Recently non-linear control methods like Model Predictive Control (MPC) and Reinforcement Learning (RL) have attracted increased interest in the quadrotor control community. In contrast to classic control methods like cascaded PID controllers, MPC and RL heavily rely on an accurate model of the system dynamics. The process of quadrotor system identification is notoriously tedious and is often pursued with additional equipment like a thrust stand. Furthermore, low-level details like motor delays which are crucial for accurate end-to-end control are often neglected. In this work, we introduce a data-driven method to identify a quadrotor’s inertia parameters, thrust curves, torque coefficients, and first-order motor delay purely based on proprioceptive data. The estimation of the motor delay is particularly challenging as usually, the RPMs can not be measured. We derive a Maximum A Posteriori (MAP)-based method to estimate the latent time constant. Our approach only requires about a minute of flying data that can be collected without any additional equipment and usually consists of three simple maneuvers. Experimental results demonstrate the ability of our method to accurately recover the parameters of multiple quadrotors. It also facilitates the deployment of RL-based, end-to-end quadrotor control of a large quadrotor under harsh, outdoor conditions.

In the following, we analyze and discuss the implementation of a novel approach for distributed flocking behavior applied to a group of Uncrewed Aerial Vehicle (UAV)s, also referred to as drones. Inspired by natural flocking phenomena observed in birds, which demonstrate coordinated movement in response to internal and external stimuli, we tackle the problem of robust and dynamic aerial motion for robots and design a control law based on a novel physical model. In contrast to previous works that rely on velocity or position-based references, this approach leverages an acceleration-based law to describe the collective dynamics of many interacting particles. As observed in the following, a third-order control possesses several advantages compared to first or second-order control, such as smoother transitions, better force balancing, and more responsive and dynamic behaviors. These advantages are thoroughly analyzed in the following, thanks to physics-based realistic simulations and field experiments with medium-sized UAVs in an unstructured outdoor environment.

Deep Reinforcement Learning (RL) can yield capable agents and control policies in several domains but is commonly plagued by prohibitively long training times. Additionally, in the case of continuous control problems, the applicability of learned policies on real-world embedded devices is limited due to the lack of real-time guarantees and portability of existing libraries. To address these challenges, we present RLtools, a dependency-free, header-only, pure C++ library for deep supervised and reinforcement learning. Its novel architecture allows RLtools to be used on a wide variety of platforms, from HPC clusters over workstations and laptops to smartphones, smartwatches, and microcontrollers. Specifically, due to the tight integration of the RL algorithms with simulation environments, RL can solve popular RL problems up to 76 times faster than other popular RL frameworks. We also benchmark the inference on a diverse set of microcontrollers and show that in most cases our optimized implementation is by far the fastest. Finally, RLtools enables the first-ever demonstration of training a deep RL algorithm directly on a microcontroller, giving rise to the field of TinyRL. The source code as well as documentation and live demos are available through our project page at https://rl.tools.

In a swarm of unmanned aerial (UAVs) or ground vehicles (UGVs), nodes can autonomously coordinate their activities and cooperate to accomplish a given task as for instance the data exchange with Internet of Things (IoT) devices. However, due to the unpredictable environmental conditions, wireless communication on the air-to-air, ground-to-air and ground-to-ground links can experience completely different channel conditions. For this reason, several Machine-to-Machine (M2M) communication technologies have been proposed with different Quality of Service (QoS) characteristics in terms of range, bandwidth and energy consumption profile: at the same time, new challenges have arisen from the integration or joint utilization of multiple M2M stacks in heterogeneous robotic environments. In this work, we address such challenges through the design and development of a new framework, called Uhura, that eases the interaction among heterogeneous devices e.g., aerial platforms, ground vehicles, robots, sensors, and more. The Uhura framework provides communication facilities for swarm of UAVs/UGVs by abstracting from the underlying M2M technologies; in addition, it supports automatic selection of the M2M stack on multi-adapter UAVs/UGVs based on QoS requirements of the application. In this paper, we describe the Uhura architecture and its ROS-based implementation. Also, we report some results of two real-world experiments involving (i) a small swarm of UAVs and (ii) a multi-adapter UAV communicating to a ground IoT gateway.

Potential field approaches have been often used to describe and model interactions within a swarm of robots performing collective motion, also called flocking. Despite the high number of proposed approaches, most have only been tested in simulation and among the minority tested on real robots, even fewer abandoned the laboratory boundaries in favor of real-world scenarios. In this work, we propose a decentralized flocking approach that builds over the classical potential field models and that is proved to work well both in simulated and real-world environments. Each robot in the swarm relies on limited information and can only perceive its local neighbors through limited communication of noisy position information. No information on individual drone orientations, velocities, or accelerations is exchanged or needed. The novel experimental achievement of this paper is the realization of collective motion in three dimensions with the above sensing limitations. The swarm dynamically adapts to the environment by keeping a preferred distance from the ground and by changing formation. To show the general applicability of the proposed control algorithm, we study how it performs with the use of different potential functions proposed in the literature and by comparing them via extensive evaluation of the results in a realistic simulated environment. Lastly, we compare the performances of the proposed approach and of the different potentials on a real-drone swarm of up to fourteen robots flying both in two and three dimensional formations and in a challenging outdoor environment.

Robotics is expected to play a major role in the agricultural domain, and often multi-robot systems and collaborative approaches are mentioned as potential solutions to improve efficiency and system robustness. Among the multi-robot approaches, swarm robotics stresses aspects like flexibility, scalability and robustness in solving complex tasks, and is considered very relevant for precision farming and large-scale agricultural applications. However, swarm robotics research is still confined into the lab, and no application in the field is currently available. In this paper, we describe a roadmap to bring swarm robotics to the field within the domain of weed control problems. This roadmap is implemented within the experiment SAGA, founded within the context of the ECORD++ EU Project. Together with the experiment concept, we introduce baseline results for the target scenario of monitoring and mapping weed in a field by means of a swarm of UAVs.

The demands from precision agriculture (PA) for high-quality information at the individual plant level require to re-think the approaches exploited to date for remote sensing as performed by unmanned aerial vehicles (UAVs). A swarm of collaborating UAVs may prove more efficient and economically viable compared to other solutions. To identify the merits and limitations of a swarm intelligence approach to remote sensing, we propose here a decentralised multi-agent system for a field coverage and weed mapping problem, which is efficient, intrinsically robust and scalable to different group sizes. The proposed solution is based on a reinforced random walk with inhibition of return, where the information available from other agents (UAVs) is exploited to bias the individual motion pattern. Experiments are performed to demonstrate the efficiency and scalability of the proposed approach under a variety of experimental conditions, accounting also for limited communication range and different routing protocols.