Towards robust personal assistant robots: Experience gained in the SRS project

Abstract

SRS is a European research project for building robust personal assistant robots using ROS (Robotic Operating System) and Care-O-bot (COB) 3 as the initial demonstration platform. In this paper, experience gained while building the SRS system is presented. A main contribution of the paper is the SRS autonomous control framework. The framework is divided into two parts. First, it has an automatic task planner, which initialises actions on the symbolic level. The planner produces proactive robotic behaviours based on updated semantic knowledge. Second, it has an action executive for coordination actions at the level of sensing and actuation. The executive produces reactive behaviours in well-defined domains. The two parts are integrated by fuzzy logic based symbolic grounding. As a whole, they represent the framework for autonomous control. Based on the framework, several new components and user interfaces are integrated on top of COB's existing capabilities to enable robust fetch and carry in unstructured environments. The implementation strategy and results are discussed at the end of the paper

Semi-Autonomous Domestic Service Robots: Evaluation of a User Interface for Remote Manipulation and Navigation With Focus on Effects of Stereoscopic Display

“…• An underlying control architecture that allows recognition of robot failure states and smooth handover of control between robot and human remote operators [5] • System-assisted, semi-autonomous telemanipulation with offline trajectory execution and editing of 3D collision maps by the user for high controllability of the telemanipulation result yet safe, collision-free operation • Remote navigation with several control modes of different autonomy, with and without collision avoidance • An ecological visualization approach that integrates data from various sensors as well as other data like a robot model and collision indicators into a single 3D representation of the remote environment [16] • Visualization of colored point clouds enhanced by global 3D environment mapping [16,45] with a freely adjustable viewpoint for high situation awareness • Reliance on low-cost interaction devices in form of a standard mouse for viewpoint adjustments and a 3D mouse for precise and intuitive 6-DOF gripper positioning and 3-DOF robot navigation • Avoidance of the need for human compensation of displaycontrol misalignment by the ability to control robot and gripper in the coordinate system of the remote operator's chosen viewpoint on the 3D scene • Optional stereoscopic display mode using contemporary active shutter technology While most of these approaches have been used previously in an isolated form in various domains (e.g., [3,4,6,22,27,29,32,[36][37][38][39]46]), our user interface integrates them into a coherent experience, highly focused on real-world applications.…”

“…2. Its foundation is a control architecture that enables the robot to recognize failure states, contact human remote operators for assistance, and reassume control afterwards [5]. Local elderly people are equipped with a portable, smartphone- User interface concept with three user groups: elderly people at home, remote relatives, and professional teleassistants sized multi-touch device so the robot can be commanded from any position in the apartment.…”

“…If a robot is unable to carry out a task or fails during execution, a human operator may take control remotely, solve the problem, and hand back control to the robot [3][4][5][6][7]. The system may further assist the operator during teleoperation.…”

A survey on assistive chair and related integrated sensing techniques

“…In terms of the difficulties experienced by the elderly, standing up and sitting down rank in the top three on the list of the most expected homecare assistances [22]. Therefore, an assistive chair that will assist the elderly in need is in demand, and could possibly delay age-related impairment and further change their lifestyle to reduce the risk of potential diseases.…”

Mobile monitoring of physical states of indoor environments for personal support

“…One of the promising applications is a robot which lives with and takes care of the elderly. Such an assistive robot usually has mobility, object recognition and manipulation skills, and interaction abilities, and assists residents in various ways (e.g., [2], [3], [4], [5]). These works mainly focus on robot operations and human robot interaction.…”