履带平台无人驾驶系统基于语义信息的模块串联方法

doi:10.12382/bgxb.2021.0832

摘要/Abstract

摘要： 为提高无人履带平台在复杂越野环境下的通行能力，提出一种通过语义信息串联无人驾驶系统中环境感知、运动规划、运动控制模块的方法。环境感知模块通过相机与激光雷达的融合感知方法，利用图像语义信息与激光雷达点云特征，结合平台通过性几何参数，对环境中可通行区域进行粗提取，之后在可通行区域利用高斯聚类模型对环境进行精细的可通行度分析，最终生成具有不同通行度语义信息的三维栅格地图；运动规划模块在考虑平台运动学模型、动力学约束以及平滑过渡约束的基础上,结合地形与道路表面属性生成行为运动基元，通过对基元的分层式在线选择生成具有行为语义的轨迹；运动控制模块基于模型预测控制算法充分考虑平台驱动电机的执行能力、跟踪偏差以及控制稳定性，借助运动规划给出的行为运动基元语义属性，对控制目标函数权重系数进行实时更新，减小轨迹跟踪的横向误差，航向误差以及速度误差。最终利用中型混合动力无人履带平台进行了实车验证，结果表明：所提运动规划方法结果相较于基于平面二值栅格地图规划的轨迹在平均俯仰角、平均侧倾角、平均曲率分别降低46.1%、46.5%、14.2%；所提出基于行为语义轨迹变参数运动控制方法相较于定参数的运动控制方法分别在横向偏差、航向偏差、速度偏差降低17.1%、2.7%、6.1%。

关键词: 履带平台, 无人驾驶系统, 语义信息, 三维栅格地图, 行为运动基元, 模型预测控制

Abstract: To improve the performance of unmanned tracked platforms in complex off-road environment, this study proposes a semantic information-based method to integrate the environment perception, motion planning and motion control modules of the unmanned system. Through the fusion perception method of camera and lidar, image semantic information and lidar point cloud features are obtained by the environment perception module, and then the traversable area is roughly determined by combining geometric parameters of the platform. Finally, a three-dimensional grid map with different traversability information is generated, after the Gaussian clustering model is used to conduct a fine traversability analysis of the environment in the traversable area. Platform kinematics and dynamic constraints are considered in the motion planning module. On the basis of smooth transition constraints, terrain and road surface attributes are taken into account to generate behavior motion primitives, and the trajectories with behavior semantics are generated using hierarchical online selection of primitives. The motion control module is based on model predictive control which considers the execution ability, tracking deviation, and control stability of the platform drive motor. Based on the semantic attributes of the behavior motion primitives provided by motion planning, the weight coefficient of the control objective function is updated in real time to reduce lateral deviation, heading deviation, and speed deviation of trajectory tracking. Finally, the medium-sized hybrid unmanned tracked platform is used for verification. The results show that the motion planning method proposed in this paper are 46.1%, 46.5% and 14.2% lower in average pitch angle, average roll angle and average curvature than the trajectory planning result using the plane binary grid map. Compared with the motion control method with fixed parameters, the proposed variable-parameter motion control method based on behavior semantic trajectory reduces the lateral deviation, heading deviation, and speed deviation by 17.1%, 2.7% and 6.1%, respectively.

Key words: trackedplatform, unmanneddrivingsystem, semanticinformation, three-dimensionalgridmap, behaviormotionprimitive, modelpredictivecontrol

中图分类号:

TG810.2

陈慧岩, 关海杰, 刘海鸥, 龚建伟, 吴贺禹. 履带平台无人驾驶系统基于语义信息的模块串联方法[J]. 兵工学报, 2022, 43(11): 2705-2716.

CHEN Huiyan, GUAN Haijie, LIU Hai'ou, GONG Jianwei, WU Heyu. A Semantic Information-based Module Series Method for Unmanned Tracked Driving Systems[J]. Acta Armamentarii, 2022, 43(11): 2705-2716.

