Animals and Robots
The goal of this project is to develop computational approaches for studying groups of agents with natural mobility and social interactions. The agents in such systems can move on their own due to complex interactions between biotic and abiotic factors, culminating in behaviors that can be studied and modeled using physical data, and ultimately controlled. We will develop algorithms for adaptive data collection during a field experiment, post-experiment data analysis for modeling behavior, and control of the movement of the group using the learned models in field experiments and environment data from satellite imagery.
The main motivation and application of this work is in the agricultural domain, in the area of free-ranging animal ecology, specifically for cattle. Groups of animals such as cattle herds are complex systems that are affected by many factors including age, group size, landscape topography, plant phenology, and weather. These factors produce interesting interactions among individuals such as friendship, kinship, group formation, leading and following. There are complex interactions with the environment as well, for example searching for drinking water or exploring a new paddock which often involves walking the perimeter along established fence lines.
This project combines computer networking, modeling, and robot motion planning and control. We use physical data collected for extensive periods of time in the field (by our collaborators at the USDA-ARS Jornada Experimental Range (JER) and CSIRO, Australia and in our previous work) to define behavior models for herds of animals, using these models to develop planning and control algorithms for coordinating the location of these herds, and using the location control system to manage the stock density and optimize the use of land. This includes:
- tracking the motion and activities of individual animals
- identifying natural group formation and behavior
- planning and controlling the location of individuals and groups
- managing the density of the group
- using animal groups as networked information backbones