Non-Prehensile Aerial Manipulation using Model-Based Deep Reinforcement Learning

TL;DR

This paper presents a model-based deep reinforcement learning approach for robust, non-prehensile aerial manipulation with UAVs, enabling effective object interaction in unknown environments without prior knowledge of object properties.

Contribution

The work introduces a novel model-based DRL method for UAV manipulation that learns environment dynamics and control policies simultaneously, improving robustness in unknown settings.

Findings

Successful push tasks with varying friction values

Repeatable behaviors across different environments

Effective learning of environment dynamics and control policies

Abstract

With the continual adoption of Uncrewed Aerial Vehicles (UAVs) across a wide-variety of application spaces, robust aerial manipulation remains a key research challenge. Aerial manipulation tasks require interacting with objects in the environment, often without knowing their dynamical properties like mass and friction a priori. Additionally, interacting with these objects can have a significant impact on the control and stability of the vehicle. We investigated an approach for robust control and non-prehensile aerial manipulation in unknown environments. In particular, we use model-based Deep Reinforcement Learning (DRL) to learn a world model of the environment while simultaneously learning a policy for interaction with the environment. We evaluated our approach on a series of push tasks by moving an object between goal locations and demonstrated repeatable behaviors across a range of friction values.