参考文献

［1］陈慧岩, 张玉. 军用地面无人机动平台技术发展综述[J]. 兵工学报,2014,35(10):1696-1706.
CHEN H Y, ZHANG Y. An overview of research on military unmanned ground vehicles[J]. Acta Armamentarii, 2014, 35(10): 1696-1706. (in Chinese)
[2] 邢志伟, 朱晓蕊, 何超. 基于行人行为学习的机器人同时定位与可通行区域制图[J]. 机械工程学报, 2019, 55(11): 36- 45.
XING Z W, ZHU X R, HE C. Simultaneous localization and traversable region mapping based on pedestrian behavior learning[J]. Journal of Mechanical Engineering, 2019, 55(11): 36-45. (in Chinese)
[3] QI C R, SU H, MO K, et al. PointNet: deep learning on point sets for 3D classification and segmentation[C]∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, US: IEEE, 2017: 77-85.
[4] GAO B, PAN Y C, LI C K, et al. Are we hungry for 3D LiDAR data for semantic segmentation? a survey of datasets and methods[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(7): 6063-6081.
[5] GAO B, HU S C, ZHAO X J, et al. Fine-grained off-road semantic segmentation and mapping via contrastive learning[C]∥Proceedings of the International Conference on Intelligent Robots and Systems(IROS 2021). Prague, Czech: IEEE, 2021: 5950-5957.
[6] ZHANG Y, CHEN H Y, WASLANDER S, et al. Hybrid trajectory planning for autonomous driving in highly con-strained environments[J]. IEEE Access, 2018, 6: 32800-32819.
[7] 杜广泽, 张旭东, 邹渊，等. 非结构道路场景下轮式无人车辆避障算法[J]. 兵工学报, 2020, 41(10): 2096-2105.
DU G Z，ZHANG X D，ZOU Y，et al. Obstacle avoidance algorithm for autonomous wheeled vehicle in unstructured environments[J]. Acta Armamentarii, 2020, 41(10): 2096-2105. (in Chinese)
[8] THORESEN M, NIELSE N H, MATHIASSEN K, et al. Path planning for UGVs based on traversability hybrid A^*[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 1216-1223.
[9] 田洪清, 王建强, 黄荷叶, 等. 越野环境下基于势能场模型的智能车概率图路径规划方法[J]. 兵工学报, 2021, 42(7): 1496-1505.
TIAN H Q, WANG J Q, HUANG H Y, et al. Probabilistic roadmap method for path planning of intelligent vehicle based on artificial potential field model in off-road environment [J]. Acta Armamentarii, 2021, 42(7): 1496-1505. (in Chinese)
[10] UGUR D, BEBEK O. Fast and efficient terrain-aware motion planning for exploration rovers[C]∥Proceedings of the 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE). Lyon, France: IEEE, 2021: 1561-1567.
[11] KRSI P, FURGALE P, BOSSE M, et al. Driving on point clouds: motion planning, trajectory optimization, and terrain assessment in generic nonplanar environments[J]. Journal of Field Robotics, 2017, 34 (5): 940-984.
[12] FABIAN S, KOHLBRECHER S, VON STRYK O. Pose Prediction for Mobile Ground Robots in Uneven Terrain Based on Difference of Heightmaps[C]∥Proceedings of the 2020 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR). Abu Dhabi, United Arab Emirates: IEEE: 2020: 49-56.
[13] 胡家铭, 胡宇辉, 陈慧岩, 等. 基于模型预测控制的无人驾驶履带车辆轨迹跟踪方法研究[J]. 兵工学报, 2019, 40(3): 456-463.
HU J M, HU Y H, CHEN H Y, et al. Research on trajectory tracking of unmanned tracked vehicles based on model predictive control[J]. Acta Armamentarii, 2019, 40(3): 456-463. (in Chinese)
[14] 王威, 陈慧岩, 马建昊, 等. 基于Frenet坐标系和控制延时补偿的智能车辆路径跟踪[J]. 兵工学报, 2019, 40(11): 2336-2351.
WANG W, CHEN H Y, MA J H, et al. Path tracking for intelligent vehicles based on frenet coordinates and delayed control[J]. Acta Armamentarii, 2019, 40(11): 2336-2351. (in Chinese)
[15] HE H, SHI M, LI J, et al. Design and experiential test of a model predictive path following control with adaptive preview for autonomous buses[J]. Mechanical Systems and Signal Processing, 2021, 157(99): 107701.
[16] 王博洋, 龚建伟, 熊光明, 等. 有级转向履带车辆的驾驶员操控行为模型[J]. 兵工学报, 2020, 41(12): 2379-2388.
WANG B Y, GONG J W, XIONG G M, et al. Driver control behavior model for tracked vehicle with stepped steering mechanism[J]. Acta Armamentarii, 2020, 41(12): 2379-2388. (in Chinese)
[17] YU C Q, GAO C X, WANG J B, et al. Bisenet V2: bilateral network with guided aggregation for real-time semantic segmentation[J]. International Journal of Computer Vision, 2021, 129(11): 3051-3068.
[18] JI K J, CHEN H Y, DI H J, et al.CPFG-SLAM: a robust simultaneous localization and mapping based on LIDAR in off-road environment[C]∥Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV 2018). Changshu, China: IEEE, 2018: 650-655.
[19] 曾根, 王伟达, 盖江涛, 等. 双侧电机耦合驱动履带车辆斜坡转向控制策略[J]. 兵工学报，2021, 42(10):2189-2195.
ZENG G, WANG W D, GAI J T, et al. Steering on ramp control strategy of double motor coupling drive transmission for tracked vehicle[J]. Acta Armamentarii, 2021, 42(10): 2189-2195. (in Chinese)
[20] WU M Z, JIN H, TANG B, et al. Constructing Topological Road Network of Wild Environment using Google Earth Pro[C]∥Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference (ITSC 2019). Auckland, New Zealand: IEEE, 2019: 2095-2100.
[21] YANG T, XIONG G M, ZHANG Y, et al.A practical planning framework and its implementation for autonomous navigation in off-road environment[C]∥Proceedings of the 2019 IEEE Intelligent Vehicles Symposium. Paris, France: IEEE, 2019: 1571-1576.

