RESUMEN

Navigation is an essential capability for autonomous robots. In particular, visual navigation has been a major research topic in robotics because cameras are lightweight, power-efficient sensors that provide rich information on the environment. However, the main challenge of visual navigation is that it requires substantial computational power and memory for visual processing and storage of the results. As of yet, this has precluded its use on small, extremely resource-constrained robots such as lightweight drones. Inspired by the parsimony of natural intelligence, we propose an insect-inspired approach toward visual navigation that is specifically aimed at extremely resource-restricted robots. It is a route-following approach in which a robot's outbound trajectory is stored as a collection of highly compressed panoramic images together with their spatial relationships as measured with odometry. During the inbound journey, the robot uses a combination of odometry and visual homing to return to the stored locations, with visual homing preventing the buildup of odometric drift. A main advancement of the proposed strategy is that the number of stored compressed images is minimized by spacing them apart as far as the accuracy of odometry allows. To demonstrate the suitability for small systems, we implemented the strategy on a tiny 56-gram drone. The drone could successfully follow routes up to 100 meters with a trajectory representation that consumed less than 20 bytes per meter. The presented method forms a substantial step toward the autonomous visual navigation of tiny robots, facilitating their more widespread application.

RESUMEN

This Review discusses the main results obtained in training end-to-end neural architectures for guidance and control of interplanetary transfers, planetary landings, and close-proximity operations, highlighting the successful learning of optimality principles by the underlying neural models. Spacecraft and drones aimed at exploring our solar system are designed to operate in conditions where the smart use of onboard resources is vital to the success or failure of the mission. Sensorimotor actions are thus often derived from high-level, quantifiable, optimality principles assigned to each task, using consolidated tools in optimal control theory. The planned actions are derived on the ground and transferred on board, where controllers have the task of tracking the uploaded guidance profile. Here, we review recent trends based on the use of end-to-end networks, called guidance and control networks (G&CNets), which allow spacecraft to depart from such an architecture and to embrace the onboard computation of optimal actions. In this way, the sensor information is transformed in real time into optimal plans, thus increasing mission autonomy and robustness. We then analyze drone racing as an ideal gym environment to test these architectures on real robotic platforms and thus increase confidence in their use in future space exploration missions. Drone racing not only shares with spacecraft missions both limited onboard computational capabilities and similar control structures induced from the optimality principle sought but also entails different levels of uncertainties and unmodeled effects and a very different dynamical timescale.

RESUMEN

Powered flight was once a capability limited only to animals, but by identifying useful attributes of animal flight and building on these with technological advances, engineers have pushed the frontiers of flight beyond our predecessors' wildest imaginations. Yet, there remain many key characteristics of biological flight that elude current aircraft design, motivating a careful re-analysis of what we have learned from animals already, and how this has been revealed experimentally, as well as a specific focus on identifying what remains unknown. Here, we review the literature to identify key contributions that began in biology and have since been translated into aeronautical devices or capabilities. We identify central areas for future research and highlight the importance of maintaining an open line of two-way communication between biologists and engineers. Such interdisciplinary, bio-informed analyses continue to push forward the frontiers of aeronautics and experimental biology alike.

Asunto(s)

RESUMEN

Flapping wing micro aerial vehicles (FWMAVs) are known for their flight agility and maneuverability. These bio-inspired and lightweight flying robots still present limitations in their ability to fly in direct wind and gusts, as their stability is severely compromised in contrast with their biological counterparts. To this end, this work aims at making in-gust flight of flapping wing drones possible using an embodied airflow sensing approach combined with an adaptive control framework at the velocity and position control loops. At first, an extensive experimental campaign is conducted on a real FWMAV to generate a reliable and accurate model of the in-gust flight dynamics, which informs the design of the adaptive position and velocity controllers. With an extended experimental validation, this embodied airflow-sensing approach integrated with the adaptive controller reduces the root-mean-square errors along the wind direction by 25.15% when the drone is subject to frontal wind gusts of alternating speeds up to 2.4 m/s, compared to the case with a standard cascaded PID controller. The proposed sensing and control framework improve flight performance reliably and serve as the basis of future progress in the field of in-gust flight of lightweight FWMAVs.

RESUMEN

Attitude control is an essential flight capability. Whereas flying robots commonly rely on accelerometers1 for estimating attitude, flying insects lack an unambiguous sense of gravity2,3. Despite the established role of several sense organs in attitude stabilization3-5, the dependence of flying insects on an internal gravity direction estimate remains unclear. Here we show how attitude can be extracted from optic flow when combined with a motion model that relates attitude to acceleration direction. Although there are conditions such as hover in which the attitude is unobservable, we prove that the ensuing control system is still stable, continuously moving into and out of these conditions. Flying robot experiments confirm that accommodating unobservability in this manner leads to stable, but slightly oscillatory, attitude control. Moreover, experiments with a bio-inspired flapping-wing robot show that residual, high-frequency attitude oscillations from flapping motion improve observability. The presented approach holds a promise for robotics, with accelerometer-less autopilots paving the road for insect-scale autonomous flying robots6. Finally, it forms a hypothesis on insect attitude estimation and control, with the potential to provide further insight into known biological phenomena5,7,8 and to generate new predictions such as reduced head and body attitude variance at higher flight speeds9.

