Syed Atif Mehdi

Methodology for robot mapping and navigation in assisted living environments

Robust navigation in living environments demands high requirements on the control system of a robot. Due to typically narrow passages between obstacles, precise navigation is required. To achieve accuracy in navigation, detailed representation of the environment around the robot needs to be developed. Robust and precise mapping of the environment helps in overcoming the dynamics in the living environment like movement of furniture and human beings. Prompt recovery from unreachable paths while navigating is also an essential component of the living environment robots. This paper describes a behaviour-based navigation system in assisted living environments. The navigation system uses a grid map created from data obtained from laser scanner and ultrasonic sensors mounted on a small sized robot, ARTOS. ARTOS is specially designed for indoor living environments able to navigate through narrow corridors and closely placed furniture in the living environment.

Use of an Autonomous Mobile Robot for Elderly Care

In our societies, there is a steady increase in the elderly population. These people need a constant supervision to perform simple tasks at their homes, which is sometimes not possible. This lack of permanent attention sometimes results in the late detection of emergency situations. Therefore, it is judicious to promote technology that helps to detect and react in case of emergency situations. In the last decade, monitoring devices have been installed in the home environments for the surveillance of the inhabitant. However, due to poor privacy there will be an unfavourably low acceptance of such systems. Another approach to the problem is to develop mobile robots for elderly care. In this scenario, a mobile robot has to navigate from place to place to search for the elderly person. Navigating inefficiently in the home environment may delay the process of searching. This paper focus on the aspect of enhancing navigational efficiency of the robot that would speed up the task of finding human being in the unstructured and dynamic household environment. To achieve precision in searching the human, a behaviour based Markov decision process (MDP) along with a detailed representation of the environment as a grid map have been developed on a small sized indoor autonomous mobile robot, ARTOS.

Behavior-based search of human by an autonomous indoor mobile robot in simulation

The paper focuses on the development of a behavior-based strategy for an indoor autonomous mobile robot to find an elderly person living alone in an unstructured home environment. A perception of presence of human being in different rooms at different times of the day is maintained. Based on this perception, the estimation of possible locations of a person is carried out using Markov decision process. The implemented methodology mainly focuses on the two criteria for searching the person, namely distance to the destination and the probability of finding the person at that location. It also takes into account the last known position of the human being for the final estimation of the possible location. The robot navigates autonomously to the desired location by planning a path and avoiding the obstacles in the way. Upon reaching the destination, the process of detecting the human being in the surrounding environment is carried out. In order to validate all aspects of the robotic behavior over a longer period of time, prior to be used in an elderly care environment, a simulated environment resembling the real home apartment has been created. To make the simulation more realistic, an animated human character has also been developed which walks in to different rooms and exhibit different postures during its movements. The promising results from the 3D simulation show the effectiveness of the developed methodology.

Using an autonomous robot to maintain privacy in assistive environments

In our societies, the number of senior citizens living on their own is increasing steadily. The lack of permanent attention results in the late detection of emergency situations. Labour-intensive care is already a high burden for the society; therefore, it seems reasonable to promote technology that helps to detect and react in case of emergency situations that elderly people may encounter. In the last decade, assistive environments have been established by integrating surveillance devices into the living environments giving remote operators access to monitor the senior inhabitant at home for detecting emergency situations. However, due to poor privacy in terms of intrusion into the private life of an elderly person, there will be an unfavourably low acceptance of such systems. This paper introduces a two-stage strategy and proposes to replace a possibly large number of human-controlled monitoring devices by a single autonomous mobile system. The first stage will be performed by the autonomous system to detect an emergency situation. The human operator will be obligatory only at the final stage when the system assumes that an emergency has occurred and the final evaluation of the situation is required. The self-assessment will reduce the human factor related to privacy issues. Copyright

A survey of human location estimation in a home environment

In recent years, much effort has been made to provide services to an elderly person living alone at home. An essential component of facilitating the person is to identify his location in the home environment. Fundamentally, three different methods are being focused by the research community to address the issue of localizing the person. Most common approach is to install a variety of sensor systems in the home environment to track and monitor the person. Another variant includes developing wearable sensors that an elderly person carries with him all the time for being able to be tracked. A more recent approach, that is still under development, is to use an autonomous mobile robot in home environments to determine the location of the person. This paper attempts to summarize these efforts and provides directions for future research in finding the person in the home environment.

