Agilicious: Open-source and open-hardware agile quadrotor for vision-based flight

  title={Agilicious: Open-source and open-hardware agile quadrotor for vision-based flight},
  author={Philipp Foehn and Elia Kaufmann and Angel Romero and Robert Pěni{\vc}ka and Sihao Sun and Leonard Bauersfeld and T. M. Laengle and Giovanni Cioffi and Yunlong Song and Antonio Loquercio and Davide Scaramuzza},
  journal={Science Robotics},
Autonomous, agile quadrotor flight raises fundamental challenges for robotics research in terms of perception, planning, learning, and control. A versatile and standardized platform is needed to accelerate research and let practitioners focus on the core problems. To this end, we present Agilicious, a codesigned hardware and software framework tailored to autonomous, agile quadrotor flight. It is completely open source and open hardware and supports both model-based and neural network–based… 

Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms

Real-time Neural MPC is presented, a framework to integrate large, complex neural network architectures as dynamics models within a model-predictive control pipeline and shows the feasibility of the framework on real-world problems by reducing the positional tracking error.

Time-Optimal Online Replanning for Agile Quadrotor Flight

In this paper, we tackle the problem of flying a quadrotor using time-optimal control policies that can be replanned online when the environment changes or when encountering unknown disturbances.

User-Conditioned Neural Control Policies for Mobile Robotics

It is demonstrated in simulation and in real-world experiments that a single control policy can achieve close to time-optimal quadrotor performance across the entire performance envelope of the robot, reaching up to 60 km/h and 4.5g in acceleration.

Learning Minimum-Time Flight in Cluttered Environments

We tackle the problem of minimum-time flight for a quadrotor through a sequence of waypoints in the presence of obstacles while exploiting the full quadrotor dynamics. Early works relied on

Learning Perception-Aware Agile Flight in Cluttered Environments

This work proposes a method to learn neural network policies that achieve perception-aware, minimum-time in cluttered environments and demonstrates the closed-loop control performance using a physical quadrotor and hardware-in-the- loop simulation at speeds up to 50km h − 1.

Minimum-Time Quadrotor Waypoint Flight in Cluttered Environments

We tackle the problem of planning a minimum-time trajectory for a quadrotor over a sequence of specified waypoints in the presence of obstacles while exploiting the full quadrotor dynamics. This

Learned Inertial Odometry for Autonomous Drone Racing

This work proposes a learning- based odometry algorithm that uses an inertial measurement unit (IMU) as the only sensor modality for autonomous drone racing tasks and shows that the system is comparable to a visual-inertial odometry solution that uses a camera and exploits the known gate location and appearance.

Virtual Reality via Object Poses and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilities

A novel telepresence system for advancing aerial manipulation in dynamic and unstructured environments that not only features a haptic device, but also a virtual reality (VR) interface that provides real-time 3D displays of the robot’s workspace as well as a haaptic guidance to its remotely located operator.

Weighted Maximum Likelihood for Controller Tuning

A probabilistic Policy Search method—Weighted Maximum Likelihood (WML)— is leveraged to automat- ically learn the optimal objective for MPCC, and is validated in the real world, where it outperforms both the previous manually tuned controller and the state-of-the-art auto-tuning baseline reaching speeds of 75 km/h.



Crazyflie 2.0 quadrotor as a platform for research and education in robotics and control engineering

Promising, preliminary results obtained in control of flying robot by pointing device (positioner) and with the support of a vision system, which basis only on a single Kinect sensor are outlined.

An Open Source and Open Hardware Deep Learning-Powered Visual Navigation Engine for Autonomous Nano-UAVs

This work presents what is, to the best of the knowledge, the first 27g nano-UAV system able to run aboard an end-to-end, closed-loop visual pipeline for autonomous navigation based on a state-of-the-art deep-learning algorithm, built upon the open-source CrazyFlie 2.0 nano-quadrotor.

A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones

This paper presents the first (to the best of the knowledge) demonstration of a navigation engine for autonomous nano-drones capable of closed-loop end-to-end DNN-based visual navigation, and develops a complete methodology for parallel execution of complex DNNs directly on board resource-constrained milliwatt-scale nodes.

Autonomous Quadrotor Flight Despite Rotor Failure With Onboard Vision Sensors: Frames vs. Events

This letter proposes the first algorithm that combines fault-tolerant control and onboard vision-based state estimation to achieve position control of a quadrotor subjected to complete failure of one rotor, and believes it will render autonomous quadrotors safer in both GPS denied or degraded environments.

Flightmare: A Flexible Quadrotor Simulator

This work proposes a paradigm-shift in the development of simulators: moving the trade-off between accuracy and speed from the developers to the end-users, and develops a novel modular quadrotor simulator: Flightmare.

Learning high-speed flight in the wild

This work demonstrates that end-to-end policies trained in simulation enable high-speed autonomous flight through challenging environments, outperforming traditional obstacle avoidance pipelines.

AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles

A new simulator built on Unreal Engine that offers physically and visually realistic simulations for autonomous vehicles in real world and that is designed from the ground up to be extensible to accommodate new types of vehicles, hardware platforms and software protocols.

PX4: A node-based multithreaded open source robotics framework for deeply embedded platforms

A novel, deeply embedded robotics middleware and programming environment that uses a multithreaded, publish-subscribe design pattern and provides a Unix-like software interface for micro controller applications, which is well suited for fast, high rate control tasks.

NeuroBEM: Hybrid Aerodynamic Quadrotor Model

This work proposes a hybrid approach fusing first principles and learning to model quadrotors and their aerodynamic effects with unprecedented accuracy, outperforming existing models with 50% reduced prediction errors, and shows strong generalization capabilities beyond the training set.

The Foldable Drone: A Morphing Quadrotor That Can Squeeze and Fly

This work proposes a novel, simpler, yet effective morphing design for quadrotors consisting of a frame with four independently rotating arms that fold around the main frame and demonstrates the first work showing stable flight without requiring any symmetry of the morphology.