Asunto(s)

RESUMEN

Natural fliers utilize passive and active flight control strategies to cope with windy conditions. This capability makes them incredibly agile and resistant to wind gusts. Here, we study how insects achieve this, by combining Computational Fluid Dynamics (CFD) analyses of flying fruit flies with freely-flying robotic experiments. The CFD analysis shows that flying flies are partly passively stable in side-wind conditions due to their dorsal-ventral wing-beat asymmetry defined as wing-stroke dihedral. Our robotic experiments confirm that this mechanism also stabilizes free-moving flapping robots with similar asymmetric dihedral wing-beats. This shows that both animals and robots with asymmetric wing-beats are dynamically stable in sideways wind gusts. Based on these results, we developed an improved model for the aerodynamic yaw and roll torques caused by the coupling between lateral motion and the stroke dihedral. The yaw coupling passively steers an asymmetric flapping flyer into the direction of a sideways wind gust; in contrast, roll torques are only stabilizing at high air gust velocities, due to non-linear coupling effects. The combined CFD simulations, robot experiments, and stability modeling help explain why the majority of flying insects exhibit wing-beats with positive stroke dihedral and can be used to develop more stable and robust flapping-wing Micro-Air-Vehicles.

RESUMEN

End-to-end trained convolutional neural networks have led to a breakthrough in optical flow estimation. The most recent advances focus on improving the optical flow estimation by improving the architecture and setting a new benchmark on the publicly available MPI-Sintel dataset. Instead, in this article, we investigate how deep neural networks estimate optical flow. A better understanding of how these networks function is important for (i) assessing their generalization capabilities to unseen inputs, and (ii) suggesting changes to improve their performance. For our investigation, we focus on FlowNetS, as it is the prototype of an encoder-decoder neural network for optical flow estimation. Furthermore, we use a filter identification method that has played a major role in uncovering the motion filters present in animal brains in neuropsychological research. The method shows that the filters in the deepest layer of FlowNetS are sensitive to a variety of motion patterns. Not only do we find translation filters, as demonstrated in animal brains, but thanks to the easier measurements in artificial neural networks, we even unveil dilation, rotation, and occlusion filters. Furthermore, we find similarities in the refinement part of the network and the perceptual filling-in process which occurs in the mammal primary visual cortex.

Asunto(s)

RESUMEN

When approaching a landing surface, many flying animals use visual feedback to control their landing. Here, we studied how foraging bumblebees (Bombus terrestris) use radial optic expansion cues to control in-flight decelerations during landing. By analyzing the flight dynamics of 4,672 landing maneuvers, we showed that landing bumblebees exhibit a series of deceleration bouts, unlike landing honeybees that continuously decelerate. During each bout, the bumblebee keeps its relative rate of optical expansion constant, and from one bout to the next, the bumblebee tends to shift to a higher, constant relative rate of expansion. This modular landing strategy is relatively fast compared to the strategy described for honeybees and results in approach dynamics that is strikingly similar to that of pigeons and hummingbirds. The here discovered modular landing strategy of bumblebees helps explaining why these important pollinators in nature and horticulture can forage effectively in challenging conditions; moreover, it has potential for bio-inspired landing strategies in flying robots.

RESUMEN

Autonomous flight for large aircraft appears to be within our reach. However, launching autonomous systems for everyday missions still requires an immense interdisciplinary research effort supported by pointed policies and funding. We believe that concerted endeavors in the fields of neuroscience, mathematics, sensor physics, robotics, and computer science are needed to address remaining crucial scientific challenges. In this paper, we argue for a bio-inspired approach to solve autonomous flying challenges, outline the frontier of sensing, data processing, and flight control within a neuromorphic paradigm, and chart directions of research needed to achieve operational capabilities comparable to those we observe in nature. One central problem of neuromorphic computing is learning. In biological systems, learning is achieved by adaptive and relativistic information acquisition characterized by near-continuous information retrieval with variable rates and sparsity. This results in both energy and computational resource savings being an inspiration for autonomous systems. We consider pertinent features of insect, bat and bird flight behavior as examples to address various vital aspects of autonomous flight. Insects exhibit sophisticated flight dynamics with comparatively reduced complexity of the brain. They represent excellent objects for the study of navigation and flight control. Bats and birds enable more complex models of attention and point to the importance of active sensing for conducting more complex missions. The implementation of neuromorphic paradigms for autonomous flight will require fundamental changes in both traditional hardware and software. We provide recommendations for sensor hardware and processing algorithm development to enable energy efficient and computationally effective flight control.

