基于Transformer的轮式里程计误差预测模型

doi:10.13229/j.cnki.jdxbgxb20221273

摘要/Abstract

摘要：

针对利用轮式里程计定位时会产生难以预测和多变误差的问题，提出了使用Transformer神经网络建立轮式里程计误差预测模型，以准确预测变化的里程误差，提高了轮式里程计的定位精度。首先，建立不考虑工况特征和考虑工况特征两种模型。然后，在多种工况下与LSTM模型进行对比实验，结果表明：在常规和挑战性工况下，本文模型相比LSTM模型具有更高的精度、稳定性和可靠性。同时，相比于不考虑工况特征，考虑工况特征能有效提高模型的整体性能。

关键词: 车辆工程, 自动驾驶, 定位, 轮式里程计, 深度学习, Transformer模型

Abstract:

To address the problem of unpredictable and variable errors when using wheel odometry for localization， a wheel odometry error prediction model based on Transformer neural network is developed to accurately predict the odometry error that accumulates and changes as the mileage increases， and to improve the accuracy of localization using wheel odometry under GPS occlusion. First， two models were established without and with the driving condition characteristics， then they were compared with the LSTM model under various driving conditions. The experimental results show that the Transformer-based wheel odometry error prediction model can accurately predict the odometry error with higher accuracy， stability and reliability than the LSTM model under both regular driving conditions and challenging driving conditions where it is difficult to measure the odometry signal accurately. At the same time， compared with the Transformer model without considering the driving condition characteristics， the Transformer model with considering the driving condition characteristics improve the performance in all evaluation indexes， which proves that considering the driving condition characteristics can effectively improve the prediction performance of the model.

Key words: vehicle engineering, autonomous driving, localization, wheel odometry, deep learning, Transformer model

中图分类号:

U469.79

何科,丁海涛,赖宣淇,许男,郭孔辉. 基于Transformer的轮式里程计误差预测模型[J]. 吉林大学学报(工学版), 2023, 53(3): 653-662.

Ke HE,Hai-tao DING,Xuan-qi LAI,Nan XU,Kong-hui GUO. Wheel odometry error prediction model based on transformer[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 653-662.

图/表 17

图1

图2

表1

图3

表2

表3

Transformer模型训练参数"

参数	IO-VNB数据子集
编码器和解码器个数 $N$	6
子层以及嵌入层的输出维度 $d m o d e l$	64
全连接层中间层层数 $d f f$	32
注意力头数 $h$	8
批量大小	32
训练次数Epochs	100
时间步长（滑动窗口）/s	11
随机失活比例 $D r o p o u t$	0
激活函数	ReLU

表3

表4

表5

Transformer参数调节过程"

	N	$d m o d e l$	$d f f$	h	Dropout	max	min	$μ$	$σ$
基准	6	64	32	8	0	1.99	0.03	0.55	0.48
A	6	64	32	4	0	2.11	0.03	0.63	0.50
A	6	64	32	16	0	2.06	0.02	0.60	0.49
B	4	64	32	8	0	2.02	0.04	0.62	0.47
B	8	64	32	8	0	2.10	0.04	0.73	0.53
C	6	32	32	8	0	2.00	0.03	0.66	0.49
C	6	128	32	8	0	1.97	0.03	0.54	0.46
D	6	64	16	8	0	2.02	0.04	0.74	0.50
D	6	64	64	8	0	1.98	0.02	0.58	0.46
E	6	64	32	8	0.1	1.99	0.03	0.83	0.52
E	6	64	32	8	0.2	2.00	0.07	0.82	0.46

表5

表6

高速公路工况的测试结果"

指标	LSTM模型误差/m	Transformer		模型误差
指标	LSTM模型误差/m	不考虑工况特征	提升/%	考虑工况特征	提升/%
$m a x$	0.68	0.70	-3	0.56	18
$m i n$	0.25	0.10	60	0.05	80
$μ$	0.46	0.34	26	0.30	35
$σ$	0.08	0.12	-50	0.15	-87.5

表6

图4

表7

车辆加速度快速变化的工况测试结果"

指标	LSTM模型误差/m	Transformer		模型误差/m
指标	LSTM模型误差/m	不考虑工况特征	提升/%	考虑工况特征	提升/%
$m a x$	2.95	2.00	32	1.99	33
$m i n$	0.54	0.08	85	0.05	91
$μ$	1.40	1.01	28	0.72	49
$σ$	0.79	0.52	34	0.55	30

表7

图5

表8

急刹车工况的测试结果"

指标	LSTM模型误差/m	Transformer		模型误差
指标	LSTM模型误差/m	不考虑工况特征	提升/%	考虑工况特征	提升/%
$m a x$	2.93	1.97	33	1.62	45
$m i n$	0.10	0.03	70	0.03	70
$μ$	1.22	0.70	43	0.23	81
$σ$	0.84	0.52	38	0.23	73

表8

图6

表9

湿/泥泞路面工况的测试结果"

