Autonomous Aerial Robots Research Articles

Energy-Aware Hierarchical Reinforcement Learning Based on the Predictive Energy Consumption Algorithm for Search and Rescue Aerial Robots in Unknown Environments

Aerial robots (drones) offer critical advantages in missions where human participation is impeded due to hazardous conditions. Among these, search and rescue missions in disaster-stricken areas are particularly challenging due to the dynamic and unpredictable nature of the environment, often compounded by the lack of reliable environmental models and limited ground system communication. In such scenarios, autonomous aerial robots’ operation becomes essential. This paper introduces a novel hierarchical reinforcement learning-based algorithm to address the critical limitation of the aerial robot’s battery life. Central to our approach is the integration of a long short-term memory (LSTM) model, designed for precise battery consumption prediction. This model is incorporated into our HRL framework, empowering a high-level controller to set feasible and energy-efficient goals for a low-level controller. By optimizing battery usage, our algorithm enhances the aerial robot’s ability to deliver rescue packs to multiple survivors without the frequent need for recharging. Furthermore, we augment our HRL approach with hindsight experience replay at the low level to improve its sample efficiency.

UAVs for forestry: Metric-semantic mapping and diameter estimation with autonomous aerial robots

To properly monitor the growth of forests and administer effective methods for their cultivation, forestry researchers require access to quantitative metrics such as diameter at breast height and stem taper profile of trees. These metrics are tedious and labor-intensive to measure by hand, especially at the scale of vast forests with thick undergrowth. Autonomous mobile robots can help to scale up such operations and provide an efficient method to capture the data. We present a set of algorithms for autonomous navigation and fine-grained metric-semantic mapping with a team of aerial robots in under-canopy forest environments. Our autonomous UAV system has 3D flight capabilities and relies only on a LIDAR and an IMU for state estimation and mapping. This allows each robot to accurately navigate in challenging forest environments with drastic terrain changes regardless of illumination conditions. Our deep-learning-driven fine-grained metric-semantic mapping module is capable of detecting and extracting detailed information such as the position, orientation, and stem taper profile of trees. This map of tree trunks is represented as a set of sparse cylinder models. Our semantic place recognition module leverages this sparse representation to efficiently estimate the relative transformation between multiple robots, and merge their information to build a globally consistent large-scale map. This ultimately allows us to scale up operations with multiple robots. Our system is able to achieve a mean absolute error of 1.45 cm for diameter estimation and 13.2 cm for relative position estimation between a pair of robots after place recognition and map merging

ConservationBots: Autonomous aerial robot for fast robust wildlife tracking in complex terrains

AbstractRadio tagging and tracking are fundamental to understanding the movements and habitats of wildlife in their natural environments. Today, the most widespread, widely applicable technology for gathering data relies on experienced scientists armed with handheld radio‐telemetry equipment to locate low‐power radio transmitters attached to wildlife from the ground. Although aerial robots can transform labor‐intensive conservation tasks, the realization of autonomous systems for tackling task complexities under real‐world conditions remains a challenge. We developed ConservationBots—small aerial robots for tracking multiple, dynamic, radio‐tagged wildlife. The aerial robot achieves robust localization performance and fast task completion times—significant for energy‐limited aerial systems while avoiding close encounters with potential, counterproductive disturbances to wildlife. Our approach overcomes the technical and practical problems posed by combining a lightweight sensor with new concepts: (i) planning to determine both trajectory and measurement actions guided by an information‐theoretic objective, which allows the robot to strategically select near‐instantaneous range‐only measurements to achieve faster localization, and time‐consuming sensor rotation actions to acquire bearing measurements and achieve robust tracking performance; (ii) a bearing detector more robust to noise; and (iii) a tracking algorithm formulation robust to missed and false detections experienced in real‐world conditions. We conducted extensive studies: simulations built upon complex signal propagation over high‐resolution elevation data on diverse geographical terrains; field testing; studies with wombats (Lasiorhinus latifrons; nocturnal, vulnerable species dwelling in underground warrens) and tracking comparisons with a highly experienced biologist to validate the effectiveness of our aerial robot and demonstrate the significant advantages over the manual method.

