Receding Horizon Control in unknown environments: Experimental results

Abstract

This paper presents a novel approach to navigation in an a priori unknown, GPS-denied environment. The aim is to combine dynamic path planning with the ability to learn about the environment. The vehicle is tasked with autonomous travel from an uncertain initial position to an uncertain target, without prior mapping information. The environment is modelled using linear segments that represent boundaries between the estimated traversable and nontraversable regions. The approach integrates Receding Horizon Control (RHC) and Simultaneous Localisation and Mapping (SLAM). The control problem is formulated as a mixed integer linear program (MILP) and explicitly includes the obstacles and vehicle dynamics. We present the results of our experiments using Pioneer robots, as well as, simulation results which clearly demonstrated the impact of each component of the system.

Implementation of Fast MPC with a Quadrotor for Obstacle Avoidance

“…It is assumed that the MAV has a limited sensing radius and the MPC trajectory is constrained to remain within a currently-visible obstacle-free region. 18 The modified operating regions are shaped in order to maximize manoeuvring space in the direction of travel, but limited to only the observed free space. For good manoeuvrability in the direction of travel, the basic shape of the operating region is chosen to be a cone, expanding from the current position to the limit of the sensor visibility.…”