technical seminar Tharun.pptm.pptx by vtu students
1. 1
Recently, bio-inspired algorithms have been increasingly explored for autonomous robot path planning on grid-based maps.
However, these approaches endure performance degradation as problem com plexity increases, often resulting in lengthy search
times to find an optimal solution. This limitation is particularly critical for real-world applications like autonomous off road
vehicles, where high quality path computation is essential for energy efficiency. To address these challenges, this paper
proposes a new graph-based optimal path planning approach that leverages a sort of bio-inspired algorithm, improved seagull
optimization algorithm (iSOA) for rapid path planning of autonomous robots. A modified Douglas–Peucker (mDP) algorithm is
developed to approximate irregular obstacles as polygonal obstacles based on the environment image in rough terrains. The
resulting mDP derived graph is then modeled using a Maklink graph theory. By applying the iSOA approach, the trajectory of
an autonomous robot in the workspaceisoptimized. Additionally, aBezier-curve-basedsmoothingapproachisdevelopedto generate
safer and smoother trajectories while adhering to curvature constraints. The proposed model is validated through simulated
experiments undertaken in various real-world settings, and its performance is compared with state-of-the-art algorithms. The
experimental results demonstrate that the proposed model outperforms existing approaches in terms of time cost and path
length.
Abstract
2. 2
Introduction
Autonomous robots play a crucial role in various fields such as autonomous
vehicles, medical robotics, agriculture, and emergency response. Effective
path planning is essential for safe and efficient navigation while avoiding
obstacles.
3. 3
Challenges in Path Planning
• High computational complexity in complex environments
• Avoiding obstacles while ensuring energy efficiency
• Need for real-time, high-quality path computation
4. Bio-Inspired Algorithms in Robotics
Bio-inspired algorithms mimic natural behaviors to optimize robotic path planning. The
Improved Seagull Optimization Algorithm (iSOA), combined with graph-based models,
improves efficiency and accuracy in autonomous robot navigation.
5. Literature Survey / Related Work
• Artificial Potential Fields (APF)
• Sampling-Based Algorithms (RRT, PRM)
• Graph-Based Methods (Delaunay Triangulation, Maklink Graph)
• Bio-Inspired Techniques (BPA, ACO)
7. Proposed Algorithm & Contributions
• Developed a graph-based optimal path planning system using iSOA.
• Integrated Maklink graph, Modified Douglas-Peucker algorithm, and Bezier curve smoothing.
• Enhanced efficiency in trajectory planning and obstacle avoidance.
8. 2. Environmental modeling — Maklink graph
❑Spatial environmental modeling enhances collision checking in robot path planning. The
Maklink graph efficiently represents free space and obstacles, improving computational
efficiency.
11. 3. Polygonal obstacle approximation algorithm
• Converts irregular obstacles into simplified polygonal shapes
• Optimizes computational efficiency while maintaining accuracy
• Enables better environmental modeling for path planning
14. 4. Proposed algorithm for robot path planning
This section describes the use of Dijkstra’s algorithm combined with an iSOA method to
enable robot path planning based on Maklink graph-based environmental modeling. An
adjacency ma trix with weights is defined in order to calculate the shortest path and a
smooth scheme is used for the computation in this paper. 4.1. Initial path planning
Dijkstra’s algorithm is a popular approach for finding the shortest path between a starting
point S and a target point T on a
where fc denotes the frequency control interval of variable A, which decreased linearly
from fc to 0.
17. Path Optimization with iSOA
• Enhances standard Seagull Optimization Algorithm
• Introduces mutation operators for better path selection
• Dynamically finds the safest and shortest path
18. Path Smoothing using Bezier Curves
• Ensures smooth, natural robotic movement
• Minimizes sudden direction changes
• Improves real-time adaptability and efficiency
21. Experimental Results & Comparison
• Compared with A*, Bi-directional A*, RRT, and BIT*
• Performance evaluated on path length, execution time, and efficiency
• Demonstrated superior results in real-world simulations
22. Conclusion & Future Work
• Developed an optimized robot path planning system using iSOA
• Future Work: Implementing real-world applications, adapting to dynamic
environments, and enhancing computational efficiency through parallel processing.
23. References
[1] L. Wang, C. Luo, J. Cai, A variable interval rescheduling strategy for dynamic flexible job shop scheduling problem
by improved genetic algorithm, J. Adv. Transp. 2017 (2017).
[2] Z. Chu, F. Wang, T. Lei, C. Luo, Path planning based on deep reinforce ment learning for autonomous underwater
vehicles under ocean current disturbance, IEEE Trans. Intell. Veh. (2022).
[3] C. Zhang, T. Liu, S. Song, J. Wang, M.Q.-H. Meng, Dynamic wheeled motion control of wheel-biped transformable
robots, Biomim. Intell. Robotics 2 (2) (2022) 100027.
[4] S. Ortiz, W. Yu, Autonomous navigation in unknown environment using sliding mode SLAM and genetic algorithm,
Intell. Robot 1 (2) (2021) 131–150.
[5] J. Wang, C. Luo, Automatic wall defect detection using an autonomous robot: A focus on data collection, in: ASCE
International Conference on Computing in Civil Engineering 2019, American Society of Civil Engineers Reston, VA,
2019, pp. 312–319. [6] W. Zhao, R. Lun, C. Gordon, et al., Liftingdoneright: A privacy-aware human motion tracking
system for healthcare professionals, Int. J. Handheld Comput. Res. (IJHCR) 7 (3) (2016) 1–15.
![References
[1] L. Wang, C. Luo, J. Cai, A variable interval rescheduling strategy for dynamic flexible job shop scheduling problem
by improved genetic algorithm, J. Adv. Transp. 2017 (2017).
[2] Z. Chu, F. Wang, T. Lei, C. Luo, Path planning based on deep reinforce ment learning for autonomous underwater
vehicles under ocean current disturbance, IEEE Trans. Intell. Veh. (2022).
[3] C. Zhang, T. Liu, S. Song, J. Wang, M.Q.-H. Meng, Dynamic wheeled motion control of wheel-biped transformable
robots, Biomim. Intell. Robotics 2 (2) (2022) 100027.
[4] S. Ortiz, W. Yu, Autonomous navigation in unknown environment using sliding mode SLAM and genetic algorithm,
Intell. Robot 1 (2) (2021) 131–150.
[5] J. Wang, C. Luo, Automatic wall defect detection using an autonomous robot: A focus on data collection, in: ASCE
International Conference on Computing in Civil Engineering 2019, American Society of Civil Engineers Reston, VA,
2019, pp. 312–319. [6] W. Zhao, R. Lun, C. Gordon, et al., Liftingdoneright: A privacy-aware human motion tracking
system for healthcare professionals, Int. J. Handheld Comput. Res. (IJHCR) 7 (3) (2016) 1–15.](https://image.slidesharecdn.com/technicalseminartharun-250511173753-e5c8974b/85/technical-seminar-Tharun-pptm-pptx-by-vtu-students-23-320.jpg)