指标	LSTM模型误差/m	Transformer		模型误差/m
指标	LSTM模型误差/m	不考虑工况特征	提升/%	考虑工况特征	提升/%
$m a x$	2.33	1.99	15	1.93	17
$m i n$	0.20	0.20	0	0.03	85
$μ$	0.66	0.64	3	0.58	12
$σ$	0.52	0.44	15	0.43	17

表9

图7

图8

参考文献 20

1	高振海,孙天骏,何磊. 汽车纵向自动驾驶的因果推理型决策[J]. 吉林大学学报: 工学版, 2019, 49(5): 1392-1404.
	Gao Zhen-hai, Sun Tian-jun, He Lei. Causal reasoning decision⁃making for vehicle longitudinal automatic driving[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49(5): 1392-1404.
2	Jo K, Kim J, Kim D, et al. Development of autonomous car—part I: distributed system architecture and development process[J]. IEEE Transactions on Industrial Electronics, 2014, 61(12): 7131-7140.
3	Lu W, Rodríguez F S A, Seignez E, et al. Lane marking-based vehicle localization using low-cost GPS and open source map[J]. Unmanned Systems, 2015, 3(4): 239-251.
4	Xu L H, Hu S G, Luo Q. A new lane departure warning algorithm considering the driver's behavior characteristics[J]. Mathematical Problems in Engineering, 2015(1): No.412126.
5	Levinson J, Montemerlo M, Thrun S. Map-based precision vehicle localization in urban environments[C]∥Robotics: Science and Systems, Atlanta, Georgia, USA, 2007: No.16.
6	秦晓辉, 王哲文, 庞涛, 等. 基于车辆模型紧耦合的封闭园区车辆定位方法[J]. 汽车工程,2021,43(9): 1328-1335.
	Qin Xiao-hui, Wang Zhe-wen, Pang Tao, et al. Vehicle positioning method based on tight coupling of vehicle model in enclosed environments[J]. Automotive Engineering, 2021, 43(9): 1328-1335.
7	Kubo N, Suzuki T. Performance improvement of RTK-GNSS with IMU and vehicle speed sensors in an urban environment[J]. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2016, 99(1): 217-224.
8	何永明, 陈世升, 冯佳, 等. 基于高精地图的超高速公路虚拟轨道系统[J/OL]. [2022-02-15].
9	Funk N, Alatur N, Deuber R, et al. Autonomous electric race car design[J/OL]. [2022-08-26].
10	Schwesinger U, Bürki M, Timpner J, et al. Automated valet parking and charging for e-mobility[C]∥2016 IEEE Intelligent Vehicles Symposium (IV), Gothenburg, Sweden, 2016: 157-164.
11	Schanz A, Spieker A, Kuhnert K D. Autonomous parking in subterranean garages-a look at the position estimation[C]∥IEEE IV2003 Intelligent Vehicles Symposium, OH, USA, 2003: 253-258.
12	Malleswaran M, Vaidehi V, Manjula S, et al. Performance comparison of HONNs and FFNNs in GPS and INS integration for vehicular navigation[C]∥2011 International Conference on Recent Trends in Information Technology (ICRTIT), Chennai, India, 2011: 223-228.
13	Malleswaran M, Vaidehi V, Saravanaselvan A, et al. Performance analysis of various artificial intelligent neural networks for GPS/INS integration[J]. Applied Artificial Intelligence, 2013, 27(5): 367-407.
14	Dai H, Bian H, Wang R, et al. An INS/GNSS integrated navigation in GNSS denied environment using recurrent neural network[J]. Defence Technology, 2020, 16(2): 334-340.
15	Fang W, Jiang J, Lu S, et al. A LSTM algorithm estimating pseudo measurements for aiding INS during GNSS signal outages[J]. Remote Sensing, 2020, 12(2): No.256.
16	Onyekpe U, Palade V, Kanarachos S, et al. Learning uncertainties in wheel odometry for vehicular localisation in GNSS deprived environments[C]∥2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA, 2020: 741-746.
17	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J/OL]. [2022-09-28].
18	Onyekpe U, Kanarachos S, Palade V, et al. Vehicular localisation at high and low estimation rates during gnss outages: a deep learning approach[J]. Deep Learning Applications, 2021,2: 237-256.
19	Onyekpe U, Palade V, Kanarachos S, et al. IO-VNBD: inertial and odometry benchmark dataset for ground vehicle positioning[J]. Data in Brief, 2021, 35: No.106885.
20	Onyekpe U, Palade V, Kanarachos S. Learning to localise automated vehicles in challenging environments using Inertial Navigation Systems (INS)[J]. Applied Sciences, 2021, 11(3): No.1270.

