Research on Path Planning of a Mining Inspection Robot in an Unstructured Environment Based on an Improved Rapidly Exploring Random Tree Algorithm
Abstract
:1. Introduction
2. Methods
2.1. Traditional RRT Algorithm
- Strong randomness: The path generated by the RRT algorithm is based on random sampling, and the randomness is strong. The algorithm randomly scatters points in the environment map. If the scatter point is close to the target point, it can search the end point faster. If the scatter point is far away from the target point, the search efficiency is reduced.
- Non-optimal solution: The path of finding a feasible solution by using the RRT algorithm many times may be different, and it does not guarantee that the optimal solution will be found. The RRT algorithm is affected by the different layout of obstacles between the starting point and the target point, resulting in a large difference in the quality of the planned path.
- Poor smoothness: The random points selected by the RRT algorithm each time may lead to the discontinuity of the path, making the path turn back or turn sharply in space. As a result, the path generated by the RRT algorithm is not smooth enough visually and does not conform to the actual motion law [17].
2.2. Path-Planning Improvement
2.2.1. Fan-Shaped Goal Orientation
2.2.2. Environment-Adaptive Step Size Expansion Strategy
Algorithm 1: Bridge detection algorithm |
1: Repeat 2: a Rand(); 3: if CollisionFree(a) = False then 4: a′ Nearpoint(a); 5: if CollisionFree(a′) = False then 6: b′ Midpoint(aa′); 7: if CollisionFree(b) = True then 9: GInsertpoint(G, b); 10: end 11: end 12: End |
2.2.3. Fusion of the FGA-RRT and PRM Algorithms
Algorithm 2: Fusion of the FGA-RRT and PRM Algorithms |
1: Input: M,xstart,xgoal 2: Output: A path Γ from xstart to xgoal 3: Γ Ø 4: for i = 1 to n do 5: xrand FanshapedSample(M) 6: xnear near(xrand,Γ); 7: if BridgeDetection(xrand) then 8: xnew Steer(xrand, xnear, addStepSize) 9: if CollisionFree(xnew, xnear) then 10: ΓaddNode(xnew) 11: if xnew = xgoal then 12: end if 13: end if 14: end if 15: end for 16: q random configuration in Γ 17: for all qi∈Γ do 18: qi the closest point to q chosen from Γ 19: if CollisionFree(q, qi) then 18: ΓaddNode(q, qi) 19: end if 20: end for 21: Return Γ |
2.3. Bessel Curve Optimization
- The generated path has no collision after obstacle collision detection.
- If there is more than one path that meets the previous condition, the path with the shortest length is selected.
3. Simulation and Analysis
3.1. Map Building
3.2. Analysis of the Influence of Extended Step Size
3.3. Experimental Simulation and Analysis
3.3.1. Map 1
3.3.2. Map 2
3.3.3. Map 3
3.4. Bessel Curve Optimization
4. Real-World Experiment
4.1. Mining Inspection Robot Platform
- (1)
- Total controller
- (2)
- Laser radar
- (3)
- Inertial measurement unit
- (4)
- Servo driver
4.2. Experiment and Analysis
4.2.1. Simulated Environment 1
4.2.2. Simulated Environment 2
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Ge, S.H.; Hu, E.Y.; Li, Y.W. New progress and new direction of robot technology in coal mine. Coal J. 2023, 48, 54–73. [Google Scholar]
- Yang, C.Y.; Zhang, X. Key technologies of environment perception and path planning for coal mine robots. J. China Coal Soc. 2022, 47, 2844–2872. [Google Scholar]
- Zhang, K.X.; Mao, J.L.; Xiang, F.H. B-HICA * multi-robot path planning algorithm based on bargaining game mechanism. Acta Autom. Sin. 2023, 49, 1483–1497. [Google Scholar]
- Luo, S.D.; Wang, Y. Tourism route optimization based on improved knowledge antcolony algorithm. Complex Intell. Syst. 2022, 8, 973–988. [Google Scholar]
- Hao, G.; Lv, Q.; Huang, Z.; Zhao, H.; Chen, W. UAV Path Planning Based on Improved Artificial Potential Field Method. Aerospace 2023, 10, 562. [Google Scholar] [CrossRef]
- Dai, J.; Li, D.; Zhao, J.; Li, Y. Autonomous navigation of robots based on the improved informed-RRT algorithm and DWA. J. Robot. 2022, 32, 49–58. [Google Scholar] [CrossRef]
