用局部优化法让机械臂省电25%，还更快更省资源。
Energy Consumption of Robotic Arm with the Local Reduction Method
- 通过调整运动参数实现局部能量优化。
- 仿真测试中节能最高达25%，优于MPC和遗传算法。
- 适合工业界追求高效低碳的场景，易与AI结合。
工业自动化中，机械臂能耗是影响运营成本和环境可持续性的关键问题。本研究探讨了局部减少法在优化机械系统能效方面的应用，该方法在不降低性能的前提下，通过精细化调整运动参数以减少能源消耗。基于三关节机械臂模型，在30秒内对抓取放置与轨迹跟踪等任务进行了仿真测试。结果表明，该方法相较传统方法（如模型预测控制MPC和遗传算法GA）最多可降低25%的能耗。相比MPC所需的高算力和GA的慢收敛速度，局部减少法展现出更强的实时适应性与计算效率。研究强调其可扩展性和简便性，适用于寻求可持续、低成本解决方案的产业。此外，该方法可无缝集成人工智能技术，进一步提升在动态复杂环境中的应用潜力。未来工作将拓展至真实场景，并引入基于AI的动态调优。
原文摘要 · Abstract (English)
Energy consumption in robotic arms is a significant concern in industrial automation due to rising operational costs and environmental impact. This study investigates the use of a local reduction method to optimize energy efficiency in robotic systems without compromising performance. The approach refines movement parameters, minimizing energy use while maintaining precision and operational reliability. A three-joint robotic arm model was tested using simulation over a 30-second period for various tasks, including pick-and-place and trajectory-following operations. The results revealed that the local reduction method reduced energy consumption by up to 25% compared to traditional techniques such as Model Predictive Control (MPC) and Genetic Algorithms (GA). Unlike MPC, which requires significant computational resources, and GA, which has slow convergence rates, the local reduction method demonstrated superior adaptability and computational efficiency in real-time applications. The study highlights the scalability and simplicity of the local reduction approach, making it an attractive option for industries seeking sustainable and cost-effective solutions. Additionally, this method can integrate seamlessly with emerging technologies like Artificial Intelligence (AI), further enhancing its application in dynamic and complex environments. This research underscores the potential of the local reduction method as a practical tool for optimizing robotic arm operations, reducing energy demands, and contributing to sustainability in industrial automation. Future work will focus on extending the approach to real-world scenarios and incorporating AI-driven adjustments for more dynamic adaptability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。