proposes a novel environment-adaptive motion planning framework for mobile robots, which utilizes deep reinforcement learning to dynamically adjust optimization objectives according to various environmental and robot-ego characteristics, greatly enhancing the adaptability and robustness compared to existing motion planning strategies. Our approach features a two-stage trajectory optimization algorithm that optimizes for smoothness, safety, and efficiency—elements critical in practical applications. Firstly, we propose a reinforcement learning algorithm that dynamically adjusts optimization objectives based on the environmental context, which carefully encodes the environment, coarse initial path and robot information into the observation space. Additionally, two techniques are designed to reduce the sim-to-real gap: 1) integrating classical optimization framework as the motion planning backbone; 2) using low-dimensional input in the learning component, which minimizes discrepancies between simulated and real-world conditions. With the hybrid strategy, not only the interpretability and stability of the classical motion planning pipeline is preserved, but also the adaptive capability of emerging DRL techniques is fully utilized. The efficacy of the proposed solution is demonstrated through extensive simulations and real-world experiments, showcasing superior performance in terms of safety and efficiency across various testing scenarios. Especially in unknown and cluttered real office environments, our approach significantly improve safety (17% increase in success rate) and efficiency (29% reduction in time cost), compared to the popular traditional methods. (Supplementary video link: https://youtu.be/ph0pDGpI864.).


  • FI-SLAM: Feature Information-Based Robust and Efficient LiDAR SLAM

    by Zhixing Song, Xuebo Zhang, Runhua Wang, Shiyong Zhang, Songyang Wu, Youwei Wang, Jing Yuan

    In environments with sparse or redundant features, the accuracy or real-time performance of LiDAR simultaneous localization and mapping (SLAM) systems significantly deteriorates. This paper proposes a novel feature information-based robust and efficient LiDAR SLAM (FI-SLAM). First, we introduce a single-feature information evaluation method based on subspace vector similarity to cope with the scale inconsistency between rotation and translation in 3-D space. Then, to overcome the limitations of existing degradation evaluation methods that only focus on constraint sufficiency, we elaborately devise a robust degradation evaluation algorithm based on total information volume and density, which considers both the sufficiency and reliability of constraints with strong robustness to environmental changes. Information density is a novel concept we introduce, referring to the average information of feature constraints, used to evaluate constraint reliability. Next, to reduce the delay of the SLAM system, we propose an efficient and reliable feature selection algorithm based on information priority, which can quickly select a feature subset with high-quality information and requires almost no additional computing time. This algorithm significantly improves system efficiency in environments with redundant features. Finally, experimental results in self-built simulation scenarios and real-world environments show that FI-SLAM outperforms state-of-the-art methods in terms of accuracy, robustness, and real-time performance. Specifically, the average time consumption for feature association and optimization is reduced by 48.39%, and the localization accuracy in degenerate environments is improved by up to 89.77%. Supplementary video is available at https://youtu.be/x9duvizvvIg.


  • STVO: Spatial-Temporal Constrained Velocity Obstacle for Safe Navigation Among Pedestrians

    by Yichen Song, Runhua Wang, Qingchen Bi, Zhangchao Pan, Haiming Gao, Xuebo Zhang

    This paper presents a novel motion planning method that safely navigates the unmanned ground vehicle (UGV) among pedestrian-rich environments by constructing the spatial-temporal constrained velocity obstacle (STVO) region. Compared with existing velocity obstacle (VO) type-based methods, the novelty of this work is twofold: 1) An innovative temporal constraint is introduced into the velocity space, also playing the role as an adaptive collision time constraint to dynamically adjust the velocity obstacle region according to real-time perceived pedestrian density; 2) The spatial constraint is proposed to foresee and evade potential entrapments for the UGV, by carefully considering the position relationship between the UGV and the VO region. Additionally, a velocity resampling mechanism is further designed to prevent the UGV from being trapped. Above techniques augments the navigation flexibility and safety of the UGV, thereby significantly improves the success rate of practical navigation in dynamic and challenging pedestrian environments. Extensive simulations and real-world experiments have been conducted, especially the experiment in pedestrian-rich school cafeteria demonstrating satisfactory practicality of our approach. (Supplementary video link: https://youtu.be/xt4KosuPMYs)


  • LRAE: Large-Region-Aware Safe and Fast Autonomous Exploration of Ground Robots for Uneven Terrains

    by Qingchen Bi, Xuebo Zhang, Shiyong Zhang, Runhua Wang, Lun Li, Jing Yuan

    Ground robot autonomous exploration for uneven terrains is still challenging since the rugged terrain structures not only degrade the exploration performance but also threaten the navigation safety of the robot. In this letter, a novel exploration planner is proposed for safe and fast exploration in uneven terrains. To obtain high exploration efficiency, we propose a large-region-aware exploration route optimization strategy that prioritizes exploring large regions while also considering exploring nearby small regions. To safely and completely explore uneven terrains, our planner fully introduces traversability information to extract unknown regions and assess exploration safety levels. The safety levels are then integrated into the design of the exploration strategy to ensure safe robotic exploration. We validate our method in various challenging simulation scenes and real-world wild uneven terrains. The results show that our method can safely explore uneven terrains and improve exploration efficiency by up to 45.3% compared with state-of-the-art methods.


  • RH-ECBS: enhanced conflict-based search for MRPP with region heuristics

    by Zhangchao Pan, Runhua Wang, Qingchen Bi, Xuebo Zhang, Jingjin Yu

    This paper proposes a novel two-layer framework based on conflict-based search and regional divisions to improve the efficiency of multi-robot path planning. The high-level layer targets the reduction of conflicts and deadlocks, while the low-level layer is responsible for actual path planning. Distinct from previous dual-level search frameworks, the novelties of this work are (1) subdivision of planning regions for each robot to decrease the number of conflicts encountered during planning; (2) consideration of the number of robots in the region during planning in the node expansion stage of A*, and (3) formal proof demonstrating the nonzero probability of the proposed method in obtaining a solution, along with providing the upper bound of the solution in a special case. Experimental comparisons with Enhanced Conflict-Based Search demonstrate that the proposed method not only reduces the number of conflicts but also achieves a computation time reduction of over 30%.


  • TC$^{2}$LI-SLAM: A Tightly-Coupled Camera-LiDAR-Inertial SLAM System

    by Yunze Tong, Xuebo Zhang, Runhua Wang, Zhixing Song, Songyang Wu, Shiyong Zhang, Youwei Wang, Jing Yuan

    In this letter, we propose TC $^{2}$ LI-SLAM, a novel and tightly-coupled camera-LiDAR-inertial SLAM system with a separated front end and a unified back end. The front end accepts non-identical frequency inputs and performs real-time pose estimation while incorporating different inputs into keyframes for the back end, benefiting from our novel keyframe-oriented data synchronization method. To improve the accuracy of the back-end optimization, we innovatively leverage multi-sensor consecutive co-vision constraints in a keyframe-based local bundle adjustment problem. To bridge the gap between different residual terms from different sensors in the optimization problem, we propose a cross-modal residual standardization method that can be easily applied. Furthermore, the proposed system can degrade into TC $^{2}$ L-SLAM, a tightly-coupled camera-LiDAR SLAM system without IMU, to cope with situations where inertial measurements are not available or reliable. Finally, both TC $^{2}$ LI-SLAM and TC $^{2}$ L-SLAM are tested on public and self-recorded datasets. The results show their superior performance in terms of accuracy compared with the state-of-the-art SLAM systems, with at most 33% accuracy improvement over ORB-SLAM3 on the KITTI dataset.