Adaptive Optical Learning Process Inspired by Honeybees

Innovation: Academia

Delft University of Technology

2021

Image: Sandy Millar / Unsplash / CC BY SA - Creative Commons Attribution + ShareAlike

Respond to Signals

To interact with its environment, a living system must not only sense a variety of signals, but also respond to them. To be energy- and material-efficient, those responses must be appropriate to the signal. This generally requires sensing thresholds to trigger an appropriate level of response (for example, hiding under a shrub versus running away to avoid a predator). Response strategies are tied to a specific signal and often have a response threshold, which determines how strong a signal must be to warrant expending energy to respond. One example is a plant that lives in arid regions in South Africa. Its seed capsules remain closed until rainfall triggers them to open to release the seeds. But the plant only responds to a second rainfall, thus protecting against releasing its seeds before there is enough sustained water for them to grow.

Search this Function

Transduce/Convert Signals

Sometimes a signal, such as sound or vibration, reaches a living system and needs to be converted into a different, usable form. This requires converting from one type of energy form to another. For example, organisms with eyes have photoreceptors at the back of the eyes that convert light into electrical pulses. These pulses travel to the brain and allows it to register color, shape, and detail.

Search this Function

Differentiate Signal From Noise

The environment surrounding any living system is full of signals, such as smells, sounds, electricity, magnetism, and more. Too many signals at once can be overwhelming, making it difficult to locate and react to any particular signal. To address this, living systems must differentiate among all signals, or “noise,” so they can focus on those they really need. During mating season, for example, male frogs gather close together in large groups to call for females. Despite their overwhelming, collective noise, females are able to find a particular male whose call is attractive to her. This is because the males use desynchronized calling, enabling individual recognition.

Search this Function

Compute

Computation allows an organism to take in and process information to make decisions. Whether it be calculating how fast prey is moving or deciding where to build a nest, computation is an important part of an organism’s life.

Search this Function

Learn

Living systems obtain information from their environment and use it to find mates and resources, and to escape threats. Some reactions to gathered information are instinctual or innate behaviors, not based on previous experiences. But other reactions are based on previous experiences, which means that, at some level, the living system is learning. Learning can involve a living system passing information to another living system, or a living system obtaining information and using it in a feedback loop. That information can include knowledge, experience, behavior, and skills. Learning takes place when information that is new to the recipient is used to modify existing behavior or skills. The making and use of tools by some species of birds and mammals is a learned behavior. If a chimpanzee uses a stick to successfully get ants out of an ant mound and continues to do so, it has learned that behavior. If another chimpanzee observes this technique and replicates it, it has learned from the first chimp.

Search this Function

Optical learning process from Delft University increases the navigational skills of flying robots.

Benefits

Collision detection & avoidance
Smoother landings

Applications

Flying robots
Surveillance

UN Sustainable Development Goals Addressed

Goal 9: Industry Innovation & Infrastructure

The Challenge

Flying robots such as drones use optical flow to create a pattern of objects in a visual field, which helps them sense movement and distance, similar to animals. Optical flow “divergence” captures how quickly things get bigger in view. If an insect such as a honeybee were to fall to the ground, this divergence would keep increasing and the grass would become increasingly bigger in view. However, honeybees employ a strategy of keeping the divergence constant by slowing down. As a result, they are able to make smooth, soft landings. Drones however, are unable to adapt their reaction height while landing, and often end up oscillating above the landing surface. In addition, the optical flow is very small in the direction the robot is moving, and is oftentimes difficult to distinguish from noise. This means that obstacles are more difficult to detect, increasing the likelihood of collisions. If researchers can overcome these limitations, they can create small flying robots that can navigate their environments more safely and land smoothly.

Innovation Details

In order to improve the optical flow of flying robots, researchers allowed robots to estimate distances of objects through their visual appearance, including shape, color, and texture. Using artificial intelligence (AI)-based learning the robot repeated this process multiple times, and was eventually able to learn and remember the distances of objects over time and avoid them. This also allowed for faster, smoother landings.

Biological Model

Honeybees use optical flow to perceive distances to objects and control divergence to slow down when approaching an object. This allows the insect to make smooth, soft landings.

See Related Strategy

honeybee flying to purple, white and yellow flower in close up photo during the day

Biological Strategy

Antennae Ensure Smooth Landings

Honeybees

The antennae of the honeybee enable smooth landings by sensing landing distance and angle, signaling the body to orient appropriately.

References

Journal article

Enhancing optical-flow-based control by learning visual appearance cues for flying robots

embedly preview

AskNature