--Successful aerial manipulation largely depends on how effectively a controller can tackle the coupling dynamic forces between the aerial vehicle and the manipulator . However, this control problem has remained largely unsolved as the existing control approaches either require precise knowledge of the aerial vehicle/manipulator inertial couplings, or neglect the state-dependent uncertainties especially arising during the interaction phase. This work proposes an adaptive control solution to overcome this long standing control challenge without any a priori knowledge of the coupling dynamic terms. Additionally, in contrast to the existing adaptive control solutions, the proposed control framework is modular, that is, it allows independent tuning of the adaptive gains for the vehicle position sub-dynamics, the vehicle attitude sub-dynamics, and the manipulator sub-dynamics. Stability of the closed loop under the proposed scheme is derived analytically, and real-time experiments validate the effectiveness of the proposed scheme over the state-of-the-art approaches. I. INTRODUCTION An Unmanned Aerial Manipulator (UAM) is a coupled system where a quadrotor (or multirotor) vehicle carries a manipulator: the presence of the manipulator greatly improves the dexterity and flexibility of the quadrotor, making it capable to accomplish a wide range of tasks, from simple payload transportation to more complex tasks such as pick and place, contact-based inspection, grasping and assembling etc. [1]-[8]. This work was supported in part by "Aerial Manipulation" under IHFC grand project (GP/2021/DA/032), in part by "Capacity building for human resource development in Unmanned Aircraft System (Drone and related Technology)", MeiTY, India, in part by the Natural Science Foundation of China grants 62233004 and 62073074, and in part by Jiangsu Provincial Scientific Research Center of Applied Mathematics grant BK20233002.

Planning and reinforcement learning are two key approaches to sequential decision making. Multi-step approximate real-time dynamic programming, a recently successful algorithm class of which AlphaZero [Silver et al., 2018] is an example, combines both by nesting planning within a learning loop. However, the combination of planning and learning introduces a new question: how should we balance time spend on planning, learning and acting? The importance of this trade-off has not been explicitly studied before. We show that it is actually of key importance, with computational results indicating that we should neither plan too long nor too short. Conceptually, we identify a new spectrum of planning-learning algorithms which ranges from exhaustive search (long planning) to model-free RL (no planning), with optimal performance achieved midway.