Complex contact-rich insertion is a ubiquitous robotic manipulation skill and usually involves nonlinear and low-clearance insertion trajectories as well as varying force requirements. A hybrid trajectory and force learning framework can be utilized to generate high-quality trajectories by imitation learning and find suitable force control policies efficiently by reinforcement learning. However, with the mentioned approach, many human demonstrations are necessary to learn several tasks even when those tasks require topologically similar trajectories. Therefore, to reduce human repetitive teaching efforts for new tasks, we present an adaptive imitation framework for robot manipulation. The main contribution of this work is the development of a framework that introduces dynamic movement primitives into a hybrid trajectory and force learning framework to learn a specific class of complex contact-rich insertion tasks based on the trajectory profile of a single task instance belonging to the task class. Through experimental evaluations, we validate that the proposed framework is sample efficient, safer, and generalizes better at learning complex contact-rich insertion tasks on both simulation environments and on real hardware.

Complex assembly tasks involve nonlinear and low-clearance insertion trajectories with varying contact forces at different stages. For a robot to solve these tasks, it requires a precise and adaptive controller which conventional force control methods cannot provide. Imitation learning is a promising method for learning controllers that can solve the nonlinear trajectories from human demonstrations without needing to explicitly program them into the robot. However, the force profiles obtain from human demonstration via tele-operation tend to be sub-optimal for complex assembly tasks, thus it is undesirable to imitate such force profiles. Reinforcement learning learns adaptive control policies through interactions with the environment but struggles with low sample efficiency and equipment tear and wear in the physical world. To address these problems, we present a combined learning-based framework to solve complex robotic assembly tasks from human demonstrations via hybrid trajectory learning and force learning. The main contribution of this work is the development of a framework that combines imitation learning, to learn the nominal motion trajectory, with a reinforcement learning-based force control scheme to learn an optimal force control policy, which can satisfy the nominal trajectory while adapting to the force requirement of the assembly task. To further improve the imitation learning part, we develop a hierarchical architecture, following the idea of goal-conditioned imitation learning, to generate the trajectory learning policy on the skill level offline. Through experimental validations, we corroborate that the proposed learning-based framework can generate high-quality trajectories and find suitable force control policies which adapt to the tasks' force requirements more efficiently.

Skillful motions in the actual assembly process are challenging for the robot to generate with conventional motion planning approaches because some states during the human assembly can be too skillful to realize automatically due to the narrow passage. To deal with this problem, this paper develops a motion planning method using the human demonstration, which can be applied to complete skillful motions in the robotic assembly process. To demonstrate conveniently without redundant third-party devices, we attach augmented reality (AR) markers to the manipulated object to track and capture its poses during the human demonstration. To overcome the problem brought by the coarse resolution of the vision system, we extract the most important key poses from the demonstration data and employ them as clues to execute motion planning to suit the target precise task. As for the selection of key poses, two policies are compared, where the first and the second derivative of the main changing parameter of every key pose serve as criteria to determine the priority of utilizing key poses. Besides, a solution to deal with colliding key poses is also proposed. The effectiveness of the presented method is verified through some simulation examples and actual robot experiments.

Complex and skillful motions in actual assembly process are challenging for the robot to generate with existing motion planning approaches, because some key poses during the human assembly can be too skillful for the robot to realize automatically. In order to deal with this problem, this paper develops a motion planning method using skillful motions from demonstration, which can be applied to complete robotic assembly process including complex and skillful motions. In order to demonstrate conveniently without redundant third-party devices, we attach augmented reality (AR) markers to the manipulated object to track and capture poses of the object during the human assembly process, which are employed as key poses to execute motion planning by the planner. Derivative of every key pose serves as criterion to determine the priority of use of key poses in order to accelerate the motion planning. The effectiveness of the presented method is verified through some numerical examples and actual robot experiments.