Optimization of Mobile Robot Delivery System Based on Deep Learning

Authors

  • Xiaoyang Chen

    The Ohio State University, Columbus, OH 43210, USA

  • Yunxiang Gan

    Moloco, CA, USA

  • Shuguang Xiong

    Microsoft Inc., Beijing 100080, China

DOI:

https://doi.org/10.30564/jcsr.v6i4.7197
Received: 3 September 2024 | Revised: 6 September 2024 | Accepted: 6 September 2024 | Published Online: 27 September 2024

Abstract

In modern logistics and delivery systems, mobile robot delivery systems have garnered significant attention due to their efficiency and flexibility. However, existing robot delivery systems still face numerous challenges in complex and dynamically changing environments. For instance, traditional algorithms exhibit low efficiency when processing high-dimensional and unstructured data, making it difficult to adapt to real-time changing environments, which results in reduced accuracy and efficiency in path planning and task execution. Additionally, the lack of effective perception and decision-making mechanisms makes it challenging for robots to handle complex scenarios and variable delivery demands. To address these issues, this paper proposes an optimization method for mobile robot delivery systems based on deep learning. Firstly, this study introduces a spatial attention mechanism into the model. By focusing on key areas in the environment and dynamically adjusting the attention points, robots can better recognize and avoid obstacles in complex environments, thus improving the accuracy of navigation and path planning. Secondly, the Deep Deterministic Policy Gradient (DDPG) algorithm is employed for policy optimization, facilitating efficient learning in high-dimensional continuous spaces, enabling robots to learn effective delivery strategies in complex environments. Finally, through an end-to-end optimization approach, the system can directly convert sensor data inputs into control command outputs, reducing the complexity and error accumulation of intermediate steps and simplifying the system structure. Experimental results demonstrate that the proposed method significantly enhances the overall performance of the delivery system. It performs exceptionally well on several key indicators, including the accuracy of path planning, task execution efficiency, and system robustness. The effectiveness of combining the spatial attention mechanism with the deep policy gradient algorithm has been fully validated, providing new insights and methods for future optimization of robot delivery systems.

Keywords:

Delivery system; Deep learning; Spatial attention mechanism; DDPG algorithm; End-to-end optimization; Path planning

References

[1] Gomes, A.C., de Lima Junior, F.B., Soliani, R.D., et al., 2023. Logistics management in e-commerce: challenges and opportunities. Revista de Gestão e Secretariado. 14, 7252–7272.

[2] MLi, M., He, J., Jiang, G., et al., 2024. DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding. arXiv preprint. arXiv:2401.01545.

[3] Dai, W., 2022. Evaluation and improvement of carrying capacity of a traffic system. Innovations in Applied Engineering and Technology. 1–9.

[4] Lei, J., 2024. Green Supply Chain Management Optimization Based on Chemical Industrial Clusters. arXiv preprint. arXiv:2406.00478.

[5] Jiang, M., Huang, G.Q., 2022. Intralogistics synchronization in robotic forward-reserve warehouses for e-commerce last-mile delivery. Transportation Research Part E: Logistics and Transportation Review. 158, 102619.

[6] Jones, M., Djahel, S., Welsh, K., 2023. Path-planning for unmanned aerial vehicles with environment complexity considerations: A survey. ACM Computing Surveys. 55, 1–39.

[7] Li, L., Li, Z., Guo, F., et al., 2024. Prototype Comparison Convolutional Networks for One-Shot Segmentation. IEEE Access.

[8] Yan, B., Chen, T., Zhu, X., et al., 2020. A comprehensive survey and analysis on path planning algorithms and heuristic functions. In Intelligent Computing: Proceedings of the 2020 Computing Conference, Volume 1. Springer. pp. 581–598.

[9] Zhang, Y., Wang, J., Li, Q., 2024. Efficient algorithms for real-time traffic prediction. Traffic Engineering & Control. 65, 201–215.

[10] Chen, R., Liu, M., Wang, X., et al., 2024. Advances in machine learning for smart logistics. Journal of Logistics Management. 12, 1–15.

