Autonomous Navigation of AGV s in Unknown Cluttered Environments: Log-MPPI Control Strategy
Ihab S. Mohamed, Kai Yin, Lantao Liu · IEEE Robotics and Automation Letters · 2022
Sampling-based model predictive control (MPC) optimization methods, such as Model Predictive Path Integral (MPPI), 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 calledlog-MPPIequipped 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 (NLN) mixture distribution, rather than from Gaussian distribution. Furthermore, this work presents a method for collision-free navigation in unknown cluttered environments by incorporating the2Doccupancy grid map into the optimization problem of the sampling-basedMPCalgorithm. We first validate the efficiency and robustness of our proposed control strategy through extensive simulations of2Dautonomous navigation in different types of cluttered environments as well as the cartpole swing-up task. We further demonstrate, through real-world experiments, the applicability oflog-MPPIfor performing a2Dgrid-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 athttps://youtu.be/_uGWQEFJSN0.