![[2602.12288] Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.12288] Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance
Summary
This paper presents an energy-aware reinforcement learning framework for robotic manipulation of articulated components in infrastructure operation and maintenance, achieving significant energy savings and efficiency improvements.
Why It Matters
As smart cities and intelligent infrastructure evolve, the need for efficient and energy-conscious robotic solutions becomes critical. This research addresses the limitations of existing methods by integrating energy considerations into robotic manipulation, paving the way for sustainable infrastructure management.
Key Takeaways
- Introduces an energy-aware reinforcement learning framework for robotic manipulation.
- Achieves 16%-30% reductions in energy consumption during operations.
- Demonstrates improved efficiency with 16%-32% fewer steps to task completion.
- Utilizes a Constrained Markov Decision Process to model actuation energy.
- Enhances scalability and sustainability in infrastructure operation and maintenance.
Electrical Engineering and Systems Science > Systems and Control arXiv:2602.12288 (eess) [Submitted on 25 Jan 2026] Title:Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance Authors:Xiaowen Tao, Yinuo Wang, Haitao Ding, Yuanyang Qi, Ziyu Song View a PDF of the paper titled Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance, by Xiaowen Tao and 4 other authors View PDF HTML (experimental) Abstract:With the growth of intelligent civil infrastructure and smart cities, operation and maintenance (O&M) increasingly requires safe, efficient, and energy-conscious robotic manipulation of articulated components, including access doors, service drawers, and pipeline valves. However, existing robotic approaches either focus primarily on grasping or target object-specific articulated manipulation, and they rarely incorporate explicit actuation energy into multi-objective optimisation, which limits their scalability and suitability for long-term deployment in real O&M settings. Therefore, this paper proposes an articulation-agnostic and energy-aware reinforcement learning framework for robotic manipulation in intelligent infrastructure O&M. The method combines part-guided 3D perception, weighted point sampling, and PointNet-based encoding to obtain a compact geometric representation that generalises across heterogeneous articulated...