Assembly Measurement Path Planning for Mobile Robots Using an Improved Deep Reinforcement Learning
Source abstract
Abstract
In addressing the challenges associated with mobile robot path planning during complex product assembly measurements, this study introduces the N-step Priority Double DQN (NDDQN) algorithm, which integrates double Q-learning and an N-step priority strategy to accelerate convergence. This approach aims to improve the obstacle avoidance capabilities of mobile robots while accelerating their learning efficiency. We conducted three grid-based obstacle avoidance simulation experiments of varying scales to compare and analyze the path planning performance of both the proximal policy optimization algorithm and the Deep Q Network algorithm. To accurately simulate real-world robotic measurement scenarios, two Gazebo environments were utilized to validate the effectiveness of our proposed algorithm. Through a comprehensive analysis of simulation results from all three algorithms, we demonstrate that the NDDQN algorithm exhibits significant effectiveness and stability in path planning. Notably, it substantially reduces iteration counts and enhances convergence speeds. This research provides a theoretical foundation for adaptive path planning in mobile robots engaged in complex product assembly measurements.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robot Manipulation and Learning · Robotic Path Planning Algorithms · Reinforcement Learning in Robotics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical Engineering, Southeast University, Nanjing 211189, China
Aerosun Corporation, Nanjing 211100, China
School of the Mechanical-Electrical and Vehicle Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China
School of Electro-Mechanical Engineering, Xidian University, Xi’an 710071, China
Funding
National Natural Science Foundation of China · Humanities and Social Science Fund of Ministry of Education of China · National key Research and Development Program of China · Jiangsu Excellent Postdoctoral Program
References (37)
Show source-provided references
1. Image-based visual servoing with collision-free path planning for monocular vision-guided assembly10.1109/TIM.2024.3463014 ↗
2. Machine learning algorithms for delaminations detection on composites panels by wave propagation signals analysis: Review, experiences and results10.1016/j.paerosci.2024.100994 ↗
3. Robot differential drive navigation through probabilistic roadmap and pure pursuit10.1109/ACCESS.2025.3536383 ↗
4. Research on reducing assembly errors in inductive encoders with observer phase detector phase-locked loop10.1109/JSEN.2023.3327252 ↗
5. Digital measurement technique for evaluating aircraft final assembly quality10.1360/SST-2020-0049 ↗
6. Mobile robots for moving-floor assembly lines design, evaluation, and deployment10.1109/MRA.2018.2815639 ↗
7. Yuan, G., Lv, F., Shi, J., Tian, G., Feng, Y., Li, Z., and Pham, D.T. (2024). Integrated optimisation of human-robot collaborative disassembly planning and adaptive evaluation driven by a digital twin. Int. J. Prod. Res., 1–19.10.1080/00207543.2024.2381710 ↗
8. Xiang, Y., Jin, X., Lei, K., and Zhang, Q. (2025). Research on energy-saving and efficiency-improving optimization of a four-way shuttle-based dense three-dimensional warehouse system based on two-stage deep reinforcement learning. Appl. Sci., 15.10.3390/app152111367 ↗
9. A graph-based pipe routing algorithm in aero-engine rotational space10.1007/s10845-013-0840-0 ↗
10. Ni, J., Ge, Y., Zhao, Y., and Gu, Y. (2025). An improved multi-UAV area coverage path planning approach based on deep Q-Networks. Appl. Sci., 15.10.3390/app152011211 ↗
11. A generalized voronoi diagram-based efficient heuristic path planning method for RRTs in mobile robots10.1109/TIE.2021.3078390 ↗
12. A hybrid formation path planning based on A* and multi-target improved artificial potential field algorithm in the 2D random environments10.1016/j.aei.2022.101755 ↗
13. SRL-ORCA: A socially aware multi-agent mapless navigation algorithm in complex dynamic scenes10.1109/LRA.2023.3331621 ↗
14. Learning decentralized multi-robot pointGoal navigation10.1109/LRA.2025.3550798 ↗
15. Plug-and-play cooperative navigation: From single-agent navigation fields to graph maintaining distributed MAS controllers10.1109/TAC.2023.3346796 ↗
16. Path planning of autonomous mobile robot in comprehensive unknown environment using deep reinforcement learning10.1109/JIOT.2024.3379361 ↗
17. Ding, X., Chen, H., Wang, Y., Wei, D., Fu, K., Liu, L., Gao, B., Liu, Q., and Huang, J. (2025). Efficient target assignment via binarized SHP path planning and plasticity-aware RL in urban adversarial scenarios. Appl. Sci., 15.10.3390/app15179630 ↗
18. Vision-based autonomous navigation approach for a tracked robot using deep reinforcement learning10.1109/JSEN.2020.3016299 ↗
19. A review of motion planning algorithms for intelligent robots10.1007/s10845-021-01867-z ↗
20. Mobile robot path planning based on improved localized particle swarm optimization10.1109/JSEN.2020.3039275 ↗
21. Smart, W.D., and Kaelbling, L.P. (2002, January 11–15). Effective reinforcement learning for mobile robots. Proceedings of the 2002 IEEE International Conference on Robotics and Automation, Washington, DC, USA.
22. Solving the optimal path planning of a mobile robot using improved Q-learning10.1016/j.robot.2019.02.013 ↗
23. Concise deep reinforcement learning obstacle avoidance for underactuated unmanned marine vessels10.1016/j.neucom.2017.06.066 ↗
24. Path planning in an unknown environment based on deep reinforcement learning with prior knowledge
25. Yang, X., and Han, Q. (2023). Improved DQN for dynamic obstacle avoidance and ship path planning. Algorithms, 16.10.3390/a16050220 ↗
26. Path planning for mobile robot considering turnabouts on narrow road by deep Q-network10.1109/ACCESS.2023.3247730 ↗
27. DM-DQN: Dueling munchausen deep Q network for robot path planning10.1007/s40747-022-00948-7 ↗
28. Anti-conflict AGV path planning in automated container terminals based on multi-agent reinforcement learning10.1080/00207543.2021.1998695 ↗
29. Mobile robots path planning algorithm based on angle searching and deep Q-network
30. Distributed multirobot path planning based on MRDWA-MADDPG10.1109/JSEN.2023.3310519 ↗
31. Adaptive Q-learning path planning algorithm based on virtual target guidance
32. Deep reinforcement learning-based hierarchical motion planning strategy for multirotors10.1109/TII.2024.3523594 ↗
33. Hierarchical control framework for path planning of mobile robots in dynamic environments through global guidance and reinforcement learning
34. Safe multi-agent reinforcement learning for behavior-based cooperative navigation10.1109/LRA.2025.3560830 ↗
35. Sim-to-real transfer of deep reinforcement learning agents for online coverage path planning10.1109/ACCESS.2025.3581035 ↗
36. An improved HM-SAC-CA algorithm for mobile robot path planning in unknown complex environments10.1109/ACCESS.2025.3535728 ↗
37. Lin, X., Yan, J., Du, H., and Zhou, F. (2025). Path planning for full coverage of farmland operations in Hilly and Mountainous areas based on the dung beetle optimization algorithm. Appl. Sci., 15.10.3390/app15169157 ↗