Abstract
Efficient detection of performance limits is critical to autonomous driving. As autonomous driving is difficult to be realized under complicated scenarios, an improved genetic algorithm-based evolution test is proposed to accelerate the evaluation of performance limits. It conducts crossover operation at all positions and mutation several times to make the high-quality chromosome exist in candidate offspring easily. Then the normal offspring is selected statistically based on the scenario complexity, which is designed to measure the difficulty of realizing autonomous driving through the Analytic Hierarchy Process. The benefits of modified cross/mutation operators on the improvement of scenario complexity are analyzed theoretically. Finally, the effectiveness of improved genetic algorithm-based evolution test is validated after being applied to evaluate the collision avoidance performance of an automatic parallel parking system.
Similar content being viewed by others
Abbreviations
- AEB:
-
Automatic emergency baking
- AHP:
-
Analytic hierarchy process
- APPS:
-
Automatic parallel parking system
- APS:
-
Automated parking system
- GA:
-
Genetic algorithm
- IGA:
-
Improved genetic algorithm
- ISO:
-
International standard organization
References
Gao, F., Dang, D., He, Y.: Robust coordinated control of nonlinear heterogeneous platoon interacted by uncertain topology. IEEE Trans. Intell. Transp. Syst. (2020). https://doi.org/10.1109/TITS.2020.3045107
Dang, D., Gao, F., Hu, Q.: Motion planning for autonomous vehicles considering longitudinal and lateral dynamics coupling. Appl. Sci. 10(9), 3180 (2020). https://doi.org/10.3390/app10093180
Li, L., Huang, W., Liu, Y., Zheng, N., Wang, F.: Intelligence testing for autonomous vehicles: a new approach. IEEE Trans. Intell. Veh. 1(2), 158–166 (2016)
Morton, J., Wheeler, T.A., Kochenderfer, M.J.: Closed-loop policies for operational tests of safety-critical systems. IEEE Trans. Intell. Veh. 3(3), 317–328 (2018)
Tumasov, A.V., Vashurin, A.S., Trusov, Y.P.: The application of hardware-in-the-loop (HIL) simulation for evaluation of active safety of vehicles equipped with electronic stability control (ESC) systems. Proc. Comput. Sci. 150, 309–315 (2019). https://doi.org/10.1016/j.procs.2019.02.057
i-VISTA: i-VISITA intelligent vehicle index. https://www.i-vista.org/download (2020). Accessed 04 March 2021
Woo, J.W., Yu, S.B., Lee, S.B.: Design and simulation of a vehicle test bed based on intelligent transport system. Int. J. Automot. Technol. 17(2), 353–359 (2016)
Berger, C., Block, D., Heeren, S.: Simulations on consumer tests: a systematic evaluation approach in an industrial case study. IEEE Intell. Transp. Syst. Mag. 7(4), 24–36 (2015)
Hannan, M.A., Lipu, M.S.H., Hussain, A., Mohamed, A.: A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: challenges and recommendations. Renew. Sust. Energ. Rev. 78, 834–854 (2017). https://doi.org/10.1016/j.rser.2017.05.001
Zhao, D., Lam, H., Peng, H.: Accelerated evaluation of automated vehicles safety in lane-change scenarios based on importance sampling techniques. IEEE Trans. Intell. Transp. Syst. 18(3), 595–607 (2017)
Perez, M., Angell, L. S., Hankey, J.: Advanced crash avoidance technologies (ACAT) program—final report of the GM-VTTI backing crash countermeasures project. Natural Highway Traffic Safety Admin. (NHTSA), Washington, DC, USA, DOT HS 811 452, (2011)
Victor, T., Bärgman, J., Hjälmdahl, M.: Sweden-Michigan naturalistic field operational test (SeMiFOT) phase 1: final report. Chalmers, Goteborg, Sweden, (2010)
Burzio, G., Guidotti, L., Perboli, G.: Results and lessons learned of a subjective field operational test on the lane departure warning function. Proc. Soc. Behav. Sci. 48, 1356–1365 (2012). https://doi.org/10.1016/j.sbspro.2012.06.1111
Hou, Y., Zhao, Y., Wagh, A.: Simulation-based testing and evaluation tools for transportation cyber–physical systems. IEEE Trans. Veh. Technol. 65(3), 1098–1108 (2016)
Yang, H., Peng, H.: Development and evaluation of collision warning/collision avoidance algorithms using an errable driver model. Veh. Syst. Dyn. 48(sup 1), 525–535 (2010)
Kang, Y., Yin, H., Berger, C.: Test your self-driving algorithm: an overview of publicly available driving datasets and virtual testing environments. IEEE Trans. Intell. Veh. 4(2), 171–185 (2019)
Gao, F., Duan, J., He, Y., Wang, Z.: A test scenario automatic generation strategy for intelligent driving systems. Math. Probl. Eng. 3737486, 1–10 (2019). https://doi.org/10.1155/2019/3737486
