Senior Robotics Software Engineer
HOPE Technik, Singapore


Task allocation refers to the general problem of organizing the workforce of a group on a set of tasks. Task allocation methods deal with the problem of defining who is doing what and when. The methods for tackling the task allocation problems can be divided into two groups: intentional and self-organized. Intentional task allocation is an approach by which the allocation of individual to tasks is defined at a global level, through negotiation and expicit communication. Self-organized task allocation, on the other hand, relies on local decisions and communication.

My work in task allocation concerns self-organized task allocation. Self-organized task allocation is based on swarm intelligence principles, and usually leads to scalable, robust and fault tolerant solutions.

Task allocation, is sometimes coupled with task partitioning: tasks are first partitioned into sub-tasks and then individuals need to be allocated to these sub-tasks. Developing methods and algorithms for autonomous task partitioning and task allocation is important in view of robotic systems that are able to autonomously organize their work.

Costs and benefits of behavioral specialization

Behavioral specialization is a mechanism by which an individual adapts his behavior to focus on a subset of all the possible tasks. An advantage of specialization arises when individuals can learn: by repeating the same tasks, the individuals improve in performing them. However, specialization can also entail costs, for example when individuals need to search for the tasks in which they are specialized. In our work we study the situation in which a swarm of robots learn when repeatedly performing the same task. We study the tradeoff between costs and benefits of a strategy that exploits behavioral specialization.

For more information about this work please refer to: