Scene Understanding with Semantic Mapping Methods in Eldercare Companion Robots
Keywords:
Semantic Mapping, Scene Understanding, Eldercare Robots, Network Simulation, Autonomous SystemsAbstract
The rapid global demographic shift towards an aging population necessitates innovative solutions for elderly care, particularly the deployment of autonomous companion robots. A fundamental requirement for these robots is the ability to navigate and interact safely within domestic environments. Traditional geometric mapping provides obstacle avoidance but lacks the contextual awareness required for complex, human-centric tasks. This paper explores the critical intersection of semantic mapping methods and high-level scene understanding, utilizing extensive network simulation environments to evaluate performance in eldercare companion robots. By integrating advanced object recognition pipelines with spatial mapping algorithms within a simulated cloud-edge computing framework, this study isolates the effects of network latency, bandwidth constraints, and computational offloading on real-time cognitive processing. The research details how semantic mapping not only labels distinct geometries but fundamentally enables predictive scene understanding, allowing robots to anticipate elderly user needs, detect anomalies such as falls, and manage medication schedules. Through comprehensive network simulations, this paper demonstrates that a distributed architecture significantly improves semantic fidelity and contextual awareness while managing the computational limits of onboard robotic hardware. The findings offer a robust framework for developing the next generation of assistive robots capable of operating reliably in dynamic and unstructured domestic spaces.References
1. Archambault, J.; Côté, D.; Raynault, M.F. Early childhood education and care access for children from disadvantaged backgrounds: Using a framework to guide intervention. Early Child. Educ. J. 2020, 48, 345–352.
2. Manda, V.K.; Christy, V.; Hlali, A. Current Trends, Opportunities, and Futures Research Directions in Geospatial Technologies for Smart Cities. In Advances in Geospatial Technologies; Darwish, D., Chemingui, H., Eds.; IGI Global: Hershey, PA, USA, 2024; pp. 239–270.
3. Wang, Y.; Cui, Y.; Yang, Y.; Li, Z.; Cui, X. Multi-UAV Path Planning for Air-Ground Relay Communication Based on Mix-Greedy MAPPO Algorithm. Drones 2024, 8, 706.
4. Millman, A.; Roberts, M.; Walsh, A.; Blomquist, W. Not whether to coordinate, but how: Concerns and mechanism choice under a mandate for inter-agency coordination. Perspect. Public Manag. Gov. 2024, 7, 60–74.
5. Crescenzi, R.; Giua, M. The EU Cohesion Policy in context: Does a bottom-up approach work in all regions? Environ. Plan. A Econ. Space 2016, 48, 2340–2357.
6. Wang, Q.; Xu, W.; Chen, H.-H. A Heterogeneous-Agent Deep Reinforcement Learning Approach for Dynamic Spectrum Access in Cognitive Wireless Networks. IEEE Trans. Cogn. Commun. Netw. 2025, 12, 2221–2235.
7. Mahmood, A.; Abdallah, A.M.; Baharom, B.B.; Habilah, A.S.K. Ensuring Satellite Operational Integrity: A Power Budget Analysis for Next Generation Satellites. IEEE Access 2025, 13, 44901–44911.
8. Hu, Z.; Liu, X.; Guo, M.; Liu, C. PPO-Based Joint Task Offloading and Resource Allocation for Vehicular Edge Computing Via V2I and V2V Communications. In Proceedings of the 2025 13th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC), Chengdu, China, 28–29 June 2025; pp. 316–321.
9. Li, S.; Huang, Q.; Chen, H.; Jiang, R.; Dong, M.; Ota, K.; Quek, T.Q.S. DRL-Based Joint Task Offloading and Resource Allocation in Air-Ground Integrated Vehicular Edge Computing Network with Energy Harvesting. IEEE Trans. Veh. Technol. 2025, 75, 6658–6672.
10. Bereketeab, L.; Zekeria, A.; Aloqaily, M.; Guizani, M.; Debbah, M. Energy Optimization in Sustainable Smart Environments with Machine Learning and Advanced Communications. IEEE Sens. J. 2024, 24, 5704–5712.
11. Jiao, L.; Shao, Y.; Sun, L.; Liu, F.; Yang, S.; Ma, W.; Li, L.; Liu, X.; Hou, B.; Zhang, X.; et al. Advanced Deep Learning Models for 6G: Overview, Opportunities, and Challenges. IEEE Access 2024, 12, 133245–133314.