Xia, Q., Duan, J., Gao, F.: Test scenario design for intelligent driving system ensuring coverage and effectiveness. Int. J. Automot. Technol. 19(4), 751–758 (2018)
Zhao, D., Huang, X., Peng, H.: Accelerated evaluation of automated vehicles in car-following maneuvers. IEEE Trans. Intell. Transp. Syst. 19(3), 733–744 (2018)
Wu, P., Gao, F., Li, K.: A vehicle type dependent car-following model based on naturalistic driving study. Electronics 8(4), 453–468 (2019)
Duan, J., Gao, F., He, Y.: Test scenario generation and optimization technology for intelligent driving systems. IEEE Intell. Transp. Syst. Mag. (2020). https://doi.org/10.1109/MITS.2019.2926269
Gao, F., Duan, J., Han, Z.: Automatic virtual test technology for intelligent driving systems considering both coverage and efficiency. IEEE Trans. Vehic. Technol. 69(12), 14365–14376 (2020)
Vos, T.E.J., Lindlar, F.F., Wilmes, B.: Evolutionary functional black-box testing in an industrial setting. Softw. Qual. J. 21(2), 259–288 (2013)
Wegener, J., Bühler, O.: Evaluation of different fitness functions for the evolutionary testing of an autonomous parking system. In: Genetic and Evolutionary Computation Conference, Seattle, USA, pp 1400–1412 (2004)
Li, J., Li, M.: An analysis on convergence and convergence rate estimate of genetic algorithms in noisy environments. Optik 124(24), 6780–6785 (2013)
Saaty, T.L.: Axiomatic foundation of the analytic hierarchy process. Manage. Sci. 32(7), 841–855 (1986)
Wind, Y., Saaty, T.L.: Marketing applications of the analytic hierarchy process. Manage. Sci. 26(7), 641–658 (1980)
Ishizaka, A., Labib, A.: Review of the main developments in the analytic hierarchy process. Exp. Syst. Appl. 38(11), 14336–14345 (2011)
Barhate, S. S.: Effective test strategy for testing automotive software. In: International Conference on Industrial Instrumentation and Control, Pune, India, 645–649, 28–30 July 2015
Rudolph, G.: Convergence analysis of canonical genetic algorithms. IEEE Trans. Neural Netw. 5(1), 96–101 (1994)
Peng, Y., Luo, X., Wei, W.: A new fuzzy adaptive simulated annealing genetic algorithm and its convergence analysis and convergence rate estimation. Int. J. Control Autom. Syst. 12(3), 670–679 (2014)
Bao, X., Xiong, Z., Zhang, N.: Path-oriented test cases generation based adaptive genetic algorithm. PLoS ONE 12(11), 1–17 (2017)
Wang, X.: Study on the key technologies of automatic parking system. Dissertation, Chongqing University (2019).
Acknowledgments
This work is supported by the Open Fund of State Key Laboratory of Vehicle NVH and Safety Technology under Grant NVHSKL-202009 and the Technological Plans of Chongqing under grant cstc2019jcyj-zdxm0022.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all the authors, the corresponding author states that there is no conflict of interest.
Additional information
Academic editor: Shuo Feng
Appendix 1 Definitions and Proofs
Appendix 1 Definitions and Proofs
1.1 Definition of Symbols
\({g}_{i}\): The objective function value corresponding to \({{\varvec{T}}}_{i}\);
\({g}_{\mathrm{th}}\): The threshold of the objective function value;
G: The generation of population;
\({G}_{\mathrm{th}}\): The maximum number of interaction test process;
\({{\varvec{P}}}_{i}^{\mathrm{C}}\): The i-th parent individual pair in the natural selected population \({{\varvec{X}}}^{\mathrm{S}}\) from \({{\varvec{X}}}_{G}\);
\({{\varvec{P}}}_{i,j}^{\mathrm{C}}\): The offspring pair generated by single-point crossover at the j-th position of \({{\varvec{P}}}_{i}^{\mathrm{C}}\);
\({{\varvec{P}}}_{i}^{\mathrm{C}\boldsymbol{*}}\): The selected offspring pair from \({{\varvec{P}}}_{i,j}^{\mathrm{C}},\boldsymbol{ }j=1,\cdots ,L\), where \(L\) is the number of genes;
\({{\varvec{T}}}^{*}\): The best test case evaluated by \({g}_{i}\), and its objective function value is \({g}^{*}\);
\({{\varvec{X}}}_{G}=\left\{{{\varvec{T}}}_{i},i=1,\cdots ,2m\right\}\): The G-th population compose of 2 m individuals;
\({{\varvec{X}}}^{\mathrm{C}}=\left\{{{\varvec{P}}}_{1}^{\mathrm{C}*},\cdots ,{{\varvec{P}}}_{m}^{\mathrm{C}*}\right\}\): The offspring population generated by crossover operation;
\({{\varvec{X}}}_{i}^{\mathrm{M}}\): The population generated by conducting the i-th mutation on \({{\varvec{X}}}^{\mathrm{C}}\);
\({{\varvec{X}}}^{\mathrm{M}*}\): The selected population from \({{\varvec{X}}}_{i}^{\mathrm{M}},\boldsymbol{ }i=1,\cdots ,N\), where \(N\) is the mutation times.
