Abdominal-Waving Control of Tethered Bumblebees Based on Sarsa With Transformed Reward

Cyborg Moth Flight Control Based on Fuzzy Deep Learning

Cyborg insect control methods can be divided into invasive methods and noninvasive methods. Compared to invasive methods, noninvasive methods are much easier to implement, but they are sensitive to complex and highly uncertain environments, for which classical control methods often have low control accuracy. In this paper, we present a noninvasive approach for cyborg moths stimulated by noninvasive ultraviolet (UV) rays. We propose a fuzzy deep learning method for cyborg moth flight control, which consists of a Behavior Learner and a Control Learner. The Behavior Learner is further divided into three hierarchies for learning the species’ common behaviors, group-specific behaviors, and individual-specific behaviors step by step to produce the expected flight parameters. The Control Learner learns how to set UV ray stimulation to make a moth exhibit the expected flight behaviors. Both the Control Learner and Behavior Learner (including its sub-learners) are constructed using a Pythagorean fuzzy denoising autoencoder model. Experimental results demonstrate that the proposed approach achieves significant performance advantages over the state-of-the-art approaches and obtains a high control success rate of over 83% for flight parameter control.

Adaptive Sliding Mode Disturbance Observer and Deep Reinforcement Learning Based Motion Control for Micropositioners

The motion control of high-precision electromechanitcal systems, such as micropositioners, is challenging in terms of the inherent high nonlinearity, the sensitivity to external interference, and the complexity of accurate identification of the model parameters. To cope with these problems, this work investigates a disturbance observer-based deep reinforcement learning control strategy to realize high robustness and precise tracking performance. Reinforcement learning has shown great potential as optimal control scheme, however, its application in micropositioning systems is still rare. Therefore, embedded with the integral differential compensator (ID), deep deterministic policy gradient (DDPG) is utilized in this work with the ability to not only decrease the state error but also improve the transient response speed. In addition, an adaptive sliding mode disturbance observer (ASMDO) is proposed to further eliminate the collective effect caused by the lumped disturbances. The micropositioner controlled by the proposed algorithm can track the target path precisely with less than 1 μm error in simulations and actual experiments, which shows the sterling performance and the accuracy improvement of the controller.

Behavioral control and changes in brain activity of honeybee during flapping

INTRODUCTION

Insect cyborg is a kind of novel robot based on insect-machine interface and principles of neurobiology. The key idea is to stimulate live insects by specific stimuli; thus, the flight trajectory of insects could be controlled as anticipated. However, the neuroregulatory mechanism of insect flight has not been elucidated completely at present.

METHODS

To explore the neuro-mechanism of insect flight behaviors, a series of electrical stimulation was applied on the optic lobes of semi-constrained honeybees. Times of flight initiation, flapping frequency, and duration were recorded by a high-speed camera. In addition, flapping and steering initiation experiments of the cyborg honeybee were verified. Moreover, series of local field potential signals of optic lobes during flapping were collected, pre-processed to remove baseline wander and DC components, then analyzed by power spectrum estimation.

RESULTS

A quantitative optimization method and optimal stimulation parameters of flight initiation were presented. Stimulation results showed that the flapping duration differed greatly while the flapping frequency varied with little difference among different individuals. Moreover, there was always a fluctuation peak around 20-30 Hz in power spectral density (PSD) curves during flapping, distinguishing from calm state, which indicated some brain activity changes during flapping.

CONCLUSIONS

Our study presented a range of relatively optimal electrical parameters to initiate honeybee flight behavior. Meanwhile, the regularity of flapping duration and flapping frequency under electrical stimulations with different parameters were given. The feasibility of controlling a honeybee's flight behavior by brain electrical stimulation was verified through the flapping and steering initiation experiment of honeybees under semi-constrained state. PSD fluctuations reflected changes in brain activity during flapping and that those fluctuation characteristics at the specific frequency band could be sensitive determinants to distinguish whether the honeybee was flying or not, which benefits our understanding of honeybee's flapping behavior and furthers the study of honeybee cyborgs.

Multisensory-motor integration in olfactory navigation of silkmoth, Bombyx mori, using virtual reality system

Most animals survive and thrive due to navigational behavior to reach their destinations. In order to navigate, it is important for animals to integrate information obtained from multisensory inputs and use that information to modulate their behavior. In this study, by using a virtual reality (VR) system for an insect, we investigated how the adult silkmoth integrates visual and wind direction information during female search behavior (olfactory behavior). According to the behavioral experiments using a VR system, the silkmoth had the highest navigational success rate when odor, vision, and wind information were correctly provided. However, the success rate of the search was reduced if the wind direction information provided was different from the direction actually detected. This indicates that it is important to acquire not only odor information but also wind direction information correctly. When the wind is received from the same direction as the odor, the silkmoth takes positive behavior; if the odor is detected but the wind direction is not in the same direction as the odor, the silkmoth behaves more carefully. This corresponds to a modulation of behavior according to the degree of complexity (turbulence) of the environment. We mathematically modeled the modulation of behavior using multisensory information and evaluated it using simulations. The mathematical model not only succeeded in reproducing the actual silkmoth search behavior but also improved the search success relative to the conventional odor-source search algorithm.