LiFe-support: an environment to get live feedback during emergency scenarios

The paper presents an environment, called LiFe-Support, for facilitating the caregiver staff at health service centers in getting live feedback of an emergency situation that may occur to an elderly person at home. The two main components of the system include an autonomous mobile robot, called ARTOS, for serving elderly people in their homes and a visual platform for the caregivers to control communication and navigation of the robot in case of an emergency situation. A preliminary evaluation of the LiFe-Support environment has been carried out and promising results indicate usefulness of the system.

Improvements in accuracy of single camera terrain classification

Autonomous terrain classification is an important requirement for robotic applications for the outdoor and more so for off-road systems. Different technique have been developed in recent years mainly relying on either color features or on texture-based features for classification. We present an approach which combines the two approaches and delivers an overall increase in performance and accuracy. We describe the computational framework, training dataset, off-line learning and real-time classification results of our system. We report overall average classification accuracies in excess of 98% in a fair experimental setup along with confusion matrices. Our method gives a noticeable improvement in accuracy for classifying similar terrain classes over the current state of the art that uses only texture for classification with acceptable overhead for real-time applications.

Behaviour based searching of human using MDP

Motivation -- To develop a methodology for cognitive search of elderly person in home environment that will help in reaching the inhabitant to determine health situations. Research approach -- A behaviour based Markov decision process (MDP) has been developed to build up cognitive information of the human at home. A simulated environment was also created to simulate the presence of human and prove the validity of the approach implemented. Design -- The idea is to enable the robot to comprehend when it is required to find the human being on its own. To achieve this task, behaviour based approach has been adapted where behaviour represents the desire to find the human and the policy for finding human is determined using MDP. Research limitations -- A simulated environment has been developed for the generation of dataset and afterwards verification of the implemented methodology. This simulated environment also gives the liberty of observing the human being as many times as is required which in real scenario is difficult to accomplish. Originality/Value -- The research promotes the need of developing behaviour based cognitive approach for finding human being in the environment. Take away message -- Using learning methodology along with behaviour based architecture might help in developing better cognitive robots.

Probabilistic search of human by autonomous mobile robot

This paper focuses on the development of an approach for an indoor mobile robot to search the elderly person living alone in an unstructured and dynamic household environment. In order to reach the elderly person, to perform different tasks or in case of an emergency, the mobile robot needs to navigate autonomously in the home environment with the perception of presence of the person at a particular place at a specific time. The estimation of possible locations of a person is carried out using a behavior based Markov Decision Process (MDP). The implemented methodology centers two criteria for searching the person, namely distance to the destination and the probability of finding the person at that location. This estimated destination is reached autonomously by the robot. The autonomous navigation is supported by building a detailed grid map of the environment and planning a path to the required target. Upon reaching the destination, a search for the human face is carried out using a Haar cascade classifier. To validate the methodology over a longer period of time, a 3D simulated environment has also been created. This environment resembles a real house environment and features simulation of a small robot, Artos, which performs the task of searching and a human simulation that walks around in different rooms. The results from simulation shows effectiveness of the developed methodology.

Ordering of Robotic Navigational Tasks in Home Environment

Autonomous navigation is an essential component of an indoor mobile robot. For an interactive user experience the robot should be able to understand multiple navigational tasks and perform them as optimally as possible. User may issue multiple random destinations to the robot to reach in a scenario like finding the elderly person, but to navigate randomly may result in an inefficient robot manoeuvring and may delay the process of finding the elderly person in the environment. To enhance the navigational efficiency, ordered and organised navigation based on certain cost function is required. In this paper, we are focusing on the need of organisation of navigational tasks keeping in view the unstructured and dynamic nature of the home environment. To achieve speed and accuracy in navigation, a detailed representation of the environment and a better evaluation of the cost function to organise the tasks is required. Navigation is based on grid map generated using laser scanner and sonar sensors mounted on the small sized indoor robot, ARTOS. The Navigational Cost is used for organising the tasks and is computed using A* algorithm to determine path to the destination.