赵丰 . 基于路面感知的车辆智能悬架控制策略研究 [D ] . 北京 : 北京理工大学 , 2016 .

ZHAO F . Controlstrategy of intelligent vehicle suspension system based on the perception of the road [D ] . Beijing : Beijing Institute of Technology , 2016 . (in Chinese)

郝胜强 . 复杂道路工况下重型越野车辆AMT换挡策略优化 [D ] . 北京 : 北京理工大学 , 2018 .

HAO S Q . The shift strategy optimization of AMT heavy off-road vehicles under complex road conditions [D ] . Beijing : Beijing Institute of Technology , 2018 . (in Chinese)

邹家祥 . 野外机器人的地形识别与自然场景分割 [D ] . 济南 : 山东大学 , 2019 .

ZHOU J X . Terrain classification and natural scene segmentation in field robot [D ] . Jinan : Shandong University , 2019 . (in Chinese)

王振宇 . 基于计算机视觉的半主动悬架预瞄控制研究 [D ] . 北京 : 北京理工大学 , 2019 .

WANG Z Y . Research on semi-active suspension system preview control based on computer vision [D ] . Beijing : Beijing Institute of Technology , 2019 . (in Chinese)

DEWANGAN D K , SAHU S P . RCNet: road classification convolutional neural networks for intelligent vehicle system [J ] . Intelligent Service Robotics , 2021 , 14 ( 2 ): 199 - 214 . DOI: 10.1007/s11370-020-00343-6 http://doi.org/10.1007/s11370-020-00343-6

ŠABANOVIC E , ZURAULIS V , PRENTKOVSKIS O , et al. Identification of road-surface type using deep neural networks for friction coefficient estimation [J ] . Sensors , 2020 , 20 ( 3 ): 612 . DOI: 10.3390/s20030612 http://doi.org/10.3390/s20030612 https://www.mdpi.com/1424-8220/20/3/612 https://www.mdpi.com/1424-8220/20/3/612 Nowadays, vehicles have advanced driver-assistance systems which help to improve vehicle safety and save the lives of drivers, passengers and pedestrians. Identification of the road-surface type and condition in real time using a video image sensor, can increase the effectiveness of such systems significantly, especially when adapting it for braking and stability-related solutions. This paper contributes to the development of the new efficient engineering solution aimed at improving vehicle dynamics control via the anti-lock braking system (ABS) by estimating friction coefficient using video data. The experimental research on three different road surface types in dry and wet conditions has been carried out and braking performance was established with a car mathematical model (MM). Testing of a deep neural networks (DNN)-based road-surface and conditions classification algorithm revealed that this is the most promising approach for this task. The research has shown that the proposed solution increases the performance of ABS with a rule-based control strategy.

WANG W L , ZHANG B T , WU K Q , et al. A visual terrain classification method for mobile robots’ navigation based on convolutional neural network and support vector machine [J ] . Transactions of the Institute of Measurement and Control , 2022 , 44 ( 4 ): 744 - 753 . DOI: 10.1177/0142331220987917 http://doi.org/10.1177/0142331220987917 http://journals.sagepub.com/doi/10.1177/0142331220987917 http://journals.sagepub.com/doi/10.1177/0142331220987917 In this paper, a hybrid method based on deep learning is proposed to visually classify terrains encountered by mobile robots. Considering the limited computing resource on mobile robots and the requirement for high classification accuracy, the proposed hybrid method combines a convolutional neural network with a support vector machine to keep a high classification accuracy while improve work efficiency. The key idea is that the convolutional neural network is used to finish a multi-class classification and simultaneously the support vector machine is used to make a two-class classification. The two-class classification performed by the support vector machine is aimed at one kind of terrain that users are mostly concerned with. Results of the two classifications will be consolidated to get the final classification result. The convolutional neural network used in this method is modified for the on-board usage of mobile robots. In order to enhance efficiency, the convolutional neural network has a simple architecture. The convolutional neural network and the support vector machine are trained and tested by using RGB images of six kinds of common terrains. Experimental results demonstrate that this method can help robots classify terrains accurately and efficiently. Therefore, the proposed method has a significant potential for being applied to the on-board usage of mobile robots.

