Page 316 - Kỷ yếu hội thảo khoa học lần thứ 12 - Công nghệ thông tin và Ứng dụng trong các lĩnh vực (CITA 2023)

300

In Fig.5, we see that Dijkstra's algorithm has the shortest computation time and EBAND
algorithm has the longest computation time for a certain destination in our implemem-
tation. As the number of obstacles increases, the difference in computation time among
the three algorithms becomes more evident.

4 Conclusion

In conclusion, we evaluated the performance of three scheduling algorithms, namely

uation showed that the EBAND algorithm outperformed the other two algorithms in
terms of path length and However,
all three algorithms were safe and avoided collisions with obstacles in the environment.
Thus, we recommend the use of the EBAND algorithm for route planning in ADVs, as
it is more efficient and faster than the other two algorithms.

References

1. Szczepanski, R.; Bereit, A.; Tarczewski, T. Efficient local path planning algorithm using
artificial potential field supported by augmented reality. Energies (2021).
2. Wang, H.; Liu, B.; Ping, X.; An, Q. Path tracking control for autonomous vehicles based on
an improved MPC. IEEE Access (2019).
3. Qian, L.; Xu, X.; Zeng, Y.; Huang, J. Deep, Consistent behavioral decision making with
planning features for autonomous vehicles. Electronics (2019).
4. URDF in Gazebo. (2016) Tutorial: Using a URDF in Gazebo. [Online]. Available: http://ga-
zebosim.org/tutorials/?tut=ros urdf.

CITA 2023 ISBN: 978-604-80-8083-9