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

Abstract

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 controllers. Also, it provides high thrust-to-weight and torque-to-inertia ratios for agility, onboard vision sensors, graphics processing unit (GPU)–accelerated compute hardware for real-time perception and neural network inference, a real-time flight controller, and a versatile software stack. In contrast to existing frameworks, Agilicious offers a unique combination of flexible software stack and high-performance hardware. We compare Agilicious with prior works and demonstrate it on different agile tasks, using both model-based and neural network–based controllers. Our demonstrators include trajectory tracking at up to 5 g and 70 kilometers per hour in a motion capture system, and vision-based acrobatic flight and obstacle avoidance in both structured and unstructured environments using solely onboard perception. Last, we demonstrate its use for hardware-in-the-loop simulation in virtual reality environments. Because of its versatility, we believe that Agilicious supports the next generation of scientific and industrial quadrotor research.

Autonomous Drone Racing: A Survey

“…The physics engine is decoupled and can be swapped out with various engines for user-defined levels of simulation fidelity. Similar to FlightGoggles, Flightmare can also provide hardware-in-the-loop simulation functions where a virtual, synthetic camera image can be provided to the drone for use in control and estimation [162].…”

“…5 Research on how expert human pilots focus on their targets during flying and provide a dataset that contains flight trajectories, videos, and data from the pilots is examined in [6] NeuroBEM [29] is a hybrid aerodynamic quadrotor model which combines blade-element-momentum-theory models with learned aerodynamic representations from highly aggressive maneuvers. While the model is fit to the specific quadrotor platform defined in [162], the approach can be used for any quadrotor platform and provides over 50% reduction in model prediction errors compared to traditional, exclusivelyfirst-principles approaches.…”

Unmanned aerial vehicle navigation in underground structure inspection: A review

“…The robotics and perception (RPG) and autonomous system lab (ASL) teams at the University of Zürich (UZH) both focus on the improvement of navigation methods for visual perception (Pfeiffer et al, 2022). They make Agilicious an open‐source framework for quadrotor drones (Foehn et al, 2022). Feng et al (2013) proposes a panoramic vision network drone for collecting stereo information.…”

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

“…The research area on the aerial robotic perception in outdoor environments is a fast growing field with several ground breaking results. For example, Saska et al (2017Saska et al ( , 2014 pioneered the area of swarm robotics, while Loquercio et al (2021); Foehn et al (2022) demonstrated impressive results in agile flights of micro aerial vehicles. Aerial robotics, with fully on-board perception, has also been part of the recent DARPA subterranean challenges (Rouček et al, 2022;Tranzatto et al, 2022;Agha et al, 2022;Hudson et al, 2022).…”