[1]	周球，周悦，孙洪鸣，郭威，吴凯，兰彦军. 深海着陆车路径规划及跟踪控制方法[J]. 兵工学报, 2023, 44(1): 298-306.
[2]	唐泽月，刘海鸥，薛明轩，陈慧岩，龚小杰，陶俊峰. 基于MPC-MFAC的双侧独立电驱动无人履带车辆轨迹跟踪控制[J]. 兵工学报, 2023, 44(1): 129-139.
[3]	宋佳睿，陶刚，李德润，臧政，吴绍斌，龚建伟. 参数自优化的有人与无人车辆编队鲁棒模型预测控制[J]. 兵工学报, 2023, 44(1): 84-97.
[4]	刘庆霄，唐泽月，张超朋，刘海鸥，陈慧岩. 基于高斯混合-隐半马尔可夫模型的双侧独立电驱动无人履带机动平台纵向决策方法[J]. 兵工学报, 2022, 43(8): 1733-1743.
[5]	马广原，陈慧岩. 无人履带平台发动机控制技术[J]. 兵工学报, 2022, 43(11): 2717-2726.
[6]	周梦如，陈慧岩，熊光明，关海杰，刘庆霄. 越野环境下无人履带平台的道路可通行性分析[J]. 兵工学报, 2022, 43(10): 2485-2496.
[7]	陈路明，廖自力，马晓军，刘春光. 基于分层控制的混合动力车辆实时能量管理策略[J]. 兵工学报, 2021, 42(8): 1580-1591.
[8]	刘聪，刘辉，韩立金，陈科. 分布式电驱动车辆极限越野环境下高速避障与稳定性控制[J]. 兵工学报, 2021, 42(10): 2102-2113.
[9]	王志福，白金，黄康伦，王军，王阳，梁常春，王瑞. 基于模型预测控制的轮毂电机驱动车辆防侧翻控制[J]. 兵工学报, 2021, 42(1): 11-25.
[10]	邓海鹏，麻斌，赵海光，吕良，刘宇. 自主驾驶车辆紧急避障的路径规划与轨迹跟踪控制[J]. 兵工学报, 2020, 41(3): 585-594.
[11]	胡家铭，胡宇辉，陈慧岩，刘凯. 基于模型预测控制的无人驾驶履带车辆轨迹跟踪方法研究[J]. 兵工学报, 2019, 40(3): 456-463.
[12]	王威，陈慧岩，马建昊，刘凯，龚建伟. 基于Frenet坐标系和控制延时补偿的智能车辆路径跟踪[J]. 兵工学报, 2019, 40(11): 2336-2351.
[13]	修观，王良明₁，孙瑞胜₁，杨荣军₁. 一种快速非线性模型预测控制律研究[J]. 兵工学报, 2011, 32(10): 1189-1194.