Uploaded January 2021 | Updated November 2026, 3 hours ago
We propose a learning process to solve two fundamental problems of optical flow control.
Problems of optical flow control
Flying insects heavily rely on optical flow for visual navigation and flight control. Roboticists have endowed small flying robots with optical flow control as well, since it requires just a tiny vision sensor.
However, when using optical flow, the robots run into two problems that insects appear to have overcome. Firstly, since optical flow only provides mixed information on distances and velocities, using it for control leads to oscillations when getting closer to obstacles. Secondly, since optical flow provides very little information on obstacles in the direction of motion, it is hardest to detect obstacles that the robot is actually going to collide with!
Learning process as a solution
We propose a solution to these problems by means of a learning process. During learning, the robot exploits self-induced oscillations to learn what the objects in its environment look like at different distances. After learning, the robot can perform faster and smoother optical flow landings and fly faster and safer flight in cluttered environments.
Moreover, our solution entails a new hypothesis for insect intelligence. Insect flight control for tasks such as landing or obstacle avoidance is typically described in terms of pre-wired optical flow control laws. Our work suggests that flying insects may learn the visual appearance of their environment to improve their flight and navigation skills over their lifetime.
Read the article at:
- nature.com/articles/s42256-020-00279-7
- doi.org/10.1038/s42256-020-00279-7
We propose a learning process to solve two fundamental problems of optical flow control.
Problems of optical flow control
Flying insects heavily rely on optical flow for visual navigation and flight control. Roboticists have endowed small flying robots with optical flow control as well, since it requires just a tiny vision sensor.
However, when using optical flow, the robots run into two problems that insects appear to have overcome. Firstly, since optical flow only provides mixed information on distances and velocities, using it for control leads to oscillations when getting closer to obstacles. Secondly, since optical flow provides very little information on obstacles in the direction of motion, it is hardest to detect obstacles that the robot is actually going to collide with!
Learning process as a solution
We propose a solution to these problems by means of a learning process. During learning, the robot exploits self-induced oscillations to learn what the objects in its environment look like at different distances. After learning, the robot can perform faster and smoother optical flow landings and fly faster and safer flight in cluttered environments.
Moreover, our solution entails a new hypothesis for insect intelligence. Insect flight control for tasks such as landing or obstacle avoidance is typically described in terms of pre-wired optical flow control laws. Our work suggests that flying insects may learn the visual appearance of their environment to improve their flight and navigation skills over their lifetime.
Read the article at:
- nature.com/articles/s42256-020-00279-7
- doi.org/10.1038/s42256-020-00279-7








![[Additional Demo] Stability-based Scale Estimation for Monocular SLAM
* Paper is available at: http://ieeexplore.ieee.org/document/8246525/
* The main demo is at: https://youtu.be/m0IvL6PD4gM
In this video, we show two autonomous flights:
1. We run our stability-based scale estimation while hovering at a small distance to the scene (2 m). Afterwards, the MAV flies backward for 10 m, hovers for 5 seconds, then comes back to the initial position and hovers. We show that the MAV hovers stably even at a large scene distance (see 2:50) and comes back to the start position accurately (compare the drones location at 0:55 and 1:40). We also display the control input and real-time SLAM output.
2. We do the similar flight, but this time we estimate the scale at a large distance to the scene (over 12 m), then fly forward and backward for 10 m. We show that the MAV hovers stably even at a small scene distance (see 5:25) and comes back to the start position (compare 3:40 and 4:19, especially the onboard view).
This demonstrates that the proposed system can still be used in a larger scale scenario with very large scene distances and variations. [Additional Demo] Stability-based Scale Estimation for Monocular SLAM](https://i.ytimg.com/vi/Dp6XhvQnWp0/mqdefault.jpg)

