COACHES Cooperative Autonomous Robots in Complex and Human Populated Environments

Abstract

The deployment of robots in dynamic, complex and uncertain environments populated by people is gaining more and more attention, from both research and application perspectives. The new challenge for the near future is to deploy intelligent social robots in public spaces to make easier and safer the use of these spaces. In this paper, we provide an overview of the COACHES project which addresses fundamental issues related to the design and development of autonomous robots to be deployed in public spaces. In particular, we describe the main components in which Artificial Intelligence techniques are used and integrated with the robotic system, as well as implementation details and some preliminary tests of these components. Public spaces in large cities are becoming increasingly complex and unwelcoming environments because of the overcrowding and complex information in signboards. It is in the interest of cities to make their public spaces easier to use, friendlier to visitors and safer to increasing elderly population and to the people with disabilities. In the last decade, we observe tremendous progress in the development of robots in dynamic environments populated by people. There are thus big expectations in the deployment of robots in public areas (malls, touristic sites, parks, etc.) to offer services to welcome people in the environment and improve its usability by visitors, elderly or disabled people. Such application domains require robots with new capabilities leading to new scientific challenges: robots should assess the situation, estimate the needs of people, socially interact in a dynamic way and in a short time, with many people, the navigation should be safe and respects the social norms. These capabilities require new skills including robust and safe navigation, robust image and video processing, short-term human-robot interaction models, human need estimation techniques and distributed and scalable multi-agent planning.

Context Aware Robot Architecture, Application to the RoboCup@Home Challenge

“…While AI 1 methods and technologies progress, expectations about service robotics are growing. This is particularly true in complex human-populated environments [1]. In this context we aim to define software architectures that orchestrate and combine different high level abilities and their sub-functions.…”

Efficient Long-term Mapping in Dynamic Environments

“…In the last years, robots have been progressively introduced in public environments where space is shared with humans, such as shopping centers [1], airports [2], elder care homes [3], hospitals or museums. In order to navigate autonomously these environments, robots require a map of the building in which they have to operate.…”

“…Map information obtained over different sessions is managed by the same graph structure obtaining a balance between simplicity and effectiveness in determining both intra-and inter-session loop closures. We release our system as open source 1 which provides ROS compatibility and visualization tools.…”