王志红 , 王少博 , 颜莉蓉 , 等 . 基于语义分割模型的路面类型识别技术研究 [J ] . 公路交通科技 , 2021 , 38 ( 1 ): 128 - 134 . DOI: 10.3969/j.issn.1002-0268.2021.01.016 http://doi.org/10.3969/j.issn.1002-0268.2021.01.016 在极端恶劣天气条件下，车辆能够及时根据路况信息调整车速和车距，将有效地减少交通事故的发生。道路类型和路面附着系数是影响路况的主要因素，传统的路面附着系数识别方法具有成本高、可靠性低的特点。同时基于机器视觉的路面信息识别技术已经成为当前研究的热点，但是精度低和鲁棒性差一直是研究的难点。将机器视觉中较为流行的语义分割模型作为基础模型，同时改进模型输出网络，提出一种新的路面类型识别技术。根据现有文献将车辆行驶路面分为以下9类，包括湿沥青路面、干沥青路面、湿混凝土路面、干混凝土路面、湿土路面、干土路面、砾石路面、压实雪地路面和结冰路面。通过拍照、下载等多种途径收集路面图片制作标准数据集，使用预处理的数据集训练改进后的语义分割网络模型。通过多次试验，选取达到预期效果的训练参数进行模型参数固化，使用固化后的语义分割模型对摄像头获取的路面图片进行预测。根据模型预测结果得到当前行驶路面的类别。大量的道路图片测试结果表明，9种道路类型的平均分类精度为94%左右，有效的提升了目前道路类型的识别精度和鲁棒性；在特定试验平台中的单张图片预测时间约为0.028 6 s，满足实时性要求。

WANG Z H , WANG S B , YAN L R , et al. Pavement type recognition based on semantic segmentation model [J ] . Journal of Highway and Transportation Research and Development , 2021 , 38 ( 1 ): 128 - 134 . (in Chinese)

LIU J , WANG B Y , LIU H O , et al. Slip Estimation for autonomous tracked vehicles via machine learning [C ] ∥Proceedings of 2021 IEEE Intelligent Vehicles Symposium(IV).Nagoya, Japan:IEEE , 2021 : 1 - 98 .

WANG S F , KODAGODA S , SHI L , et al. Road-terrain classification for land vehicles:employing an acceleration-based approach [J ] . IEEE Vehicular Technology Magazine , 2017 , 12 ( 3 ): 34 - 41 . DOI: 10.1109/MVT.2017.2656949 http://doi.org/10.1109/MVT.2017.2656949 http://ieeexplore.ieee.org/document/7994646/ http://ieeexplore.ieee.org/document/7994646/

BAI C C , GUO J F , ZHENG H X . Three-dimensional vibration-based terrain classification for mobile robots [J ] . IEEE Access , 2019 , 7 : 63485 - 63492 . DOI: 10.1109/Access.6287639 http://doi.org/10.1109/Access.6287639 https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639

BAI C C , GUO J F , GUO L L , et al. Deep multi-layer perception based terrain classification for planetary exploration rovers [J ] . Sensors , 2019 , 19 ( 14 ): 3102 . DOI: 10.3390/s19143102 http://doi.org/10.3390/s19143102 https://www.mdpi.com/1424-8220/19/14/3102 https://www.mdpi.com/1424-8220/19/14/3102 Accurate classification and identification of the detected terrain is the basis for the long-distance patrol mission of the planetary rover. But terrain measurement based on vision and radar is subject to conditions such as light changes and dust storms. In this paper, under the premise of not increasing the sensor load of the existing rover, a terrain classification and recognition method based on vibration is proposed. Firstly, the time-frequency domain transformation of vibration information is realized by fast Fourier transform (FFT), and the characteristic representation of vibration information is given. Secondly, a deep neural network based on multi-layer perception is designed to realize classification of different terrains. Finally, combined with the Jackal unmanned vehicle platform, the XQ unmanned vehicle platform, and the vibration sensor, the terrain classification comparison test based on five different terrains was completed. The results show that the proposed algorithm has higher classification accuracy, and different platforms and running speeds have certain influence on the terrain classification at the same time, which provides support for subsequent practical applications.

WANG M M , YE L , SUN X Y . Adaptive online terrain classification method for mobile robot based on vibration signals [J ] . International Journal of Advanced Robotic Systems , 2021 , 18 ( 6 ):17298814211062035.

