Relational approach to knowledge engineering for POMDP-based assistance systems as a translation of a psychological model

Abstract

Assistive systems for persons with cognitive disabilities (e.g. dementia) are difficult to build due to the wide range of different approaches people can take to accomplishing the same task, and the significant uncertainties that arise from both the unpredictability of client's behaviours and from noise in sensor readings. Partially observable Markov decision process (POMDP) models have been used successfully as the reasoning engine behind such assistive systems for small multi-step tasks such as hand washing. POMDP models are a powerful, yet flexible framework for modelling assistance that can deal with uncertainty and utility. Unfortunately, POMDPs usually require a very labour intensive, manual procedure for their definition and construction. Our previous work has described a knowledge driven method for automatically generating POMDP activity recognition and context sensitive prompting systems for complex tasks. We call the resulting POMDP a SNAP (SyNdetic Assistance Process). The spreadsheet-like result of the analysis does not correspond to the POMDP model directly and the translation to a formal POMDP representation is required. To date, this translation had to be performed manually by a trained POMDP expert. In this paper, we formalise and automate this translation process using a probabilistic relational model (PRM) encoded in a relational database. The database encodes the relational skeleton of the PRM, and includes the goals, action preconditions, environment states, cognitive model, client and system actions (i.e., the outcome of the SNAP analysis), as well as relevant sensor models. The database is easy to approach for someone who is not an expert in POMDPs, allowing them to fill in the necessary details of a task using a simple and intuitive procedure. The database, when filled, implicitly defines a ground instance of the relational skeleton, which we extract using an automated procedure, thus generating a POMDP model of the assistance task. A strength of the database is that it allows constraints to be specified, such that we can verify the POMDP model is, indeed, valid for the task given the analysis. We demonstrate the method by eliciting three assistance tasks from non-experts: handwashing, and toothbrushing for elderly persons with dementia, and on a factory assembly task for persons with a cognitive disability. We validate the resulting POMDP models using case-based simulations to show that they are reasonable for the domains. We also show a complete case study of a designer specifying one database, including an evaluation in a real-life experiment with a human actor.

Automated Planning for Ubiquitous Computing

“…For unknown values, Eppe and Bhatt [2015] create multiple possible states and pick the one that contains the missing information provided by sensing actions. The rest of the classified studies deal with partial observability using observations based on probabilistic models, such as dynamic Bayesian networks [Kr üger et al 2011], Markov decision processes [Grześ et al 2014;Jean-Baptiste et al 2015], and other probability distributions Harrington and Cahill 2011].…”

“…MDPs are used to produce plans that maximise an expected reward [Courtemanche et al 2008] and maximise user requirements [Yau and Buduru 2014]. POMDPs are employed to model uncertainty coming from the unpredictability of human behaviour and inconsistency of data [Grześ et al 2014], and to compute plans that provide optimal alerts to people [Jean-Baptiste et al 2015]. adopt a partially observable planning approach to reason over belief situations and reach situations in which plans with satisfactory values are found.…”

Energy Efficient Execution of POMDP Policies

“…We developed a POMDP model for a mobile application called "LaCasa" [11], [26] that estimates the risk faced by the PwD and decides on the appropriate action to take, such as prompting the PwD or calling the caregiver. The model was designed and instantiated using our technique for engineering POMDPs [27]. Contextual information gathered from sensors is integrated into the model, including current location, battery power, and proximity to the caregiver.…”

Analysis on the Cognition Process and Teaching Reform of English Translation Based on the Theory of Cognitive Psychology

“…In the study of translation theory: scholars have repeatedly emphasized that the understanding and mastery of the translation process is the cornerstone for the improvement of translation quality; some scholars believe that translation work is an important practice of language psychology; some scholars applied constructivism to translation teaching and conducted relevant practical researches. Based on the researches of scholars in the industry, this paper aims to demonstrate the Bell's translation process model through translation teaching experiment, and to explore the relevance of translators' psychological cognition level and the translation quality (Ulvydiene, 2013;Grze, Hoey, Khan et al, 2014).…”