This letter introduces a novel control method for the underactuated triple pendulum robot (UTPR), allowing it to maintain balance while controlling the end-effector motion in the operational space. The UTPR is influenced by gravity in the vertical plane, with the first joint being passive (underactuated) and the rest being active (actuated). Previous research primarily focused on controlling end-effector motion within a gravity-free plane or investigating pendulum swing-up motion under gravity's influence. This letter proposes a novel dynamic model that includes the dynamics of the center of mass (CoM) and the operational space, describing the exact balancing physical processes of the system. Based on the new dynamic model and analysis of its inherent constraints, we derive the relationship between angular momentum and the CoM and design an effective operational space and balancing controller. Due to underactuation, a Quadratic Programming (QP) based controller is devised to minimize the error between the desired acceleration commands and actual accelerations. Simulation results demonstrate that the proposed method enables the system's end-effector to maintain stability at the task point and under external force disturbance and achieves excellent trajectory tracking.
This paper addresses the challenge of balance control for the underactuated triple pendulum robot (UTPR) using a model-free reinforcement learning (RL) strategy. A curriculum-based Soft Actor-Critic strategy, with a quadratic form and an integral term in the reward function (CSAC-QI), is proposed. By incorporating the integral of cumulative joint angle errors into the reward function, the CSAC-QI method significantly reduces steady-state errors and enhances control precision. CSAC-QI improves convergence efficiency through an adaptive curriculum learning (CL) framework that enables a structured transition from simpler to more complex tasks. To enhance control robustness, motor friction identification and domain randomization are implemented during training, thereby equipping the UTPR to cope with real-world uncertainties. Simulation experiments demonstrate superior performance of the CSAC-QI method in handling larger initial joint deviations, achieving accurate end-effector positioning, and maintaining balance under dynamic randomization, sensor noise, and external disturbances. Notably, the trained policy is directly deployed on the UTPR prototype, where it successfully maintains balance in real-world conditions.