12. Bai, W.; Zheng, G.; Xia, W.; Mu, Y.; Xue, Y. Multi-User Opportunistic Spectrum Access for Cognitive Radio Networks Based on Multi-Head Self-Attention and Multi-Agent Deep Reinforcement Learning. Sensors 2025, 25, 2025.
13. Xie, W.; Yang, H.; Xiong, Z. Resource Allocation for UAV-Assisted Anti-Jamming Semantic D2D Networks: A Graph Reinforcement Learning Approach. Comput. Netw. 2025, 269, 111463.
14. World Health Organization (WHO).
2025. Available online: https://www.who.int/health-topics/one-health#tab=tab_1 (accessed on 22 November 2025).
15. Available online: https://www.who.int/publications/m/item/one-health-definitions-and-principles (accessed on 22 November 2025).
16. Life Cycle Assessment (LCA).
2022. Available online: https://pre-sustainability.com/articles/life-cycle-assessment-lca-basics/ (accessed on 22 November 2025).
17. Hodge, N. How to Address Low-Probability, High-Impact Risks. Risk Manag. 2021, 68, 26–29.
18. Xu, J.; Zhao, Z.; Wang, L.; Zhang, Y. A Novel Deep Reinforcement Learning Architecture for Dynamic Power and Bandwidth Allocation in Multibeam Satellites. Acta Astronaut. 2023, 204, 73–82.
19. Sadiki, A.; Bentahar, J.; Dssouli, R.; En-Nouaary, A.; Otrok, H. Deep Reinforcement Learning for the Computation Offloading in MIMO-Based Edge Computing. Ad Hoc Netw. 2023, 141, 103080.
20. Zhang, Y.; Joe, I. The Optimized Deployment of Service Function Chain Based on Deep Reinforcement Learning Algorithm. In Proceedings of the International Conference on Machine Learning, Pattern Recognition and Automation Engineering, Singapore, 7–9 August 2024; ACM: New York, NY, USA, 2024; pp. 24–28.
21. Foerster, J.N.; Assael, Y.M.; de Freitas, N.; Whiteson, S. Learning to Communicate with Deep Multi-Agent Reinforcement Learning. In Advances in Neural Information Processing Systems 29 (NeurIPS 2016), Barcelona, Spain, 5–10 December 2016; Curran Associates, Inc.: Red Hook, NY, USA, 2016; pp. 2137–2145.
22. Maciel, F.; De Souza, A.M.; Bittencourt, L.F.; Villas, L.A. Resource Aware Client Selection for Federated Learning in IoT Scenarios. In Proceedings of the 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT); IEEE: Piscataway, NJ, USA, 2023; pp. 1–8.
23. Zhen, Y.; Tao, L.; Wu, D.; Tang, T.; Wang, R. Energy-Saving Control Strategy for Ultra-Dense Network Base Stations Based on Multi-Agent Reinforcement Learning. Digit. Commun. Netw. 2025, 11, 1007–1017.
24. Cui, H. Evaluating the Performance Metrics of PPO, DQN, and DDPG in Continuous Control Tasks. ITM Web Conf. 2025, 78, 01009.
25. Sefati, S.S.; Haq, A.U.; Nidhi; Craciunescu, R.; Halunga, S.; Mihovska, A.; Fratu, O. A Comprehensive Survey on Resource Management in 6G Network Based on Internet of Things. IEEE Access 2024, 12, 113741–113784.
26. Zhang, Q.; Fu, S.; Yang, Z. Jointly Optimizing Satellite Handover and Power Allocation in LEO Satellite Network: A Dual-Agent Framework. IEEE Trans. Veh. Technol. 2026, 1–6.
27. Chen, A.C.H.; Jia, W.-K.; Hwang, F.-J.; Liu, G.; Song, F.; Pu, L. Machine Learning and Deep Learning Methods for Wireless Network Applications. EURASIP J. Wirel. Commun. Netw. 2022, 2022, 115.
28. Zhang, C.; Wu, C.; Lin, M.; Lin, Y.; Liu, W. Proximal Policy Optimization for Efficient D2D-Assisted Computation Offloading and Resource Allocation in Multi-Access Edge Computing. Future Internet 2024, 16, 19.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are distributed under the Creative Commons Attribution 4.0 International License (CC BY 4.0), unless otherwise stated.