Projection operator‐based robust adaptive control of an aerial robot with a manipulator

AbstractThis paper describes a quadcopter manipulator system, an aerial robot with an extended workspace, its controller design, and experimental validation. The aerial robot is based on a quadcopter with a three degree of freedom robotic arm connected to the base of the vehicle. The work aims to create a stable airborne robot with a robotic arm that can work above and below the airframe, regardless of where the arm is attached. Integrating a robotic arm into an underactuated, unstable system like a quadcopter can enhance the vehicle's functionality while increasing instability. To execute a mission with accuracy and reliability during a real‐time task, the system must overcome the inter‐coupling effects and external disturbances. This work presents a novel design for a robust adaptive feedback linearization controller with a model reference adaptive controller and hardware implementation of the quadcopter manipulator system with plant uncertainties. The closed‐loop stability of the aerial robot and the tracking error convergence with the robust controller is analyzed using Lyapunov stability analysis. The quadcopter manipulator system is custom developed in the lab with an off‐the‐shelf quadcopter and a 3D‐printed robotic arm. The robotic system architecture is implemented using a Jetson Nano companion computer for autonomous onboard flight. Experiments were conducted on quadcopter manipulator system to evaluate the autonomous aerial robot's stability and trajectory tracking with the proposed controller.

Motion Optimization and Control of Single and Multiple Autonomous Aerial, Land, and Marine Robots

Fast-paced developments in the fields of aerial, land, and marine robotics are steadily paving the way for a wide spectrum of scientific and commercial applications of autonomous vehicles with far-reaching societal implications [...].

Enhanced Decentralized Autonomous Aerial Robot Teams With Group Planning

Designing autonomous aerial robot team systems remains a grand challenge in robotics. Existing works in this field can be categorized as centralized and decentralized. Centralized methods suffer from scale dilemmas, while decentralized ones often lead to poor planning quality. In this paper, we propose an enhanced decentralized autonomous aerial robot team system with group planning. According to the spatial distribution of agents, the system dynamically divides the team into several groups and isolated agents. For conflicts within each group, we propose a novel coordination mechanism named group planning. The group planning consists of efficient multi-agent pathfinding (MAPF) and trajectory joint optimization, which can significantly improve planning quality and success rate. We demonstrate through simulations and real-world experiments that our method not only has applicability for a large-scale team but also has top-level planning quality

A Finite-Time Partial Integrated Guidance and Control Approach for Formation of Autonomous Aerial and Ground Robots

A Finite-Time Partial Integrated Guidance and Control Approach for Formation of Autonomous Aerial and Ground Robots

Cooperative Adaptive Model-Free Control With Model-Free Estimation and Online Gain Tuning.

In this article, a distributed adaptive model-free control algorithm is proposed for consensus and formation-tracking problems in a network of agents with completely unknown nonlinear dynamic systems. The specification of the communication graph in the network is incorporated in the adaptive laws for estimation of the unknown linear and nonlinear terms, and in the online updating of the elements in the main controller gain matrix. The decentralized control signal at each agent in the network requires information about the states of the leader agent, as well as the desired formation variables of the agents in a local coordinate frame. These two sets of variables are provided at each agent by utilizing two recently proposed distributed observers. It is shown that only a spanning-tree rooted at the leader agent is enough for the convergence and stability of the proposed cooperative control and observer algorithms. Two simulation studies are provided to evaluate the performance of the proposed algorithm in comparison with two state-of-the-art distributed model-free control algorithms. With lower control effort as well as fewer offline gain tuning, the same level of consensus errors is achieved. Finally, the application of the proposed solution is studied in the formation-tracking control of a team of autonomous aerial mobile robots via simulation results.