SKOCZYLAS A , STACHOWIAK M , STEFANIAK P , et al. Terrain classification using neural network based on inertial sensors for wheeled robot [C ] ∥Proceedings of Asian Conference on Intelligent Information and Database Systems.Phuket, Thailand:Springer , 2021 : 429 - 440 .

CHENG C , CHANG J , LÜ W , et al. Frequency-temporal disagreement adaptation for robotic terrain classification via vibration in a dynamic environment [J ] . Sensors , 2020 , 20 ( 22 ): 6550 . DOI: 10.3390/s20226550 http://doi.org/10.3390/s20226550 https://www.mdpi.com/1424-8220/20/22/6550 https://www.mdpi.com/1424-8220/20/22/6550 The accurate terrain classification in real time is of great importance to an autonomous robot working in field, because the robot could avoid non-geometric hazards, adjust control scheme, or improve localization accuracy, with the aid of terrain classification. In this paper, we investigate the vibration-based terrain classification (VTC) in a dynamic environment, and propose a novel learning framework, named DyVTC, which tackles online-collected unlabeled data with concept drift. In the DyVTC framework, the exterior disagreement (ex-disagreement) and interior disagreement (in-disagreement) are proposed novely based on the feature diversity and intrinsic temporal correlation, respectively. Such a disagreement mechanism is utilized to design a pseudo-labeling algorithm, which shows its compelling advantages in extracting key samples and labeling; and consequently, the classification accuracy could be retrieved by incremental learning in a changing environment. Since two sets of features are extracted from frequency and time domain to generate disagreements, we also name the proposed method feature-temporal disagreement adaptation (FTDA). The real-world experiment shows that the proposed DyVTC could reach an accuracy of 89.5%, but the traditional time- and frequency-domain terrain classification methods could only reach 48.8% and 71.5%, respectively, in a dynamic environment.

SHI W , LI Z , LÜ W , et al. Laplacian support vector machine for vibration-based robotic terrain classification [J ] . Electronics , 2020 , 9 ( 3 ): 513 . DOI: 10.3390/electronics9030513 http://doi.org/10.3390/electronics9030513 https://www.mdpi.com/2079-9292/9/3/513 https://www.mdpi.com/2079-9292/9/3/513 The achievement of robot autonomy has environmental perception as a prerequisite. The hazards rendered from uneven, soft and slippery terrains, which are generally named non-geometric hazards, are another potential threat reducing the traversing efficient, and therefore receiving more and more attention from the robotics community. In the paper, the vibration-based terrain classification (VTC) is investigated by taking a very practical issue, i.e., lack of labels, into consideration. According to the intrinsic temporal correlation existing in the sampled terrain sequence, a modified Laplacian SVM is proposed to utilise the unlabelled data to improve the classification performance. To the best of our knowledge, this is the first paper studying semi-supervised learning problem in robotic terrain classification. The experiment demonstrates that: (1) supervised learning (SVM) achieves a relatively low classification accuracy if given insufficient labels; (2) feature-space homogeneity based semi-supervised learning (traditional Laplacian SVM) cannot improve supervised learning’s accuracy, and even makes it worse; (3) feature- and temporal-space based semi-supervised learning (modified Laplacian SVM), which is proposed in the paper, could increase the classification accuracy very significantly.

ANDRADES I S , CASTILLO AGUILAR J J , GARCíA J M V , et al. Low-cost road-surface classification system based on self-organizing maps [J ] . Sensors , 2020 , 20 ( 21 ): 6009 . DOI: 10.3390/s20216009 http://doi.org/10.3390/s20216009 https://www.mdpi.com/1424-8220/20/21/6009 https://www.mdpi.com/1424-8220/20/21/6009 Expanding the performance and autonomous-decision capability of driver-assistance systems is critical in today’s automotive engineering industry to help drivers and reduce accident incidence. It is essential to provide vehicles with the necessary perception systems, but without creating a prohibitively expensive product. In this area, the continuous and precise estimation of a road surface on which a vehicle moves is vital for many systems. This paper proposes a low-cost approach to solve this issue. The developed algorithm resorts to analysis of vibrations generated by the tyre-rolling movement to classify road surfaces, which allows for optimizing vehicular-safety-system performance. The signal is analyzed by means of machine-learning techniques, and the classification and estimation of the surface are carried out with the use of a self-organizing-map (SOM) algorithm. Real recordings of the vibration produced by tyre rolling on six different types of surface were used to generate the model. The efficiency of the proposed model (88.54%) and its speed of execution were compared with those of other classifiers in order to evaluate its performance.

