Rapid fault recovery strategies for resilient robot swarms


Robots are increasingly becoming an important part of our day-to-day lives, automating tasks such as keeping our homes clean, and picking/packing our parcels at large warehouses. The existing fault-tolerant systems for robot swarms are limited. They are constrained to diagnose only faults anticipated a priori by the designer, which can hardly encompass all the possible scenarios a robot swarm may encounter while operating in complex environments for extended periods. Fault recovery in a robot swarm may instead be formulated as an online behaviour-adaptation process. With such an approach, the robots of the swarm adapt their behaviour to sustained faults by rapidly learning via trial-and-error new compensatory behaviours that work despite the faults.

Project aims

The overall aim of this project is to lay the algorithmic foundations for resilient robot swarms, capable of rapidly — in no more than a few minutes — recovering from faults and damages sustained by individual robots of the swarm. This is to be achieved by developing a novel family of algorithms to (i) creatively discover a large and diverse map of swarm robot behaviours, and (ii) when damaged (discovered by a drop in robot’s performance), efficiently select compensatory behaviours from the map via trial-and-error reset-free learning.


Autonomous operation will be an essential feature of the next generation of robot swarms, allowing the robots to continue functioning despite faults resulting from common wear and tear of their functional parts, and unexpected changes in their operational environments. This ability increases the usefulness of the robots, and extends the amount of time they can continue operating without human intervention, thus providing a substantial economic advantage. A promising real-world application scenario for robot swarms is that of autonomous surface vehicles (ASVs) in rivers, lakes and marine environments. In such environments, robots are required to operate over vast areas, with minimal human intervention. ASV robots have been commercialised, and widely used in commerce, industry and military applications; such an established and active market for the platform now opens up potential avenues for applications with ASV swarms.


Algorithms developed within the scope of this project are available open-source on GitHub.


The project acknowledges support of the EPSRC New Investigator Award grant EP/R030073/1.