Alle Publikationen
- <<
- <
- 1
2017
-
(2017): Toward an intelligent long-term assistance for people with dementia in the context of navigation in indoor environments : Intelligente Langzeit-Unterstützung für Menschen mit Demenz im Kontext der Navigation in Gebäuden. In: Universität Würzburg, Graduate School of Science and Technology
Abstract: Designed and examined a system for indoor environments for people with moderate to severe dementia, who are unable or reluctant to use smartphone technology. To this end, a series of 10 studies was conducted with total of 35 adults with dementia. In the first step, a user-centered design approach was adopted to gather context and requirements of people with dementia in order to understand needs and difficulties (especially in spatial disorientation and wayfinding problems) experienced in dementia care facilities. Then, an "Implicit Interactive Intelligent (III) Environment" for people with dementia was proposed emphasizing implicit interaction and natural interface. The backbone of this III Environment is based on supporting orientation and navigation tasks with three systems: a monitoring system, an intelligent system, and a guiding system. The monitoring system and intelligent system automatically detect and interpret the locations and activities performed by the users i.e. people with dementia. This approach (implicit input) reduces cognitive workload as well as physical workload on the user to provide input. The intelligent system is also aware of context, predicts next situations (location, activity), and decides when to provide an appropriate service to the users. The guiding system with intuitive and dynamic environmental cues (lighting with color) has the responsibility for guiding the users to the places they need to be. Overall, three types of a monitoring system with Ultra-Wideband and iBeacon technologies, different techniques and algorithms were implemented for different contexts of use. They showed a high user acceptance with a reasonable price as well as decent accuracy and precision. In the intelligent system, models were built to recognize the users' current activity, detect the erroneous activity, predict the next location and activity, and analyze the history data, detect issues, notify them and suggest solutions to caregivers via visualized web interfaces. Regarding the guiding systems, five studies were conducted to test and evaluate the effect of lighting with color on people with dementia. The results were promising. Although several components of III Environment in general and three systems, in particular, are in place (implemented and tested separately), integrating them all together and employing this as a fully properly evaluation with formal stakeholders (people with dementia and caregivers) need to be examined in future research.
2016
-
(2016): Socially adaptive path planning in human environments using inverse reinforcement learning. In: International Journal of Social Robotics 8 (1), S. 51-66. DOI: 10.1007/s12369-015-0310-2
DOI: https://doi.org/10.1007/s12369-015-0310-2 Abstract: A key skill for mobile robots is the ability to navigate efficiently through their environment. In the case of social or assistive robots, this involves navigating through human crowds. Typical performance criteria, such as reaching the goal using the shortest path, are not appropriate in such environments, where it is more important for the robot to move in a socially adaptive manner such as respecting comfort zones of the pedestrians. We propose a framework for socially adaptive path planning in dynamic environments, by generating human-like path trajectory. Our framework consists of three modules: a feature extraction module, inverse reinforcement learning (IRL) module, and a path planning module. The feature extraction module extracts features necessary to characterize the state information, such as density and velocity of surrounding obstacles, from a RGB-depth sensor. The inverse reinforcement learning module uses a set of demonstration trajectories generated by an expert to learn the expert’s behaviour when faced with different state features, and represent it as a cost function that respects social variables. Finally, the planning module integrates a three-layer architecture, where a global path is optimized according to a classical shortest-path objective using a global map known a priori, a local path is planned over a shorter distance using the features extracted from a RGB-D sensor and the cost function inferred from IRL module, and a low-level system handles avoidance of immediate obstacles. We evaluate our approach by deploying it on a real robotic wheelchair platform in various scenarios, and comparing the robot trajectories to human trajectories. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
- <<
- <
- 1