Autonomous Navigation of <i>AGV</i>s in Unknown Cluttered Environments: <i>Log-MPPI</i> Control Strategy
Ihab S. Mohamed, Kai Yin, Lantao Liu
Abstract
Sampling-based model predictive control ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPC</i> ) optimization methods, such as Model Predictive Path Integral ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPPI</i> ), have recently shown promising results in various robotic tasks. However, it might produce an infeasible trajectory when the distributions of all sampled trajectories are concentrated within high-cost even infeasible regions. In this study, we propose a new method called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">log-MPPI</i> equipped with a more effective trajectory sampling distribution policy which significantly improves the trajectory feasibility in terms of satisfying system constraints. The key point is to draw the trajectory samples from the normal log-normal ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">NLN</i> ) mixture distribution, rather than from Gaussian distribution. Furthermore, this work presents a method for collision-free navigation in unknown cluttered environments by incorporating the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2D</i> occupancy grid map into the optimization problem of the sampling-based <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MPC</i> algorithm. We first validate the efficiency and robustness of our proposed control strategy through extensive simulations of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2D</i> autonomous navigation in different types of cluttered environments as well as the cartpole swing-up task. We further demonstrate, through real-world experiments, the applicability of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">log-MPPI</i> for performing a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2D</i> grid-based collision-free navigation in an unknown cluttered environment, showing its superiority to be utilized with the local costmap without adding additional complexity to the optimization problem. A video demonstrating the real-world and simulation results is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://youtu.be/_uGWQEFJSN0</uri> .