Imitation-Based Motion Planning and Control of a Multi-Section Continuum Robot Interacting With the Environment

Abstract

Recently, flexible robots are growing in importance owing to their merits over rigid robots in maneuverability and safety, which equips them to work in unstructured environments, such as occur in medical applications. However, motion planning and control of flexible manipulators is challenging due to their compliance behavior and system uncertainties. Thus, this letter presents an Imitation-based Motion Planning (IbMP) approach, along with dynamic impedance control for learning, planning, and trajectory tracking of a two-section soft continuum robot in a dynamic environment. Point-to-point motion demonstrations, including the robot's tip position and orientation are intuitively provided by a motion capture system (OptiTrack V120-trio) and a similar kinematic flexible interface. Additionally, a singularity-free dynamic model based on Lagrangian formulation and Taylor expansion series of a two-section continuum robot is derived while planning for robot motions. The simulation results show that the IbMP approach, along with the dynamic impedance control, generalizes the robot's motion by varying the initial and goal of the robot's tip pose while avoiding static and dynamic obstacles, and moving back to the desired track after disturbances. Finally, the stability and performance of the IbMP algorithm against input disturbances are assessed using a Monte Carlo approach that can guide the selection of gain values.