A general real-time optimization framework for polynomial-based trajectory planning of autonomous flying robots

This paper presents a general real-time, numerically stable optimization framework for time polynomial-based trajectory generation of autonomous aerial robots. The proposed general optimization framework (GOF) allows various optimization criteria for trajectory generation cost-function, such as minimizing the trajectory total length, time, and position derivatives. Minimizing position derivatives includes velocity, acceleration, jerk, and snap, or any combination of them. This study considers the quadrotor as the test platform. By exploiting tools from the calculus of variations, differential flatness property, and polynomial-based trajectories, the developed algorithm finds feasible trajectories without extensive computational sampling and iterative searching in the high-dimensional state space of quadrotor dynamics. The GOF includes a segment-wise gradient descent-like algorithm to iteratively decrease the allowed time of each segment individually so as to avoid getting stuck at a local minimum. The comparison analysis with existing methods validated the numerical stability and computational speed advantages of the proposed approach. It also shows that the algorithm is suitable for the real-time generation of high-performance long-range trajectories consisting of a large number of waypoints and high-order piecewise polynomials. An animated simulation of this work is available at https://youtu.be/E1AC1vyPqOE

Heterogeneous Autonomous Robotic System in Viticulture and Mariculture: Vehicles Development and Systems Integration.

There are activities in viticulture and mariculture that require extreme physical endurance from human workers, making them prime candidates for automation and robotization. This paper presents a novel, practical, heterogeneous, autonomous robotic system divided into two main parts, each dealing with respective scenarios in viticulture and mariculture. The robotic components and the subsystems that enable collaboration were developed as part of the ongoing HEKTOR project, and each specific scenario is presented. In viticulture, this includes vineyard surveillance, spraying and suckering with an all-terrain mobile manipulator (ATMM) and a lightweight autonomous aerial robot (LAAR) that can be used in very steep vineyards where other mechanization fails. In mariculture, scenarios include coordinated aerial and subsurface monitoring of fish net pens using the LAAR, an autonomous surface vehicle (ASV), and a remotely operated underwater vehicle (ROV). All robotic components communicate and coordinate their actions through the Robot Operating System (ROS). Field tests demonstrate the great capabilities of the HEKTOR system for the fully autonomous execution of very strenuous and hazardous work in viticulture and mariculture, while meeting the necessary conditions for the required quality and quantity of the work performed.

Autonomous Aerial Robot for High-Speed Search and Intercept Applications

In recent years, high-speed navigation and environment interaction in the context of aerial robotics has become a field of interest for several academic and industrial research studies. In particular, Search and Intercept (SaI) applications for aerial robots pose a compelling research area due to their potential usability in several environments. Nevertheless, SaI tasks involve a challenging development regarding sensory weight, onboard computation resources, actuation design, and algorithms for perception and control, among others. In this work, a fully autonomous aerial robot for high-speed object grasping has been proposed. As an additional subtask, our system is able to autonomously pierce balloons located in poles close to the surface. Our first contribution is the design of the aerial robot at an actuation and sensory level consisting of a novel gripper design with additional sensors enabling the robot to grasp objects at high speeds. The second contribution is a complete software framework consisting of perception, state estimation, motion planning, motion control, and mission control in order to rapidly and robustly perform the autonomous grasping mission. Our approach has been validated in a challenging international competition and has shown outstanding results, being able to autonomously search, follow, and grasp a moving object at 6 m/s in an outdoor environment.

Estimation of the Energy Consumption of an All-Terrain Mobile Manipulator for Operations in Steep Vineyards

A heterogeneous robotic system that can perform various tasks in the steep vineyards of the Mediterranean region was developed and tested as part of the HEKTOR—Heterogeneous Autonomous Robotic System in Viticulture and Mariculture—project. This article describes the design of hardware and an easy-to-use method for evaluating the energy consumption of the system, as well as, indirectly, its deployment readiness level. The heterogeneous robotic system itself consisted of a flying robot—a light autonomous aerial robot (LAAR)—and a ground robot—an all-terrain mobile manipulator (ATMM), composed of an all-terrain mobile robot (ATMR) platform and a seven-degree-of-freedom (DoF) torque-controlled robotic arm. A formal approach to describe the topology and parameters of selected vineyards is presented. It is shown how Google Earth data can be used to make an initial estimation of energy consumption for a selected vineyard. On this basis, estimates of energy consumption were made for the tasks of protective spraying and bud rubbing. The experiments were conducted in two different vineyards, one with a moderate slope and the other with a much steeper slope, to evaluate the proposed estimation method.