[11] Liu, Y., Bao, Y., 2023. Real-time remote measurement of distance using ultra-wideband (UWB) sensors. Automation in Construction. 150, 104849.

[12] Zhou, Y., Osman, A., Willms, M., et al., 2023. Semantic wireframe detection. Ndt. net DGZfP. 2023, 1–20.

[13] Qiu, Y., 2019. Estimation of tail risk measures in finance: Approaches to extreme value mixture modeling. Johns Hopkins University.

[14] Du, S., Chen, Z., Wu, H., et al., 2021. Image recommendation algorithm combined with deep neural network designed for social networks. Complexity. 2021, 5196190.

[15] Wang, Y., Chen, Z., Fu, C., 2022. Synergy masks of domain attribute model DaBERT: emotional tracking on time-varying virtual space communication. Sensors. 22, 8450.

[16] Hao, Y., Chen, Z., Jin, J., et al., 2023. Joint operation planning of drivers and trucks for semi-autonomous truck platooning. Transportmetrica A: Transport Science. 1–37.

[17] Hao, Y., Chen, Z., Sun, X., et al., 2024. Planning of Truck Platooning for Road-Network Capacitated Vehicle Routing Problem. arXiv preprint. arXiv:2404.13512.

[18] Li, S., Kou, P., Ma, M., et al., 2024. Application of semi-supervised learning in image classification: Research on fusion of labeled and unlabeled data. IEEE Access.

[19] Ye, M., Zhou, H., Yang, H., et al., 2024. Multi-strategy improved dung beetle optimization algorithm and its applications. Biomimetics. 9, 291.

[20] Zhou, Y., Xiao, J., Zhou, Y., et al., 2022. Multi-robot collaborative perception with graph neural networks. IEEE Robotics and Automation Letters. 7, 2289–2296.

[21] Wu, J., Li, H., 2020. Deep ensemble reinforcement learning with multiple deep deterministic policy gradient algorithm. Mathematical Problems in Engineering. 2020, 4275623.

[22] Wang, J., Liu, Y., Li, B., 2020. Reinforcement learning with perturbed rewards. Proceedings of the AAAI conference on artificial intelligence. 34, 6202–6209.

[23] Zhu, Y., Zhao, Y., Song, C., et al., 2024. Evolving reliability assessment of systems using active learning-based surrogate modelling. Physica D: Nonlinear Phenomena. 457, 133957.

[24] Wang, Z., Zhao, Y., Song, C., et al., 2024. A new interpretation on structural reliability updating with adaptive batch sampling-based subset simulation. Structural and Multidisciplinary Optimization. 67, 7.

[25] Chen, L., Wu, P., Chitta, K., et al., 2023. End-to-end autonomous driving: Challenges and frontiers. arXiv preprint. arXiv:2306.16927.

[26] Xiong, S., Zhang, H., 2024. A Multi-model Fusion Strategy for Android Malware Detection Based on Machine Learning Algorithms.

[27] Wang, X., Zhao, Y., Wang, Z., et al., 2024. An ultrafast and robust structural damage identification framework enabled by an optimized extreme learning machine. Mechanical Systems and Signal Processing. 216, 111509.

[28] Zhou, L., Luo, Z., Pan, X., 2024. Machine learning-based system reliability analysis with Gaussian Process Regression. arXiv preprint. arXiv:2403.11125.

[29] Chen, Z., Fu, C., Wu, R., et al., 2023. LGFat-RGCN: Faster Attention with Heterogeneous RGCN for Medical ICD Coding Generation. Proceedings of the 31st ACM International Conference on Multimedia. 5428–5435.

[30] Xu, H., Shi, C., Fan, W., et al., 2024. Improving diversity and discriminability based implicit contrastive learning for unsupervised domain adaptation. Applied Intelligence. 1–11.

[31] Erke, S., Bin, D., Yiming, N., et al., 2020. An improved A-Star based path planning algorithm for autonomous land vehicles. International Journal of Advanced Robotic Systems. 17, 1729881420962263.

[32] Mirahadi, F., McCabe, B.Y., 2021. EvacuSafe: A real-time model for building evacuation based on Dijkstra's algorithm. Journal of Building Engineering. 34, 101687.

