Alexey Gribovskiy

Towards mixed societies of chickens and robots

To design, to study, and to control mixed animals-robots societies is a challenging field of scientific exploration that can bring new frameworks to study individual and collective behaviors in animal and mixed robot-animal societies. In the Chicken Robot project we aim at developing a mobile robot, able to collaborate with a group of chicks and to control certain group behaviors. The first research step is to build formal models of relevant animal behaviors by performing ethological experiments. Hence, one of the principal tasks is to design a setup equipped with appropriate monitoring tools. In this paper, we present a toolset for running chick-robot experiments and analyzing results. It includes an autonomous PoulBot robot and an experimental setup, able to autonomously record experimental video and audio data, to detect displacements of chicks and robots, to detect their calling activity and to provide robots with these data. We also present a visual data analysis system to extract behavioral features of individual chicks using the variational Bayesian Gaussian mixture model classification with a particle filters based prediction of future positions of chicks. We show how these tools are currently used to carry out chick-robot experiments, to collect behavioral data and to extract animal behavioral features that allow us to build behavioral models bound to be implemented in the robot.

ASSISI: mixing animals with robots in a hybrid society

This paper describes the newly started EU-funded FP7 project ASSISI|bf, which deals with mixed societies: A honeybee society integrated with a group of stationary and interacting autonomous robotic nodes and a group of fish integrated in a society of autonomous moving robots.

Autonomous construction of a roofed structure: Synthesizing planning and stigmergy on a mobile robot

We demonstrate a scenario in which a mobile robot, according to a plan, builds a structure that it can then enter. The robot interacts with the construction using local sensing. This synthesis of planning and stigmergy opens the way to new construction techniques using mobile robots.

Design of a modular robotic system that mimics small fish locomotion and body movements for ethological studies

Robotic animals are nowadays developed for various types of research, such as bioinspired robotics, biomimetics, and animal behavioral studies. The design of these robots poses great challenges as they often have to achieve very high-level performances in terms of locomotion, size, and visual aspect. We developed a robotic system for direct underwater interactions with small fish species. This robotic platform is composed of two subsystems: a miniature wheeled mobile robot that can achieve complex locomotion patterns and a robotic fish lure that is able to beat its soft caudal peduncle to generate fish-like body movements. The two subsystems are coupled with magnets that allow the robotic lure to reach very high speeds and accelerations, thanks to the mobile robot. We used zebrafish (Danio rerio) to model small fish locomotion patterns and construct a controller for the motion of our robotic system. We have demonstrated that the designed system is able to achieve the same types of motion patterns as the zebrafish while mimicking the body movements of the fish. These results define new standards for robotic fish lures and bring to the field of fish–robot interaction a new tool for ethological studies.

Closed-loop interactions between a shoal of zebrafish and a group of robotic fish in a circular corridor

Collective behavior based on self-organization has been observed in populations of animals from insects to vertebrates. These findings have motivated engineers to investigate approaches to control autonomous multi-robot systems able to reproduce collective animal behaviors, and even to collectively interact with groups of animals. In this article, we show collective decision making by a group of autonomous robots and a group of zebrafish, leading to a shared decision about swimming direction. The robots can also modulate the collective decision-making process in biased and non-biased experimental setups. These results demonstrate the possibility of creating mixed societies of vertebrates and robots in order to study or control animal behavior.

Multi-robot control and tracking framework for bio-hybrid systems with closed-loop interaction

Bio-mimetic robots can interact with groups of animals in bio-hybrid systems to study their behaviour by producing calibrated stimuli and by analysing their responses. Integrating a group of robots into a group of animals to mimic their behaviour is challenging, both in terms of robotic hardware design and robot control. In particular, the robots must be able to react in real-time to the animal changes of behaviour. This implies the need to adequately track and identify animal behaviour. In this paper, we present a novel framework to control several bio-mimetic robots to integrate into groups of fish. Our framework is able to track the position of the fish and robots in real-time. The robots are driven by a bio-mimetic model of fish behaviour from the literature. We show that our multi-robot system can successfully integrate into groups of fish with closed-loop interactions between the robots and the fish.