Air Learning: a deep reinforcement learning gym for autonomous aerial robot visual navigation

We introduce Air Learning, an open-source simulator, and a gym environment for deep reinforcement learning research on resource-constrained aerial robots. Equipped with domain randomization, Air Learning exposes a UAV agent to a diverse set of challenging scenarios. We seed the toolset with point-to-point obstacle avoidance tasks in three different environments and Deep Q Networks (DQN) and Proximal Policy Optimization (PPO) trainers. Air Learning assesses the policies’ performance under various quality-of-flight (QoF) metrics, such as the energy consumed, endurance, and the average trajectory length, on resource-constrained embedded platforms like a Raspberry Pi. We find that the trajectories on an embedded Ras-Pi are vastly different from those predicted on a high-end desktop system, resulting in up to 40% longer trajectories in one of the environments. To understand the source of such discrepancies, we use Air Learning to artificially degrade high-end desktop performance to mimic what happens on a low-end embedded system. We then propose a mitigation technique that uses the hardware-in-the-loop to determine the latency distribution of running the policy on the target platform (onboard compute on aerial robot). A randomly sampled latency from the latency distribution is then added as an artificial delay within the training loop. Training the policy with artificial delays allows us to minimize the hardware gap (discrepancy in the flight time metric reduced from 37.73% to 0.5%). Thus, Air Learning with hardware-in-the-loop characterizes those differences and exposes how the onboard compute’s choice affects the aerial robot’s performance. We also conduct reliability studies to assess the effect of sensor failures on the learned policies. All put together, Air Learning enables a broad class of deep RL research on UAVs. The source code is available at: https://github.com/harvard-edge/AirLearning.

Introducing autonomous aerial robots in industrial manufacturing

Although ground robots have been successfully used for many years in manufacturing, the capability of aerial robots to agilely navigate in the often sparse and static upper part of factories makes them suitable for performing tasks of interest in many industrial sectors. This paper presents the design, development, and validation of a fully autonomous aerial robotic system for manufacturing industries. It includes modules for accurate pose estimation without using a Global Navigation Satellite System (GNSS), autonomous navigation, radio-based localization, and obstacle avoidance, among others, providing a fully onboard solution capable of autonomously performing complex tasks in dynamic indoor environments in which all necessary sensors, electronics, and processing are on the robot. It was developed to fulfill two use cases relevant in many industries: light object logistics and missing tool search. The presented robotic system, functionalities, and use cases have been extensively validated with Technology Readiness Level 7 (TRL-7) in the Centro Bahía de Cádiz (CBC) Airbus D&S factory in fully working conditions.

Deep Reinforcement Learning for End-to-End Local Motion Planning of Autonomous Aerial Robots in Unknown Outdoor Environments: Real-Time Flight Experiments

Autonomous navigation and collision avoidance missions represent a significant challenge for robotics systems as they generally operate in dynamic environments that require a high level of autonomy and flexible decision-making capabilities. This challenge becomes more applicable in micro aerial vehicles (MAVs) due to their limited size and computational power. This paper presents a novel approach for enabling a micro aerial vehicle system equipped with a laser range finder to autonomously navigate among obstacles and achieve a user-specified goal location in a GPS-denied environment, without the need for mapping or path planning. The proposed system uses an actor–critic-based reinforcement learning technique to train the aerial robot in a Gazebo simulator to perform a point-goal navigation task by directly mapping the noisy MAV’s state and laser scan measurements to continuous motion control. The obtained policy can perform collision-free flight in the real world while being trained entirely on a 3D simulator. Intensive simulations and real-time experiments were conducted and compared with a nonlinear model predictive control technique to show the generalization capabilities to new unseen environments, and robustness against localization noise. The obtained results demonstrate our system’s effectiveness in flying safely and reaching the desired points by planning smooth forward linear velocity and heading rates.

