Autor: |
Olivier Orfila, Dominique Gruyer, Karima Hamdi, Sébastien Glaser |
Jazyk: |
angličtina |
Rok vydání: |
2019 |
Předmět: |
|
Zdroj: |
International Journal of Automotive Engineering, Vol 10, Iss 1, Pp 26-33 (2019) |
Druh dokumentu: |
article |
ISSN: |
2185-0992 |
DOI: |
10.20485/jsaeijae.10.1_26 |
Popis: |
This paper proposes and evaluates an algorithm called Multi-Objective planning based on Simulated Annealing (MOSA) that plans a trajectory (speed profile) for a passenger car on a free, single lane road. This algorithm is relying on a decomposition of the decision space into “chunks” that are optimized separately. Two objectives have been taken into account: travel time and fuel consumption. Optimization constraints are built from safety modelings combining legal speed, curves speed limits and junctions limits. The multi-objective optimization is performed through a linear scalairisation method and the optimization is a parametric optimization based on simulated annealing. The algorithm has been tested on simulated annealing convergence and results show a good convergence under 500 iterations and a small sensitivity to variables initialization. However, sensitivity to core parameters of the simulated annealing (initial temperature and temperature decreasing rate) is very high and some guidelines for the calibration of these parameters are given in this paper. Then, the algorithm has been tested and compared to experimental results and it shows that, even if some drivers can drive the road quicker than the algorithm, they cannot drive with a lower fuel consumption. Furthermore, the algorithm results are better than the most of the experimental results according to the Pareto definition of dominance and global results outperform results from another planning algorithm based on Dijkstra’s algorithm. Future works will concentrate on improving the algorithm to be more reactive to unexpected obstacles and more consistant in the “chunks” transitions. |
Databáze: |
Directory of Open Access Journals |
Externí odkaz: |
|