The week's pick
Random Articles
Reseach Article
Integrating Real-Time Visual Return Grading with Deep Reinforcement Learning for Sustainable Reverse Logistics
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 91 |
| Year of Publication: 2026 |
| Authors: Rahul Raj |
10.5120/ijca2026926620
|
Rahul Raj . Integrating Real-Time Visual Return Grading with Deep Reinforcement Learning for Sustainable Reverse Logistics. International Journal of Computer Applications. 187, 91 ( Mar 2026), 28-33. DOI=10.5120/ijca2026926620
Abstract
The exponential growth of e-commerce has intensified reverse logistics challenges, with product returns generating substantial carbon emissions through inefficient routing and processing. This research proposes an integrated architecture combining edge-deployed convolutional neural networks (CNNs) for real-time return quality assessment with Deep Reinforcement Learning (DRL) for carbon-aware dynamic routing optimization. The edge vision module classifies returned items into disposition categories with sub-second latency; these assessments feed directly into a DRL optimizer formulated as a Markov Decision Process (MDP). Simulation experiments on benchmark VRPSDP instances demonstrate 18–23% carbon emission reduction, 94.2% classification accuracy, and 67% lower decision latency compared to cloud-based alternatives. A six-month pilot with two retail partners validating 78,000 returns confirms operational viability with 99.2% system uptime. This is the first end-to-end framework integrating edge AI vision with DRL-based carbon-optimized routing for retail reverse logistics.
References
- Arvind, S. Srinivasan, K. Ramesh, and P. Kumar, "Intelligent Warehousing: A Machine Learning and IoT Framework for Precision Inventory Optimisation," IEEE Access, vol. 13, pp. 1–15, 2025. DOI: 10.1109/access.2025.3614679
- Y. Hou, L. Zhang, and X. Wang, "Vehicle Routing Model Based on Real-Time Road Conditions Considering Carbon Emissions," Proc. 2024 Int. Conf. NTCI, 2024, pp. 1–6. DOI: 10.1109/ntci64025.2024.10776332
- F. A. Santos, G. R. Mateus, and A. S. da Cunha, "Green Reverse Logistics: Exploring the VRPDDP," Omega — Int. J. Management Sci., vol. 118, art. 102864, 2023. DOI: 10.1016/j.omega.2023.102864
- Y. Cheng, X. Liu, and Z. Wang, "Low-Carbon Logistics Distribution Vehicle Routing Optimization Based on INNC-GA," Applied Sci., vol. 14, no. 7, art. 3061, 2024. DOI: 10.3390/app14073061
- S. Mandal, R. Kumar, and A. Sharma, "Implementation of AI Transportation Routing in Reverse Logistics to Reduce CO2 Footprint," Int. J. Supply Chain Management, vol. 13, no. 2, pp. 45–58, 2024. DOI: 10.47604/ijscm.3079
- W. Zou, Y. Chen, and H. Li, "Deep Reinforcement Learning-Based optimization of Reverse Logistics Transport in Closed-Loop Supply Chain," Proc. ICE – Transport, pp. 1–12, 2025. DOI: 10.1680/jtran.24.00163
- M. Younesse, A. Benali, and K. El Moutaouakil, "New Wave Logistics Framework: Enabling Sustainable Practices in Road Transportation," Proc. 2025 Int. Conf. ECAI, 2025. DOI: 10.1109/ecai65401.2025.11095484
- C. Giri, S. Jain, and M. K. Tiwari, "AI-Enabled Circular Supply Chain Framework for Sustainable Returns Management," 2025. [Preprint]
- S. Ullah, M. Ahmad, and F. Khan, "AI-Driven Intelligent Transportation for Sustainable Business Ecosystems," 2025. [Preprint]
- D. S. Juliet, "AI-Driven Smart Logistics Route Optimisation Using IoT and Machine Learning," Proc. 2025 Int. Conf. ICCSP, 2025. DOI: 10.1109/iccsp64183.2025.11089166
- Y. Qian, "Research on E-Commerce Smart Logistics Distribution Path optimization Based on AI," Proc. 2025 5th Int. Conf. ISCTT, 2025. DOI: 10.1109/isctt66403.2025.11137854
- E. van der Linden, N. Kempers, W. van Jaarsveld, and R. Dijkman, "Reinforcement Learning for Efficient Returns Management," arXiv:2501.14394, 2025. DOI: 10.48550/arxiv.2501.14394
- R. Sasikala, M. Priya, and S. Kumar, "Reducing Carbon Footprint with AI-Driven Logistics Planning," Advances in Computational Intelligence and Robotics, IGI Global, 2025, ch. 7. DOI: 10.4018/979-8-3693-9856-2.ch007
- O. O. Ilufoye, A. B. Adeyemi, and T. O. Ogunleye, "A Carbon Analytics Framework for Reducing Environmental Footprint in Retail Supply Chains," Eng. Tech. J., vol. 10, no. 8, 2025. DOI: 10.47191/etj/v10i08.19
- Y. Li, X. Zhang, and Q. Wang, "An Intelligent Distribution System for Green Logistics in the Blockchain Environment," Int. J. Logistics Res. Appl., pp. 1–18, 2023. DOI: 10.1080/13675567.2023.2289463
- S. Krishnamurthy, R. Patel, and A. Gupta, "Leveraging AI and ML to Optimize Retail Operations," DIRA Int. J., vol. 12, no. 3, 2024. DOI: 10.36676/dira.v12.i3.140
- J. C. Ferreira, A. L. Martins, and P. D. Gaspar, "Enhancing Sustainable Last-Mile Delivery: Impact of EVs and AI Optimisation," World Electric Vehicle J., vol. 16, no. 5, art. 242, 2025. DOI: 10.3390/wevj16050242
- G. Zahn, M. Spann, and B. Skiera, "The Smart Green Nudge: Reducing Product Returns through Enriched Digital Footprints and Causal Machine Learning," SSRN, 2022. DOI: 10.2139/ssrn.4262656
- A. Kulkarni, S. Mehta, and R. Sharma, "Utilising Gen AI and Computer Vision for Applications in the Retail Sector," J. AI and Cloud Computing, vol. 2, no. 2, 2023. DOI: 10.47363/jaicc/2023(2)181.
- F. Felder, M. Brossog, and J. Franke, "Smart Routing for Sustainable Supply Chain Networks: An AI and Knowledge Graph Driven Approach," Applied Sci., vol. 15, no. 14, art. 8001, 2025. DOI: 10.3390/app15148001
Index Terms
Keywords