Predictive Kinematic Coordinate Control for Aerial Manipulators based on Modified Kinematics Learning

TL;DR

This paper tackles the problem of achieving high-precision end-effector control for aerial manipulators by integrating a learning-based modified kinematic model with a model predictive control scheme that allocates weights to coordinate quadcopter and manipulator motions. The core contributions are a two-submodel kinematic framework that accounts for closed-loop dynamics via an equivalent quadcopter model and online residual learning, and an MPC with a weight-allocation strategy that dynamically shifts emphasis between flight and manipulation to maintain precision within a learning space. Empirical results in simulation show a substantial reduction in tracking error (up to 59.6% over a baseline integral model) and successful moving-target tracking with robust mode switching between flight, hover, and coordinated modes. The approach promises practical benefits for aerial manipulation, though future work is needed to validate on physical hardware and further enhance residual learning while sustaining real-time MPC performance.

Abstract

High-precision manipulation has always been a developmental goal for aerial manipulators. This paper investigates the kinematic coordinate control issue in aerial manipulators. We propose a predictive kinematic coordinate control method, which includes a learning-based modified kinematic model and a model predictive control (MPC) scheme based on weight allocation. Compared to existing methods, our proposed approach offers several attractive features. First, the kinematic model incorporates closed-loop dynamics characteristics and online residual learning. Compared to methods that do not consider closed-loop dynamics and residuals, our proposed method has improved accuracy by 59.6$\%$. Second, a MPC scheme that considers weight allocation has been proposed, which can coordinate the motion strategies of quadcopters and manipulators. Compared to methods that do not consider weight allocation, the proposed method can meet the requirements of more tasks. The proposed approach is verified through complex trajectory tracking and moving target tracking experiments. The results validate the effectiveness of the proposed method.

Figures (4)

• Figure 1: Schematic of the MPC with learning based modified kinematic model.
• Figure 2: Different mode of the Aerial Manipulator. The red and blue circles represent State Transition Boundaries.
• Figure 3: The results of the complex trajectory tracking experiment.
• Figure 4: The results of the moving target tracking experiment.