2021
DOI: 10.3390/s21062244
|View full text |Cite
|
Sign up to set email alerts
|

Development of an Improved Rapidly Exploring Random Trees Algorithm for Static Obstacle Avoidance in Autonomous Vehicles

Abstract: Safe path planning for obstacle avoidance in autonomous vehicles has been developed. Based on the Rapidly Exploring Random Trees (RRT) algorithm, an improved algorithm integrating path pruning, smoothing, and optimization with geometric collision detection is shown to improve planning efficiency. Path pruning, a prerequisite to path smoothing, is performed to remove the redundant points generated by the random trees for a new path, without colliding with the obstacles. Path smoothing is performed to modify the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
0

Year Published

2021
2021
2025
2025

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 25 publications
(10 citation statements)
references
References 38 publications
0
9
0
Order By: Relevance
“…For a robotic arm, the redundant turning points will cause unnecessary energy loss, cause wear and reduce the service life of the robotic arm. Therefore, this article adopts an operation to remove redundant points [28,29]. The redundant node removal operation is performed on the generated path.…”
Section: Redundant Node Deletion Operationmentioning
confidence: 99%
“…For a robotic arm, the redundant turning points will cause unnecessary energy loss, cause wear and reduce the service life of the robotic arm. Therefore, this article adopts an operation to remove redundant points [28,29]. The redundant node removal operation is performed on the generated path.…”
Section: Redundant Node Deletion Operationmentioning
confidence: 99%
“…It is to solve continuous and discrete optimization problem. Global and local path planning Advantages: Suitable for large datasets and dynamic environment Solving capacitated vehicle routing problem Limitation: Probability of being trapped in local minima Energy-efficient green Ant Colony Optimization (Sangeetha et al 2021 ) Collective behaviour of trail-laying ants for finding shortest path Advantages: Distributed search to avoid local minima, greedy heuristics Path planning in dynamic 3D environments Limitation: Slow convergence speed Improved Rapidly Rapidly-Exploring Random Trees (Yang and Lin 2021 ) Expand on all regions based on weights and create path Advantages: It works dynamically and does not require a prior path, can handle constraints that are non-integrable into positional constraints Static obstacle avoidance in autonomous vehicles Limitation: Low accuracy D* lite Algorithm (Yao et al 2021 ) Path planning in partially known and dynamic environment Advantages: Path cost optimization planning, where the cost changes dynamically Efficient path planning for Unmanned Surface Vehicles in complex environments Limitation: High memory consumption A* (Foead et al 2021 ) Similar to Dijkstra, but guides the agent towards the next promising node Advantages: Simpler and computationally effective Shortest path Limitation: Trade-off between speed and accuracy Dijkstra Algorithm (Akram et al 2021 ) Single source shortest path Advantages: Works well in an acyclic environment Finding shortest paths in networks Limitation: Does not keep track of all the nodes previously travelled. Single source only and it requires more memory CSO-ALO (Deb and Gao 2021 ) ...…”
Section: State-of-the Artmentioning
confidence: 99%
“…Lu et al utilized Dubins curves to generate a path, but the curvature of the generated path is discontinuous [ 38 ]. Yang et al used path pruning to delete unnecessary path nodes without considering the included angles between line segments between path nodes, resulting in excessive curvature of the final planned path [ 39 ]. Chen et al adopted path pruning based on inserted points to solve the initial path without considering the influence of inserted points on the path length, causing the length of the final planned path may not be optimal [ 29 ].…”
Section: Introductionmentioning
confidence: 99%