RESUMEN

The identification and solution of a major efficiency loss in small flapping wing drones lead to more agile aerobatic maneuvers.

RESUMEN

The combination of spiking neural networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from the raw stimuli generated with an event-based camera. A novel adaptive neuron model and stable spike-timing-dependent plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. After convergence, the neural architecture exhibits the main properties of biological visual motion systems, namely feature extraction and local and global motion perception. Convolutional layers with input synapses characterized by single and multiple transmission delays are employed for feature and local motion perception, respectively; while global motion selectivity emerges in a final fully-connected layer. The proposed solution is validated using synthetic and real event sequences. Along with this paper, we provide the cuSNN library, a framework that enables GPU-accelerated simulations of large-scale spiking neural networks. Source code and samples are available at https://github.com/tudelft/cuSNN.

RESUMEN

This work presents a review and discussion of the challenges that must be solved in order to successfully develop swarms of Micro Air Vehicles (MAVs) for real world operations. From the discussion, we extract constraints and links that relate the local level MAV capabilities to the global operations of the swarm. These should be taken into account when designing swarm behaviors in order to maximize the utility of the group. At the lowest level, each MAV should operate safely. Robustness is often hailed as a pillar of swarm robotics, and a minimum level of local reliability is needed for it to propagate to the global level. An MAV must be capable of autonomous navigation within an environment with sufficient trustworthiness before the system can be scaled up. Once the operations of the single MAV are sufficiently secured for a task, the subsequent challenge is to allow the MAVs to sense one another within a neighborhood of interest. Relative localization of neighbors is a fundamental part of self-organizing robotic systems, enabling behaviors ranging from basic relative collision avoidance to higher level coordination. This ability, at times taken for granted, also must be sufficiently reliable. Moreover, herein lies a constraint: the design choice of the relative localization sensor has a direct link to the behaviors that the swarm can (and should) perform. Vision-based systems, for instance, force MAVs to fly within the field of view of their camera. Range or communication-based solutions, alternatively, provide omni-directional relative localization, yet can be victim to unobservable conditions under certain flight behaviors, such as parallel flight, and require constant relative excitation. At the swarm level, the final outcome is thus intrinsically influenced by the on-board abilities and sensors of the individual. The real-world behavior and operations of an MAV swarm intrinsically follow in a bottom-up fashion as a result of the local level limitations in cognition, relative knowledge, communication, power, and safety. Taking these local limitations into account when designing a global swarm behavior is key in order to take full advantage of the system, enabling local limitations to become true strengths of the swarm.

RESUMEN

Insects are among the most agile natural flyers. Hypotheses on their flight control cannot always be validated by experiments with animals or tethered robots. To this end, we developed a programmable and agile autonomous free-flying robot controlled through bio-inspired motion changes of its flapping wings. Despite being 55 times the size of a fruit fly, the robot can accurately mimic the rapid escape maneuvers of flies, including a correcting yaw rotation toward the escape heading. Because the robot's yaw control was turned off, we showed that these yaw rotations result from passive, translation-induced aerodynamic coupling between the yaw torque and the roll and pitch torques produced throughout the maneuver. The robot enables new methods for studying animal flight, and its flight characteristics allow for real-world flight missions.

Asunto(s)

RESUMEN

Robust attitude control is an essential aspect of research on autonomous flight of flapping wing Micro Air Vehicles. The mechanical solutions by which the necessary control moments are realised come at the price of extra weight and possible loss of aerodynamic efficiency. Stable flight of these vehicles has been shown by several designs using a conventional tail, but also by tailless designs that use active control of the wings. In this study a control mechanism is proposed that provides active control over the wings. The mechanism improves vehicle stability and agility by generation of control moments for roll, pitch and yaw. Its effectiveness is demonstrated by static measurements around all the three axes. Flight test results confirm that the attitude of the test vehicle, including a tail, can be successfully controlled in slow forward flight conditions. Furthermore, the flight envelope is extended with robust hovering and the ability to reverse the flight direction using a small turn space. This capability is very important for autonomous flight capabilities such as obstacle avoidance. Finally, it is demonstrated that the proposed control mechanism allows for tailless hovering flight.

Asunto(s)

RESUMEN

To avoid collisions, Micro Air Vehicles (MAVs) flying in teams require estimates of their relative locations, preferably with minimal mass and processing burden. We present a relative localization method where MAVs need only to communicate with each other using their wireless transceiver. The MAVs exchange on-board states (velocity, height, orientation) while the signal strength indicates range. Fusing these quantities provides a relative location estimate. We used this for collision avoidance in tight areas, testing with up to three AR.Drones in a 4 m × 4 m area and with two miniature drones ( ≈ 50 g ) in a 2 m × 2 m area. The MAVs could localize each other and fly several minutes without collisions. In our implementation, MAVs communicated using Bluetooth antennas. The results were robust to the high noise and disturbances in signal strength. They could improve further by using transceivers with more accurate signal strength readings.

