PAMPC: Perception-Aware Model Predictive Control for Quadrotors

By Davide Falanga, Philipp Foehn, Peng Lu, Davide Scaramuzza. 2018

275 citations recorded by the source corpus.

We present the first perception-aware model predictive control framework for quadrotors that unifies control and planning with respect to action and perception objectives. Our framework leverages numerical optimization to compute trajectories that satisfy the system dynamics and require control inputs within the limits of the platform. Simultaneously, it optimizes perception objectives for robust and reliable sensing by maximizing the visibility of a point of interest and minimizing its velocity in the image plane. Considering both perception and action objectives for motion planning and control is challenging due to the possible conflicts arising from their respective requirements. For example, for a quadrotor to track a reference trajectory, it needs to rotate to align its thrust with the direction of the desired acceleration. However, the perception objective might require to minimize such rotation to maximize the visibility of a point of interest. A model-based optimization framework, able to consider both perception and action objectives and couple them through the system dynamics, is therefore necessary. Our perception-aware model predictive control framework works in a receding-horizon fashion by iteratively solving a non-linear optimization problem. It is capable of running in real-time, fully onboard our lightweight, small-scale quadrotor using a low-power ARM computer, together with a visual-inertial odometry pipeline. We validate our approach in experiments demonstrating (I) the conflict between perception and action objectives, and (II) improved behavior in extremely challenging lighting conditions.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing (2018, methodology): “2) Model Predictive Control: We formulate the control problem as a quadratic optimization problem which we solve using sequential quadratic programming as described in [3]:”
Learning high-speed flight in the wild (2021, background): “can be tracked by a model-predictive controller accurately [43, 44].”
Data-Driven MPC for Quadrotors (2021, methodology): “Very little work exists on agile control of quadrotors at speeds beyond 5ms−1 and accelerations above 2 g, [1]–[8].”
RAPTOR: Robust and Perception-Aware Trajectory Replanning for Quadrotor Fast Flight (2020, background): “Although much attention has been paid to planning with the awareness of localization [31]–[33] and target tracking [34, 35], less emphasis is put on environment perception.”