Constrained energy efficiency optimization for robotic manipulators using neuro-dynamics approach

In the paper, a neurodynamic-based energy efficiency optimization strategy (NEE-OS) is proposed to decrease the energy expenditure of robotic manipulators. Different from the traditional approaches, the proposed NEE-OS integrates several necessary constrains from the environment and the robotic manipulator, which could affect energy consumptions of the robotic manipulator in engineering applications to a large extent. To handle the constraints formulated as equalities and inequalities, the energy efficiency optimization problem is converted into a constrained quadratic programming (QP) problem, which is solved using a linear variable inequality-based primal-dual neural network (PDNN) efficiently.