\(\overline{D}\left( {\mathbf{X}} \right) = \frac{1}{n}\sum\limits_{{i{ = 1}}}^{n} {D\left( {{\varvec{T}}_{i} } \right)}\): The average complexity of a population \({\mathbf{X}} = \left\{ {{\varvec{T}}_{1} ,{\varvec{T}}_{2} , \ldots ,{\varvec{T}}_{n} } \right\}\);
\({P}_{\mathrm{r}}\left(\bullet \right)\): The occurrence probability of an event.
1.2 Proof of Theorem 1
where \(D_{i,j}^{C} = e^{{d \times \overline{D}\left( {P_{i,j}^{C} } \right)}} /\sum\limits_{k = 1}^{L} {e^{{d \times \overline{D}\left( {P_{i,j}^{C} } \right)}} }\) is the normalized complexity of \({\varvec{P}}_{i,j}^{C}\). According to whether the full crossover can increase the complexity of offspring, Eq. (11) can be re-written as
where \({\Omega }_{+}^{\mathrm{C}}=\left\{j|{D}_{i,j}^{\mathrm{C}}\ge \frac{{p}_{\mathrm{C}}}{L}\right\}\) and \({\Omega }_{-}^{\mathrm{C}}=\left\{j|j=1,\cdots ,L\right\}-{\Omega }_{+}^{\mathrm{C}}\).
From Eq. (5) and the definition of \({D}_{i,j}^{\mathrm{C}}\):
when \({p}_{\mathrm{C}}=1\), the following equation establishes from Eq. (13):
Then substituting Eq. 14 and \({p}_{\mathrm{C}}=1\) to Eq. (12) yields
According to the definition of \({\Omega }_{+}^{\mathrm{C}}\) and \({\Omega }_{-}^{\mathrm{C}}\):
Conclusion C1 is proved by substituting Eq. (16) to Eq. (15).
When \(0\le {p}_{\mathrm{C}}<1\), the following equation is deduced by substituting Eq. (13) to Eq. (11):
Equation (17) is monotonically decreasing with \({p}_{\mathrm{C}}\) as the variable when Eq. (7) establishes, and so C2 establishes with the conclusion derived from C1.
1.3 Proof of Lemma 1
Since the N times canonical mutations are independent, the following equations are obtained:
where \({\mathrm{C}}_{N}^{i}=\frac{N!}{i!\left(N-i\right)!}\) denotes the combination number.
According to the binomial expansion
Lemma 1: Is proved by substituting Eq. (19) to Eq. (18).
1.4 Proof of Theorem 2
According to Step 6 and Lemma 1:
Being similar to the analysis procedure of Eq. (12), Eq. (20) is re-written as
where \({\Omega }_{+}^{\mathrm{M}}=\left\{i|{D}_{i}^{\mathrm{M}}\ge \frac{1}{N}\right\}\), \({\Omega }_{-}^{\mathrm{M}}=\left\{i|i=1,\cdots ,N\right\}-{\Omega }_{+}^{\mathrm{M}}\) and \(D_{i}^{M} = e^{{d \times \overline{D}\left( {X_{i}^{M} } \right)}} /\sum\limits_{k = 1}^{N} {e^{{d \times \overline{D}\left( {X_{k}^{M} } \right)}} }\) is the normalized complexity. Equation (9) is derived referring to the analysis process from (15) to (16) with the fact that \(\sum\nolimits_{i = 1}^{N} {D_{i}^{M} = 1}\).
Rights and permissions
About this article
Cite this article
Gao, F., Mu, J., Han, X. et al. Performance Limit Evaluation Strategy for Automated Driving Systems. Automot. Innov. 5, 79–90 (2022). https://doi.org/10.1007/s42154-021-00168-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42154-021-00168-8