- Lanteigne, E.; Jnifene, A. Biologically Inspired Node Generation Algorithm for Path Planning of Hyper-redundant Manipulators Using Probabilistic Roadmap. Int. J. Autom. Comput. 2014, 11, 153–161. [Google Scholar] [CrossRef]
- Li, T.; Zhao, H.S. Mobile Robot Path Optimization Based on Evolutionary Ant Colony Algorithm. Control. Decis. 2023, 38, 612–620. [Google Scholar]
- Huang, Z.F.; Liu, Y.H. Low altitude path planning of urban UAV based on improved lion swarm algorithm. Inf. Control 2023, 52, 747–757+772. [Google Scholar] [CrossRef]
- Zhang, L.; Wang, X.; Zhang, J. Path planning of improved RRT algorithm in multi-obstacle scenario. Comput. Eng. Des. 2023, 44, 1706–1713. [Google Scholar]
- Xu, W.; Yang, Y.; Yu, L. A global path planning algorithm based on improved RRT. Control. Decis. 2022, 37, 829–838. [Google Scholar]
- Luan, T.T.; Wang, H.; Sun, M.X.; Lv, C.Y. Path planning of unmanned vehicle based on dynamic variable sampling area RRT. Control. Decis. Mak. 2023, 38, 1721–1729. [Google Scholar]
- Sun, L.; Duan, X.; Zhang, K.; Xu, P.; Zheng, X.; Yu, Q. Improved path planning algorithm for mobile robots. Soft Comput. 2023, 27, 15057–15073. [Google Scholar] [CrossRef]
- Ding, J.; Zhou, Y.X.; Huang, X.; Song, K.; Lu, S.Q.; Wang, L.S. An improved RRT* algorithm for robot path planning based on path expansion heuristic sampling. J. Comput. Sci. 2023, 67, 101937. [Google Scholar] [CrossRef]
- Liu, H.L.; Lei, B.; Wang, W.Y. Path planning of warehouse mobile robot based on improved chimpanzee optimization algorithm. Inf. Control 2023, 12, 1–9. [Google Scholar]
- Karaman, S.; Frazzoli, E. Sampling-based algorithms for optimal motion planning. Int. J. Robot. Res. 2011, 30, 846–894. [Google Scholar] [CrossRef]
- Zhang, T.; Li, Q. Mobile robot path planning based on B-RRT* FND algorithm. Control. Decis. 2023, 38, 3121–3127. [Google Scholar]
- Fu, J.P.; Zeng, G.H.; Bo, B.H. Path planning of narrow channel based on bidirectional fast exploration random tree. Comput. Appl. 2019, 39, 2865–2869. [Google Scholar]
Combination | 1 | 2 | 3 | 4 | 5 | 6 |
---|---|---|---|---|---|---|
Non-narrow channel | 2 | 3 | 4 | 4 | 5 | 6 |
Narrow channel | 4 | 5 | 4 | 6 | 7 | 8 |
Time (s) | Map 1 | Map 2 | Map 3 |
---|---|---|---|
Combination 1 | 12.06 | 10.53 | 9.14 |
Combination 2 | 9.84 | 7.64 | 8.23 |
Combination 3 | 9.76 | 7.51 | 7.30 |
Combination 4 | 6.76 | 4.69 | 7.05 |
Combination 5 | 11.56 | 10.52 | 13.52 |
Combination 6 | 15.95 | 14.86 | 17.56 |
Algorithm | Path-Planning Length | Inflection Points | Rate of Success |
---|---|---|---|
Traditional RRT | 80.59 | 16.3 | 63% |
EP-RRT* | 71.52 | 11.5 | 78% |
FGA-RRT and PRM fusion | 67.72 | 3.2 | 94% |
Algorithm | Path-Planning Length | Inflection Points | Rate of Success |
---|---|---|---|
Traditional RRT | 79.68 | 14.2 | 66% |
EP-RRT* | 75.53 | 12.6 | 85% |
FGA-RRT and PRM fusion | 66.53 | 3.5 | 95% |
Algorithm | Path-Planning Length | Inflection Points | Rate of Success |
---|---|---|---|
Traditional RRT | 78.15 | 13.6 | 90% |
EP-RRT* | 74.34 | 10.7 | 92% |
FGA-RRT and PRM fusion | 70.55 | 4.8 | 98% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wu, J.; Zhao, L.; Liu, R. Research on Path Planning of a Mining Inspection Robot in an Unstructured Environment Based on an Improved Rapidly Exploring Random Tree Algorithm. Appl. Sci. 2024, 14, 6389. https://doi.org/10.3390/app14146389
Wu J, Zhao L, Liu R. Research on Path Planning of a Mining Inspection Robot in an Unstructured Environment Based on an Improved Rapidly Exploring Random Tree Algorithm. Applied Sciences. 2024; 14(14):6389. https://doi.org/10.3390/app14146389
Chicago/Turabian StyleWu, Jingwen, Liang Zhao, and Ruixue Liu. 2024. "Research on Path Planning of a Mining Inspection Robot in an Unstructured Environment Based on an Improved Rapidly Exploring Random Tree Algorithm" Applied Sciences 14, no. 14: 6389. https://doi.org/10.3390/app14146389