Project Description

General Idea

Imagine a social or an industrial facility of the future where a team of robots have been deployed in order to provide services and accomplish everyday tasks such as

In such a context, different robots with different actuation, manipulation and perception capabilities must be coordinated in order to achieve various complex tasks that require collaborative actions with each other and with human operators. Thus, the effective and efficient supervision and coordination of the overall heterogeneous system mandates a decentralized framework that integrates

BOSCH lab 

Motivation

The World Robotics Survey1 points out that “…service robots for professional use boom…”, with indoor logistics being a major market. Sales of professional service robots in the logistics segment registered a growth of 28% in 2014 with the value of sales increasing to USD 2.2 billion. This shows the huge opportunity for European companies to address this area and satisfy the market demand. Emerging markets for indoor logistics robotics are offices, hotels and hospitals, where a close interaction between the robots and humans is required. For example, studies have given ground to the estimate that “logistics-related activities account for over 40 percent of a hospital's spending” and that medical staff spends up to 20% of their time on transportation tasks. Automating these tasks leads to great opportunities for cost savings.

Current practice in coordination of robotic teams is at a great deal based on offline, centralized planning, leaving only a little room for real- time and coordinated decentralized actions. This restricts the operational efficiency of the multi- robot system in crowded and dynamic environments, since in most cases, sudden changes in the environment, the type of assigned tasks, and the need for coordination, would cause the system to halt, ask for a human intervention and restart. Therefore, despite the fact that public facilities are in some degree pre-structured, the introduction of a decentralized, real-time, automated task (re)-planning framework for semi-autonomous systems

Based on the above ascertainments, the Co4Robots proposal is motivated by:

Task Coordination 

Objectives

Within co4robots, a team of heterogeneous robots needs to be coordinated when different tasks are assigned in a distributed, dynamic and non-predefined fashion. Based on these requirements, our goal is to build

The proposed framework builds upon various cases of base interactions between heterogeneous agent pairs, with the prototype inter-agent interactions consisting of

Considered Cases 
Cases Table