王世峰 , 都凯悦 , 孟颖 , 等 . 基于机器学习的车辆路面类型识别技术研究 [J ] . 兵工学报 , 2017 , 38 ( 8 ): 1642 - 1648 . DOI: 10.3969/j.issn.1000-1093.2017.08.023 http://doi.org/10.3969/j.issn.1000-1093.2017.08.023 当车辆在各种不同的路面上行驶时，获知路面类型信息将有助于提高乘车人的安全性和舒适性，不同的路面类型将对车辆的加速、制动及操控等驾驶策略产生影响。基于机器学习的基本原理，提出一种使用加速度传感器和相机特征数据融合对路面类型进行分类的方法，并与单独使用其中一种传感器进行了比较。使用垂直加速度和车速数据并利用车辆动态模型还原路面轮廓，进而完成特征提取和路面类型分类；对相机采集的路面图像数据进行特征提取和分类；将两类传感器的数据特征进行融合，完成路面类型识别任务。实验结果表明：使用两种传感器数据特征融合的方法，不但识别精度有所提高，而且其可靠性和适应性也都优于单独使用加速度数据或路面图像数据。

WANG S F , DOU K Y , MENG Y , et al. Machine learning-based road terrain recognition for land vehicles [J ] . Acta Armamentarii , 2017 , 38 ( 8 ): 1642 - 1648 . (in Chinese)

DIMASTROGIOVANNI M , CORDES F , REINA G . Terrain estimation for planetary exploration robots [J ] . Applied Sciences , 2020 , 10 ( 17 ): 6044 . DOI: 10.3390/app10176044 http://doi.org/10.3390/app10176044 https://www.mdpi.com/2076-3417/10/17/6044 https://www.mdpi.com/2076-3417/10/17/6044 A planetary exploration rover’s ability to detect the type of supporting surface is critical to the successful accomplishment of the planned task, especially for long-range and long-duration missions. This paper presents a general approach to endow a robot with the ability to sense the terrain being traversed. It relies on the estimation of motion states and physical variables pertaining to the interaction of the vehicle with the environment. First, a comprehensive proprioceptive feature set is investigated to evaluate the informative content and the ability to gather terrain properties. Then, a terrain classifier is developed grounded on Support Vector Machine (SVM) and that uses an optimal proprioceptive feature set. Following this rationale, episodes of high slippage can be also treated as a particular terrain type and detected via a dedicated classifier. The proposed approach is tested and demonstrated in the field using SherpaTT rover, property of DFKI (German Research Center for Artificial Intelligence), that uses an active suspension system to adapt to terrain unevenness.

BONFITTO A , FERACO S , TONOLI A , et al. Combined regression and classification artificial neural networks for sideslip angle estimation and road condition identification [J ] . Vehicle System Dynamics , 2020 , 58 ( 11 ): 1766 - 1787 . DOI: 10.1080/00423114.2019.1645860 http://doi.org/10.1080/00423114.2019.1645860 https://www.tandfonline.com/doi/full/10.1080/00423114.2019.1645860 https://www.tandfonline.com/doi/full/10.1080/00423114.2019.1645860

SANDLER M , HOWARD A , ZHU M L , et al. MobileNetV2:inverted residuals and linear bottlenecks [C ] ∥Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,US:IEEE , 2018 : 4510 - 4520 .

MARSLAND S . Machine learning: an algorithmic perspective [M ] . New York,NY , US : Chapman and Hall/CRC , 2011 : 119 - 130 .

BREIMAN L , FRIEDMAN J H , OLSHEN R A , et al. Classification and regression trees [M ] .Boca Raton,FL, US:Routledge , 2017 : 23 - 48 .

BREIMAN L . Bagging predictors [J ] . Machine Learning , 1996 , 24 ( 2 ): 123 - 140 .

BREIMAN L . Random forests [J ] . Machine Learning , 2001 , 45 ( 1 ): 5 - 32 . DOI: 10.1023/A:1010933404324 http://doi.org/10.1023/A:1010933404324 http://link.springer.com/10.1023/A:1010933404324 http://link.springer.com/10.1023/A:1010933404324