Computationally efficient path planning algorithm for autonomous vehicle
- Authors: Debnath, Sanjoy , Omar, Rosli , Abdul Latip, Nor , Bagchi, Susama , Sabudin, Elia , Mumin, Abdul , Soomro, Abdul , Nafea, Marwan , Muhammad, Bashir , Naha, Ranesh
- Date: 2021
- Type: Text , Journal article
- Relation: Jurnal teknologi Vol. 83, no. 1 (2021), p. 133-143
- Full Text: false
- Reviewed:
- Description: This paper analyses an experimental path planning performance between the Iterative Equilateral Space Oriented Visibility Graph (IESOVG) and conventional Visibility Graph (VG) algorithms in terms of computation time and path length for an autonomous vehicle. IESOVG is a path planning algorithm that was proposed to overcome the limitations of VG which is slow in obstacle-rich environment. The performance assessment was done in several identical scenarios through simulation. The results showed that the proposed IESOVG algorithm was much faster in comparison to VG. In terms of path length, IESOVG was found to have almost similar performance with VG. It was also found that IESOVG was complete as it could find a collision-free path in all scenarios.
Energy efficient elliptical concave visibility graph algorithm for unmanned aerial vehicle in an obstacle-rich environment
- Authors: Debnath, Sanjoy , Omar, Rosli , Bagchi, Susama , Nafea, Marwan , Naha, Ranesh , Nadira Sabudin, Elia
- Date: 2020
- Type: Text , Conference proceedings
- Relation: 2020 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS); Shah Alam, Malaysia;20 June 2020 p. 129-134
- Full Text: false
- Reviewed:
- Description: This paper proposes a path planning algorithm for unmanned aerial vehicle (UAV) called Elliptical Concave Visibility Graph (ECoVG). The algorithm, which is based on visibility graph (VG), overcomes the limitations of VG computation time and hence, it can be applied in real-time and in obstacle-rich environments. An experimental investigation has been done to compare the performance between ECoVG and another VG based method namely Equilateral-Space Oriented VG (ESOVG) in terms of computational time and path length. The investigation was done in identical scenarios through simulation to show that the ECoVG has a better computation time than that of ESOVG for its efficient selection of a region in calculating the path. It is also found that the proposed algorithm is energy efficient and complete since it can find a path if one exists.