Automated Calibration of a Biomimetic Space-Dependent Model for Zebrafish and Robot Collective Behaviour in a Structured Environment

Animal and robotic collective behaviours can exhibit complex dynamics that require multi-level descriptions. Here, we are interested in developing a multi-level modeling framework for the use of robots in studies about animal collective decision-making. In this context, using robots can be useful for validating models in silico, inducing calibrated repetitive stimuli to trigger animal responses or modulating and controlling animal collective behaviour. However, designing appropriate biomimetic robotic behaviour faces a major challenge: how to go from the collective decision dynamics observed with animals to an actual algorithmic implementation in robots. In previous work, this was mainly done by hand, often by taking inspiration from human-designed models. Typically, models of behaviour are either macroscopic (differential equations of the population dynamics) or microscopic (explicit spatio-temporal state of each individual). Only microscopic models can easily be implemented as robot controllers. Here, we address the problem of automating the design of lower level description models that can be implemented in robots and exhibit the same collective dynamics as a given higher level model. We apply evolutionary algorithms to simultaneously optimise the parameters of models accounting for different levels of description. This methodology is applied to an experimentally validated shelterselection problem solved by gregarious insects and robots. We successfully design and calibrate automatically both a microscopic and a hybrid model exhibiting the same dynamics as a macroscopic one. Our framework can be used for multi-level modeling of collective behaviour in animal or robot populations and bio-hybrid systems.Bio-hybrid systems made of robots and animals can be useful tools both for biology and robotics. To socially integrate robots into animal groups the robots should behave in a biomimetic manner with close loop interactions between robots and animals. Behavioural zebrafish experiments show that their individual behaviours depend on social interactions producing collective behaviour and depend on their position in the environment. Based on those observations we build a multilevel model to describe the zebrafish collective behaviours in a structured environment. Here, we present this new model segmented in spatial zones that each corresponds to different behavioural patterns. We automatically fit the model parameters for each zone to experimental data using a multi-objective evolutionary algorithm. We then evaluate how the resulting calibrated model compares to the experimental data. The model is used to drive the behaviour of a robot that has to integrate socially in a group of zebrafish. We show experimentally that a biomimetic multilevel and context-dependent model allows good social integration of fish and robots in a structured environment.

How mimetic should a robotic fish be to socially integrate into zebrafish groups

Biomimetic robots are promising tools in animal behavioural studies. If they are socially integrated in a group of animals, they can produce calibrated social stimuli to test the animal responses. However, the design of such social robots is challenging as it involves both a luring capability including appropriate robot behaviours, and the acceptation of the robots by the animals as social companions. Here, we investigate the integration of a biomimetic robot driven by biomimetic behavioural models into a group of zebrafish (Danio rerio). The robot behaviours are based on a stochastic model linking zebrafish visual perception to individual behaviour and calibrated experimentally to correspond to the behaviour of zebrafish. We show that our robot can be integrated into a group of zebrafish, mimic their behaviour and exhibit similar collective dynamics compared to fish-only groups. This study shows that an autonomous biomimetic robot was enhanced by a biomimetic behavioural model so that it can socially integrate into groups of fish.

Building a safe robot for behavioral biology experiments

A robot accepted by animals as conspecific is a very powerful tool in behavioral biology, particularly in studies of gregarious animals. However in experiments where animals and robots share the same physical environment, there is always a risk of a robot accident that can lead to animal injuries. Safety regulations have to be developed to guide the design of an intrinsically safe robotic hardware and software. Currently this question is not addressed in experimental biology. In this paper, we present our efforts to build a safe robot for experimentation with domestic chickens. The methodology we use is based on robot safety studies done in the field of physical humanrobot interaction. The safety elements were introduced in the mechanical design of the robot, its control system and into the experimental environment. We show how in particular cases, when local information available to the robot is insufficient to detect an abnormal situation, the global information provided by the external vision system can be used by a novelty detection system based on extreme value theory. We believe that this study can be useful for robotic researchers providing robots for biological studies, as the concepts presented are universal and can be applied to other types of animals.

Designing a socially integrated mobile robot for ethological research

Abstract A robot introduced into an animal group, accepted by the animals as conspecifics, and capable of interacting with them is an efficient tool for ethological research, particularly in studies of collective and social behaviour. In this paper, we present the implementation of an autonomous mobile robot developed by the authors to study group behaviour of chicks of the domestic chicken (Gallus gallus domesticus). We discuss the design of the robot and of the experimental framework that we built to run animal–robot experiments. The robot design was experimentally validated, we demonstrated that the robot can be socially integrated into animal groups. The designed system extends the current state of the art in the field of animal–robot interaction in general and the birds study in particular by combining such advantages as (1) the robot being a part of the group, (2) the possibility of mixed multi-robot, multi-animal groups, and (3) close-loop control of robots. It opens new opportunities in the study of behaviour in domestic fowl by using mobile robots; being socially integrated into the animal group, robots can profit from the positive feedback mechanism that plays key roles in animal collective behaviour. They have potential applications in various domains, from pure scientific research to applied areas such as control and ensuring welfare of poultry.