Increasing the Efficiency of Low-land Natural Disaster Search and Rescue through ‘Supervised Hybrid Animal-UAV Interactions’ (completed)

Starting Date: Summer 2021
Prerequisites: Python, C++, Undergraduate Student
Will results be assigned to University: No

Search and Rescue (SAR) is a time-critical event: after a finite period of time the chances of recovering individuals who have become lost, or trapped in the wake of a disaster, trend towards zero. As a result, management of search and rescue resources is paramount. Travel time, planning and executing search grids, are pivotal tasks which demand expediency as well as accuracy One must also account for the replacement of exhausted human, animal and technological assets over time. We must therefore consider the critical points of failure in search and rescue operations: misallocation of resources based on false positives (misidentification of proof/presence of life), and the ability of experts to process information and allocated critical assets (doctors, search teams, animals) to where they are needed both quickly and accurately.

Intelligence data, and the speed with which it can be rendered into an actionable analysis upon which a search strategy can be build or adapted, is the key ingredient to this process. As commercial UAVs have become affordable and increased in endurance/flight times, smaller SAR operations have benefitted from a flow of aerial reconnaissance that they could not have benefitted from a decade ago. Still, we see issues in how the data provided by said drones may be interpreted, and how this intelligence informs the allocation of key assets. Alongside these UAV systems stand canine assets, SAR-trained tracking dogs capable of identifying where victims of disasters may be trapped. These animals excel at relatively short-range location of victims, but are costly to train and are thus a limited resource. This returns us to the first problem: where do we allocate canine assets in large scale low land search operations to maximise the speed with which individuals may be found and given appropriate treatment? In the wake of natural disasters, landscapes may change significantly, requiring systems that can rapidly map an area before assessing where the likely hotspots of post-disaster human presence may be.

This project will explore the use of canine biometric data (ECG data associated with excitation during training activities) and hypothetical haptic feedback systems (vibrations from pads in a dog harness), to model the UAV portion of a hybrid animal-UAV search and rescue system. The aim of this project is to produce a proof-of-concept system, identifying how UAVs may direct simulated canine assets to areas with a high probability of post-disaster human presence, using biometric data from canine assets to automatically report on the likelihood of survivors/remains without a human-in-loop component. This will increase the speed with which machine and animal assets (and handlers) can be moved within a changing SAR environment, without burdening strategic control, who must also oversee relief efforts involving medical supplies and expert human assets such as doctors.

Required Skills

The ideal candidate will have well-developed Python and C++ skills, and a familiarity with simulation software such as Matlab and Simulink. AirSim will be used for UAV simulation, which possesses a Python, Java, C# and C++ API. An attention to detail and rigorous reporting skills are a must: this project requires a thorough logbook, design document and analysis of the resulting proof of concept.


  • Airsim model for Supervised Human-Animal Interactions for Low land Natural Disaster-based SAR
  • Data and logs associated with all experiments run in the simulation environment
  • Github/equivalent repository of project code, including all Airsim constructs, functions and API calls
  • An evaluation of the feasibility of the proposed system
  • A complete log book of development and analysis activities
  • OPTIONAL: hardware-in-loop demonstration of the project concepts in a small, controlled environment

ISG-SCC Track Record

ISG-SCC has successfully run the UROP for the last two years. The success of the previous two years has produced a patent application (under review by patent office) and commercial demo (MVP) under development, and five research papers. Corresponding undergraduate students are named as first authors on the papers and co-inventor on the patent application. Research papers by undergraduate students have won one ‘best student paper award’, featured in a news article on Medium and being pivotal for a World Economic Forum’s project for anti-corruption project. The ethos of ISG-SCC is that undergraduate students have the talent and imagination to sort out unique and innovative solutions. They just need guidance from established researchers, and this is what ISG-SCC will provide during the UROP.