Bio-inspired design is often used in autonomous UAV navigation due to the capacity of biological systems for flight and obstacle avoidance despite limited sensory and computational capabilities. In particular, honeybees mainly use the sensory input of optic flow, the apparent motion of objects in their visual field, to navigate cluttered environments. In our work, we train a Reinforcement Learning agent to navigate a tunnel with obstacles using only optic flow as sensory input. We inspect the attention patterns of trained agents to determine the regions of optic flow on which they primarily base their motor decisions. We find that agents trained in this way pay most attention to regions of discontinuity in optic flow, as well as regions with large optic flow magnitude. The trained agents appear to navigate a cluttered tunnel by avoiding the obstacles that produce large optic flow, while maintaining a centered position in their environment, which resembles the behavior seen in flying insects. This pattern persists across independently trained agents, which suggests that this could be a good strategy for developing a simple explicit control law for physical UAVs.

In this paper, we investigate the prospects and challenges of sensor suites in achieving autonomous control for flying insect robots (FIRs) weighing less than a gram. FIRs, owing to their minuscule weight and size, offer unparalleled advantages in terms of material cost and scalability. However, their size introduces considerable control challenges, notably high-speed dynamics, restricted power, and limited payload capacity. While there have been notable advancements in developing lightweight sensors, often drawing inspiration from biological systems, no sub-gram aircraft has been able to attain sustained hover without relying on feedback from external sensing such as a motion capture system. The lightest vehicle capable of sustained hover -- the first level of "sensor autonomy" -- is the much larger 28 g Crazyflie. Previous work reported a reduction in size of that vehicle's avionics suite to 187 mg and 21 mW. Here, we report a further reduction in mass and power to only 78.4 mg and 15 mW. We replaced the laser rangefinder with a lighter and more efficient pressure sensor, and built a smaller optic flow sensor around a global-shutter imaging chip. A Kalman Filter (KF) fuses these measurements to estimate the state variables that are needed to control hover: pitch angle, translational velocity, and altitude. Our system achieved performance comparable to that of the Crazyflie's estimator while in flight, with root mean squared errors of 1.573 degrees, 0.186 m/s, and 0.139 m, respectively, relative to motion capture.

The implementation of collective motion, traditionally, disregard the limited sensing capabilities of an individual, to instead assuming an omniscient perception of the environment. This study implements a visual flocking model in a ``robot-in-the-loop'' approach to reproduce these behaviors with a flock composed of 10 independent spherical robots. The model achieves robotic collective motion by only using panoramic visual information of each robot, such as retinal position, optical size and optic flow of the neighboring robots. We introduce a virtual anchor to confine the collective robotic movements so to avoid wall interactions. For the first time, a simple visual robot-in-the-loop approach succeed in reproducing several collective motion phases, in particular, swarming, and milling. Another milestone achieved with by this model is bridging the gap between simulation and physical experiments by demonstrating nearly identical behaviors in both environments with the same visual model. To conclude, we show that our minimal visual collective motion model is sufficient to recreate most collective behaviors on a robot-in-the-loop system that is scalable, behaves as numerical simulations predict and is easily comparable to traditional models.

This study explores the utility of various internet data sources to select among a set of template robot behaviors to perform skills. Learning contact-rich skills involving tool use from internet data sources has typically been challenging due to the lack of physical information such as contact existence, location, areas, and force in this data. Prior works have generally used internet data and foundation models trained on this data to generate low-level robot behavior. We hypothesize that these data and models may be better suited to selecting among a set of basic robot behaviors to perform these contact-rich skills. We explore three methods of template selection: querying large language models, comparing video of robot execution to retrieved human video using features from a pretrained video encoder common in prior work, and performing the same comparison using features from an optic flow encoder trained on internet data. Our results show that LLMs are surprisingly capable template selectors despite their lack of visual information, optical flow encoding significantly outperforms video encoders trained with an order of magnitude more data, and important synergies exist between various forms of internet data for template selection. By exploiting these synergies, we create a template selector using multiple forms of internet data that achieves a 79\% success rate on a set of 16 different cooking skills involving tool-use.

A gaze-fixating robot perceives distance to the fixated object and relative positions of surrounding objects immediately, accurately, and robustly. We show how fixation, which is the act of looking at one object while moving, exploits regularities in the geometry of 3D space to obtain this information. These regularities introduce rotation-translation couplings that are not commonly used in structure from motion. To validate, we use a Franka Emika Robot with an RGB camera. We a) find that error in distance estimate is less than 5 mm at a distance of 15 cm, and b) show how relative position can be used to find obstacles under challenging scenarios. We combine accurate distance estimates and obstacle information into a reactive robot behavior that is able to pick up objects of unknown size, while impeded by unforeseen obstacles. Project page: https://oxidification.com/p/one-object-at-a-time/ .

We have designed a neural network which detects the direction of ego(cid:173) motion from optic flow in the presence of eye movements (Lappe and Rauschecker, 1993). The performance of the network is consistent with human psychophysical data, and its output neurons show great similarity to "triple component" cells in area MSTd of monkey visual cortex. We now show that by using assumptions about the kind of eye movements that the obsenrer is likely to perform, our model can generate various other cell types found in MSTd as well.

Scientists have developed a theory that can explain how flying insects determine the gravity direction without using accelerometers. It also forms a substantial step in the creation of tiny, autonomous drones. Scientists have discovered a novel manner for flying drones and insects to estimate the gravity direction. Whereas drones typically use accelerometers to this end, the way in which flying insects do this has until now been shrouded in mystery, since they lack a specific sense for acceleration. In an article published in Nature, scientists from TU Delft and Aix Marseille Université / CNRS in France have shown that drones can estimate the gravity direction by combining visual motion sensing with a model of how they move.

They are not just cute and stripy, but devastatingly efficient when it comes to locating the best pollen-rich flowers. As a result, the humble bee is at the centre of a £4.8 million project to create drones and driverless cars. In a unusual experiment, scientists painstakingly stuck tiny radar transponders to hundreds of bumblebees and honey bees, to track them as they flew. Bees are famous in the animal world for their intelligence, even directing each other to delicious flowers using a'waggle dance'. To harness their navigational skills, researchers used radar to track bees' precise flight path as they buzzed over farmland in Hertfordshire Carefully avoiding painful stings, the researchers have also put bees in virtual reality chambers, then watched how their brains works as they navigate.

We implement a model of obstacle avoidance in flying insects on a small, monocular robot. The result is a system that is capable of rapid navigation through a dense obstacle field. The key to the system is the use of zigzag behavior to articulate the body during movement. It is shown that this behavior compensates for a parallax blind spot surrounding the focus of expansion normally found in systems without parallax behavior.

We implement a model of obstacle avoidance in flying insects on a small, monocular robot. The result is a system that is capable of rapid navigation through a dense obstacle field. The key to the system is the use of zigzag behavior to articulate the body during movement. It is shown that this behavior compensates for a parallax blind spot surrounding the focus of expansion normally found in systems without parallax behavior.