Digital Twin-Based Energy-Efficient Trajectory Optimization for Robotic Pick-and-Place Process Under Uncertain Payload

Robotic pick-and-place process is a typical robotic manufacturing process, which is widely used in many applications. In the meanwhile, sustainable manufacturing is being paid much attention and the energy consumption during the robotic pick-and-place process could be further improved to enhance the sustainability. However, the payload deployed on the industrial robot is always uncertain and the existing energy-efficient trajectory optimization method could not be dynamically used for this situation. In this paper, digital twin-based energy-efficient trajectory optimization for robotic pick-and-place process under uncertain load is proposed. The digital twin for robotic pick-and-place process under uncertain payload is firstly built. Afterwards, the proximal policy optimization algorithm is used to realize energy-efficient trajectory optimization under uncertain payload. Finally, case study is conducted to validate the proposed method. The results show the effectiveness of the digital twin model and the Proximal Policy Optimization algorithm in reducing the energy consumption of the robotic pick-and-place process, which improves the sustainability of robotic pick-and-place process.