Auto-Tuned Event-Based Perception Scheme for Intrusion Monitoring With UAS

This paper presents an asynchronous event-based scheme for automatic intrusion monitoring using Unmanned Aerial Systems (UAS). Event cameras are neuromorphic sensors that capture the illumination changes in the camera pixels with high temporal resolution and dynamic range. In contrast to conventional frame-based cameras, they are naturally robust against motion blur and lighting conditions, which make them ideal for outdoor aerial robot applications. The presented scheme includes two main perception components. First, an asynchronous event-based processing system efficiently detects intrusions by combining several asynchronous event-based algorithms that exploit the advantages of the sequential nature of the event stream. The second is an off-line training mechanism that adjusts the parameters of the event-based algorithms to a particular surveillance scenario and mission. The proposed perception system was implemented in ROS for on-line execution on board UAS, integrated in an autonomous aerial robot architecture, and extensively validated in challenging scenarios with a wide variety of lighting conditions, including day and night experiments in pitch dark conditions.

Study on Arbitrary Direction Navigation System for Autonomous Multirotor with Arbitrary Configuration of Rotors

In this paper, an autonomous aerial robot system with a multirotor mechanism is described, where the robot has an arbitrary configuration of rotors. To construct a navigation system for the arbitrary 3-axis direction, the static constraint conditions are treated as dynamic equilibrium, and the analytical solution of this formulation is obtained with regard to two terms, namely attitude and height control. Moreover, the obtained analytical solution is implemented as a proportional-integral-derivative controller such that the navigation control system is fused with the attitude and height control systems optimally. To confirm the efficacy of this constructed navigation control system, navigation experiments with arbitrary azimuth direction and height are executed for a manufactured trial quadrotor system as an aerial robot and the results are estimated.

Optimal Strategies for a Class of Multi-Player Reach-Avoid Differential Games in 3D Space

A multi-player reach-avoid differential game with autonomous aerial robots in the three dimensional space is studied. Two pursuers form a team to guard a target against an evader with the same speed as the pursuers. This letter provides the complete solution of this differential game that resides within a high-dimensional state space. The Barrier surface is characterized and the saddle-point strategies are synthesized and verified. Degeneration of the two-pursuer one-evader game into the one-on-one case is addressed and the corresponding strategies are obtained. Finally, several examples illustrate the robustness properties and the guarantees provided by the saddle-point strategies obtained in this letter.

Building the executive system of autonomous aerial robots using the Aerostack open-source framework

A variety of open-source software tools are currently available to help building autonomous mobile robots. These tools have proven their effectiveness in developing different types of robotic systems, but there are still needs related to safety and efficiency that are not sufficiently covered. This article describes recent advances in the Aerostack software framework to address part of these needs, which may become critical in the case of aerial robots. The article describes a software tool that helps to develop the executive system, an important component of the control architecture whose characteristics significantly affect the quality of the final autonomous robotic system. The presented tool uses an original solution for execution control that aims at simplifying mission specification and protecting against errors, considering also the efficiency needs of aerial robots. The effectiveness of the tool was evaluated by building an experimental autonomous robot. The results of the evaluation show that it provides significant benefits about usability and reliability with acceptable development effort and computational cost. The tool is based on Robot Operating System and it is publicly available as part of the last release of the Aerostack software framework (version 3.0).

Autonomous aerial robot using dual‐fisheye cameras

AbstractSafety is undoubtedly the most fundamental requirement for any aerial robotic application. It is essential to equip aerial robots with omnidirectional perception coverage to ensure safe navigation in complex environments. In this paper, we present a light‐weight and low‐cost omnidirectional perception system, which consists of two ultrawide field‐of‐view (FOV) fisheye cameras and a low‐cost inertial measurement unit (IMU). The goal of the system is to achieve spherical omnidirectional sensing coverage with the minimum sensor suite. The two fisheye cameras are mounted rigidly facing upward and downward directions and provide omnidirectional perception coverage: 360° FOV horizontally, 50° FOV vertically for stereo, and whole spherical for monocular. We present a novel optimization‐based dual‐fisheye visual‐inertial state estimator to provide highly accurate state‐estimation. Real‐time omnidirectional three‐dimensional (3D) mapping is combined with stereo‐based depth perception for the horizontal direction and monocular depth perception for upward and downward directions. The omnidirectional perception system is integrated with online trajectory planners to achieve closed‐loop, fully autonomous navigation. All computations are done onboard on a heterogeneous computing suite. Extensive experimental results are presented to validate individual modules as well as the overall system in both indoor and outdoor environments.