[33] Wu, Z., Meng, Z., Zhao, W., et al., 2021. Fast-RRT: A RRT-based optimal path finding method. Applied Sciences. 11, 11777.

[34] Zhang, Z., Wu, J., Dai, J., et al., 2020. A novel real-time penetration path planning algorithm for stealth UAV in 3D complex dynamic environment. IEEE Access. 8, 122757–122771.

[35] Segato, A., Di Marzo, M., Zucchelli, S., et al., 2021. Inverse reinforcement learning intra-operative path planning for steerable needle. IEEE Transactions on Biomedical Engineering. 69, 1995–2005.

[36] Qadir, Z., Ullah, F., Munawar, H.S., et al., 2021. Addressing disasters in smart cities through UAVs path planning and 5G communications: A systematic review. Computer Communications. 168, 114–135.

[37] Lee, M.-F.R., Yusuf, S.H., 2022. Mobile robot navigation using deep reinforcement learning. Processes. 10, 2748.

[38] Gupta, A., Anpalagan, A., Guan, L., et al., 2021. Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues. Array. 10, 100057.

[39] Neri, I., Dinarama, E., 2024. Cities' Match-Making: Fostering International Collaboration for Climate-Resilient Twins. The Routledge Handbook on Greening High-Density Cities. Routledge, 15–29.

[40] Torres, J.F., Hadjout, D., Sebaa, A., et al., 2021. Deep learning for time series forecasting: a survey. Big Data. 9, 3–21.

[41] Zhao, C., Zhu, Y., Du, Y., et al., 2022. A novel direct trajectory planning approach based on generative adversarial networks and rapidly-exploring random tree. IEEE Transactions on Intelligent Transportation Systems. 23, 17910–17921.

[42] Zhao, F., Yu, F., Trull, T., et al., 2023. A new method using LLMs for keypoints generation in qualitative data analysis. 2023 IEEE Conference on Artificial Intelligence (CAI). IEEE. 333–334.

[43] Li, J., Qiao, Y., Liu, S., et al., 2022. An improved YOLOv5-based vegetable disease detection method. Computers and Electronics in Agriculture. 202, 107345.

[44] Wang, X., Wang, S., Liang, X., et al., 2022. Deep reinforcement learning: A survey. IEEE Transactions on Neural Networks and Learning Systems. 35(4), 5064–5078.

[45] Zhao, J., Zhao, W., Deng, B., et al., 2023. Autonomous driving system: A comprehensive survey. Expert Systems with Applications. 122836.

[46] Zhang, L., Zhang, Y., Li, Y., 2020. Path planning for indoor mobile robot based on deep learning. Optik. 219, 165096.

[47] Aslan, M.F., Durdu, A., Sabanci, K., 2022. Visual-Inertial Image-Odometry Network (VIIONet): A Gaussian process regression-based deep architecture proposal for UAV pose estimation. Measurement. 194, 111030.

[48] Lee, D.-H., Liu, J.-L., 2023. End-to-end deep learning of lane detection and path prediction for real-time autonomous driving. Signal, Image and Video Processing. 17, 199–205.

[49] Gu, Y., Zhu, Z., Lv, J., et al., 2023. DM-DQN: Dueling Munchausen deep Q network for robot path planning. Complex & Intelligent Systems. 9, 4287–4300.

[50] Huang, R., Qin, C., Li, J.L., et al., 2023. Path planning of mobile robot in unknown dynamic continuous environment using reward-modified deep Q-network. Optimal Control Applications and Methods. 44, 1570–1587.

[51] Chen, L., Jiang, Z., Cheng, L., et al., 2022. Deep reinforcement learning based trajectory planning under uncertain constraints. Frontiers in Neurorobotics. 16, 883562.

Downloads

How to Cite

Chen, X., Gan, Y., & Xiong, S. (2024). Optimization of Mobile Robot Delivery System Based on Deep Learning. Journal of Computer Science Research, 6(4), 51–65. https://doi.org/10.30564/jcsr.v6i4.7197