相关文章 15

[1]	王登峰,陈宏利,那景新,陈鑫. 单双搭接接头经高温老化后的失效对比[J]. 吉林大学学报(工学版), 2023, 53(2): 346-354.
[2]	张佩,王志伟,杜常清,颜伏伍,卢炽华. 车用质子交换膜燃料电池空气系统过氧比控制方法[J]. 吉林大学学报(工学版), 2022, 52(9): 1996-2003.
[3]	王克勇,鲍大同,周苏. 基于数据驱动的车用燃料电池故障在线自适应诊断算法[J]. 吉林大学学报(工学版), 2022, 52(9): 2107-2118.
[4]	曹起铭,闵海涛,孙维毅,于远彬,蒋俊宇. 质子交换膜燃料电池低温启动水热平衡特性[J]. 吉林大学学报(工学版), 2022, 52(9): 2139-2146.
[5]	隗海林,王泽钊,张家祯,刘洋. 基于Avl-Cruise的燃料电池汽车传动比及能量管理策略[J]. 吉林大学学报(工学版), 2022, 52(9): 2119-2129.
[6]	刘岩,丁天威,王宇鹏,都京,赵洪辉. 基于自适应控制的燃料电池发动机热管理策略[J]. 吉林大学学报(工学版), 2022, 52(9): 2168-2174.
[7]	高金武,贾志桓,王向阳,邢浩. 基于PSO-LSTM的质子交换膜燃料电池退化趋势预测[J]. 吉林大学学报(工学版), 2022, 52(9): 2192-2202.
[8]	李丞,景浩,胡广地,刘晓东,冯彪. 适用于质子交换膜燃料电池系统的高阶滑模观测器[J]. 吉林大学学报(工学版), 2022, 52(9): 2203-2212.
[9]	池训逞,侯中军,魏伟,夏增刚,庄琳琳,郭荣. 基于模型的质子交换膜燃料电池系统阳极气体浓度估计技术综述[J]. 吉林大学学报(工学版), 2022, 52(9): 1957-1970.
[10]	裴尧旺,陈凤祥,胡哲,翟双,裴冯来,张卫东,焦杰然. 基于自适应LQR控制的质子交换膜燃料电池热管理系统温度控制[J]. 吉林大学学报(工学版), 2022, 52(9): 2014-2024.
[11]	胡广地,景浩,李丞,冯彪,刘晓东. 基于高阶燃料电池模型的多目标滑模控制[J]. 吉林大学学报(工学版), 2022, 52(9): 2182-2191.
[12]	陈凤祥,伍琪,李元松,莫天德,李煜,黄李平,苏建红,张卫东. 2.5吨燃料电池混合动力叉车匹配、仿真及优化[J]. 吉林大学学报(工学版), 2022, 52(9): 2044-2054.
[13]	武小花,余忠伟,朱张玲,高新梅. 燃料电池公交车模糊能量管理策略[J]. 吉林大学学报(工学版), 2022, 52(9): 2077-2084.
[14]	高青,王浩东,刘玉彬,金石,陈宇. 动力电池应急冷却喷射模式实验分析[J]. 吉林大学学报(工学版), 2022, 52(8): 1733-1740.
[15]	王奎洋,何仁. 基于支持向量机的制动意图识别方法[J]. 吉林大学学报(工学版), 2022, 52(8): 1770-1776.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

特征序号	描述	特征序号	描述
1	里程	17	急刹车
2	环岛	18	左右急转弯
3	山路	19	换挡
4	乡村道路	20	打滑
5	高速公路	21	连续左右转
6	市中心	22	短时间加速度快速变化
7	市区内	23	U-turn
8	蜿蜒道路	24	倒车
9	住宅小区	25	漂移
10	山谷	26	碰撞
11	雨	27	Z字形行驶
12	土路	28	近似直线的行驶
13	碎石路	29	静止
14	潮湿道路	30	停车
15	泥路	31	里程误差
16	坑洞

序号	IO-VNB数据子集	序号	IO-VNB数据子集
1	V-Vta1a	14	V-Vtb1
2	V-Vta2	15	V-Vtb2
3	V-Vta8	16	V-Vtb3
4	V-Vta10	17	V-Vtb5
5	V-Vta16	18	V-Vw4
6	V-Vta17	19	V-Vw5
7	V-Vta20	20	V-Vw14b
8	V-Vta21	21	V-Vw14c
9	V-Vta22	22	V-Vfa01
10	V-Vta27	23	V-Vfa02
11	V-Vta28	24	V-Vfb01a
12	V-Vta29	25	V-Vfb01b
13	V-Vta30	26	V-Vfb02b

场景	IO-VNB数据子集	行驶总时间/min	行驶距离/km	速度/（km·h^-1）	加速度/（9.8 m·s^-2）
高速公路	V-Vw12	1.75	2.64	82.6~97.4	-0.06~0.07
加速度快速变化	V-Vfb02e	1.6	1.52	37.4~73.9	-0.24~0.19
加速度快速变化	V-Vta12	1.1	1.27	44.7~85.3	-0.44~0.13
急刹车	V-Vw16b	2.0	1.99	1.3~86.3	-0.75~0.29
	V-Vw17	0.5	0.54	31.5~72.7	-0.8~0.19
	V-Vta9	0.4	0.43	48.9~87.7	-0.6~0.14
湿/泥泞路面	V-Vtb8	1.2	1.35	60.9~76.5	-0.35~0.08
	V-Vtb11	0.7	0.84	5.1~75.3	-0.05~0.12
	V-Vtb13	2.1	0.99	7.5~43.3	-0.31~0.22