RESUMEN

One of the major challenges of evolutionary robotics is to transfer robot controllers evolved in simulation to robots in the real world. In this article, we investigate abstraction of the sensory inputs and motor actions as a tool to tackle this problem. Abstraction in robots is simply the use of preprocessed sensory inputs and low-level closed-loop control systems that execute higher-level motor commands. To demonstrate the impact abstraction could have, we evolved two controllers with different levels of abstraction to solve a task of forming an asymmetric triangle with a homogeneous swarm of micro air vehicles. The results show that although both controllers can effectively complete the task in simulation, the controller with the lower level of abstraction is not effective on the real vehicle, due to the reality gap. The controller with the higher level of abstraction is, however, effective both in simulation and in reality, suggesting that abstraction can be a useful tool in making evolved behavior robust to the reality gap. Additionally, abstraction aided in reducing the computational complexity of the simulation environment, speeding up the optimization process. Preeminently, we show that the optimized behavior exploits the environment (in this case the identical behavior of the other robots) and performs input shaping to allow the vehicles to fly into and maintain the required formation, demonstrating clear sensory-motor coordination. This shows that the power of the genetic optimization to find complex correlations is not necessarily lost through abstraction as some have suggested.

Asunto(s)

RESUMEN

The visual cue of optical flow plays an important role in the navigation of flying insects, and is increasingly studied for use by small flying robots as well. A major problem is that successful optical flow control seems to require distance estimates, while optical flow is known to provide only the ratio of velocity to distance. In this article, a novel, stability-based strategy is proposed for monocular distance estimation, relying on optical flow maneuvers and knowledge of the control inputs (efference copies). It is shown analytically that given a fixed control gain, the stability of a constant divergence control loop only depends on the distance to the approached surface. At close distances, the control loop starts to exhibit self-induced oscillations. The robot can detect these oscillations and hence be aware of the distance to the surface. The proposed stability-based strategy for estimating distances has two main attractive characteristics. First, self-induced oscillations can be detected robustly by the robot and are hardly influenced by wind. Second, the distance can be estimated during a zero divergence maneuver, i.e., around hover. The stability-based strategy is implemented and tested both in simulation and on board a Parrot AR drone 2.0. It is shown that the strategy can be used to: (1) trigger a final approach response during a constant divergence landing with fixed gain, (2) estimate the distance in hover, and (3) estimate distances during an entire landing if the robot uses adaptive gain control to continuously stay on the 'edge of oscillation.'

Asunto(s)

RESUMEN

Evolutionary Robotics allows robots with limited sensors and processing to tackle complex tasks by means of sensory-motor coordination. In this article we show the first application of the Behavior Tree framework on a real robotic platform using the evolutionary robotics methodology. This framework is used to improve the intelligibility of the emergent robotic behavior over that of the traditional neural network formulation. As a result, the behavior is easier to comprehend and manually adapt when crossing the reality gap from simulation to reality. This functionality is shown by performing real-world flight tests with the 20-g DelFly Explorer flapping wing micro air vehicle equipped with a 4-g onboard stereo vision system. The experiments show that the DelFly can fully autonomously search for and fly through a window with only its onboard sensors and processing. The success rate of the optimized behavior in simulation is 88%, and the corresponding real-world performance is 54% after user adaptation. Although this leaves room for improvement, it is higher than the 46% success rate from a tuned user-defined controller.

Asunto(s)

RESUMEN

Tragopogon pratensis is a small herbaceous plant that uses wind as the dispersal vector for its seeds. The seeds are attached to parachutes that increase the aerodynamic drag force and increase the total distance travelled. Our hypothesis is that evolution has carefully tuned the air permeability of the seeds to operate in the most convenient fluid dynamic regime. To achieve final permeability, the primary and secondary fibres of the pappus have evolved with complex weaving; this maximises the drag force (i.e., the drag coefficient), and the pappus operates in an "optimal" state. We used computational fluid dynamics (CFD) simulations to compute the seed drag coefficient and compare it with data obtained from drop experiments. The permeability of the parachute was estimated from microscope images. Our simulations reveal three flow regimes in which the parachute can operate according to its permeability. These flow regimes impact the stability of the parachute and its drag coefficient. From the permeability measurements and drop experiments, we show how the seeds operate very close to the optimal case. The porosity of the textile appears to be an appropriate solution to achieve a lightweight structure that allows a low terminal velocity, a stable flight and a very efficient parachute for the velocity at which it operates.

Asunto(s)