Quantifying the biomimicry gap in biohybrid robot-fish pairs.

Biohybrid systems in which robotic lures interact with animals have become compelling tools for probing and identifying the mechanisms underlying collective animal behavior. One key challenge lies in the transfer of social interaction models from simulations to reality, using robotics to validate the modeling hypotheses. This challenge arises in bridging what we term the 'biomimicry gap', which is caused by imperfect robotic replicas, communication cues and physics constraints not incorporated in the simulations, that may elicit unrealistic behavioral responses in animals. In this work, we used a biomimetic lure of a rummy-nose tetra fish (Hemigrammus rhodostomus) and a neural network (NN) model for generating biomimetic social interactions. Through experiments with a biohybrid pair comprising a fish and the robotic lure, a pair of real fish, and simulations of pairs of fish, we demonstrate that our biohybrid system generates social interactions mirroring those of genuine fish pairs. Our analyses highlight that: 1) the lure and NN maintain minimal deviation in real-world interactions compared to simulations and fish-only experiments, 2) our NN controls the robot efficiently in real-time, and 3) a comprehensive validation is crucial to bridge the biomimicry gap, ensuring realistic biohybrid systems.

Predicting the long-term collective behaviour of fish pairs with deep learning.

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social interactions in the fish species Hemigrammus rhodostomus. We compare the results of our deep learning approach with experiments and with the results of a state-of-the-art analytical model. To that end, we propose a systematic methodology to assess the faithfulness of a collective motion model, exploiting a set of stringent individual and collective spatio-temporal observables. We demonstrate that machine learning (ML) models of social interactions can directly compete with their analytical counterparts in reproducing subtle experimental observables. Moreover, this work emphasizes the need for consistent validation across different timescales, and identifies key design aspects that enable our deep learning approach to capture both short- and long-term dynamics. We also show that our approach can be extended to larger groups without any retraining, and to other fish species, while retaining the same architecture of the deep learning network. Finally, we discuss the added value of ML in the context of the study of collective motion in animal groups and its potential as a complementary approach to analytical models.

Bidirectional interactions facilitate the integration of a robot into a shoal of zebrafish Danio rerio.

Many studies on collective animal behavior seek to identify the individual rules that underlie collective patterns. However, it was not until the recent advancements of micro-electronic and embedded systems that scientists were able to create mixed groups of sensor-rich robots and animals and study collective interactions from the within a bio-hybrid group. In recent work, scientists showed that a robot-controlled lure is capable of influencing the collective decisions of zebrafish Danio rerio shoals moving in a ring and a two-room setup. Here, we study a closely related topic, that is, the collective behavior patterns that emerge when different behavioral models are reproduced through the use of a robotic lure. We design a behavioral model that alternates between obeying and disobeying the collective motion decisions in order to become socially accepted by the shoal members. Subsequently, we compare it against two extreme cases: a reactive and an imposing decision model. For this, we use spatial, directional and information theoretic metrics to measure the degree of integration of the robotic agent. We show that our model leads to similar information flow as in freely roaming shoals of zebrafish and exhibits leadership skills more often than the open-loop models. Thus, in order for the robot to achieve higher degrees of integration in the zebrafish shoal, it must, like any other shoal member, be bidirectionally involved in the decision making process. These findings provide insight on the ability to form mixed societies of animals and robots and yield promising results on the degree to which a robot can influence the collective decision making.