Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance

2026-01-25

arXiv.org

AI Summary

This work addresses the lack of explicit energy consumption modeling in existing robotic manipulation approaches for infrastructure operation and maintenance, which often struggle to balance efficiency, generality, and long-term sustainability. The paper proposes an articulation-agnostic, energy-aware reinforcement learning framework that, for the first time, incorporates energy consumption as an explicit constraint in general articulated object manipulation tasks. By formulating the problem as a constrained Markov decision process, the approach integrates geometric perception with policy optimization through component-guided 3D perception, weighted point sampling, PointNet-based encoding, and a Lagrangian-based constrained Soft Actor-Critic algorithm. Evaluated on representative maintenance tasks, the method achieves 16%–30% lower energy consumption and 16%–32% fewer action steps while maintaining high success rates, significantly enhancing cross-object generalization and deployment sustainability.

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 objects. Manipulation is formulated as a Constrained Markov Decision Process (CMDP), in which actuation energy is explicitly modelled and regulated via a Lagrangian-based constrained Soft Actor-Critic scheme. The policy is trained end-to-end under this CMDP formulation, enabling effective articulated-object operation while satisfying a long-horizon energy budget. Experiments on representative O&M tasks demonstrate 16%-30% reductions in energy consumption, 16%-32% fewer steps to success, and consistently high success rates, indicating a scalable and sustainable solution for infrastructure O&M manipulation.

Problem

• energy-aware
• robotic manipulation
• articulated components
• infrastructure operation and maintenance
• actuation energy

Innovation

• energy-aware reinforcement learning
• articulated object manipulation
• constrained Markov decision process
• 3D geometric representation
• infrastructure operation and maintenance