Distributed Cognitive Aid with Scheduling and Interactive Task Guidance

RESNA 28th Annual Conference - Atlanta, Georgia

Edmund F. LoPresti1, Richard Simpson2, Ned Kirsch3, Debra Schreckenghost4, Steve Hayashi1

1AT Sciences, Pittsburgh, PA; 2University of Pittsburgh, Pittsburgh, PA;

3University of Michigan; Ann Arbor, MI; 4Metrica/TRACLabs; Houston, TX


Solo is a cognitive assistive device that provides support in remembering when to perform tasks, remembering the steps in a task, and recovering from unexpected events. The system includes an interface for clients to receive reminders, an interface for caregivers to enter information about the client’s schedule, and a Cognition Manager which provides reminders and task guidance at appropriate times.


Cognitive disability, prospective memory, traumatic brain injury, task guidance, memory aid


External cueing systems can assist people with cognitive disabilities in the performance of activities of daily living [1]. Such devices can remediate prospective memory limitations by reminding someone to perform a task at the appropriate time. However, a person may also need assistance with multi-step activities due to problems remembering the steps in the task, problems with sequential processing (e.g., add flour and butter before adding water) or other difficulties [2,3]. Therefore, people may also benefit from a task guidance system that is able to provide messages in sequence.

In addition to prospective memory and sequential processing limitations, a person may have difficulty with problem solving [4]. If events do not occur in the expected order, the person may not be able to recover by finding alternative ways to accomplish a task. In most cases, this is a limitation shared by technology. However, artificial intelligence systems can be taught rules for rearranging plans in response to unexpected events; thus providing problem solving support for people with cognitive disabilities.


The goal of this study is to develop a single system, called Solo, which provides both scheduling assistance and task guidance, as well as intelligent, automatic re-planning on the levels of both the schedule and individual tasks. To circumvent the limited processing capabilities and memory of existing handheld devices, Solo will use a distributed architecture. Automated schedule management takes place on a central server. Clients receive instructions remotely on any internet-enabled computer, personal digital assistant, or cell phone. This distributed architecture supports interactive communication with both the client and his or her clinician or caregiver. The device will be able to elicit feedback from the client to inform changes in plans if obstacles arise to performing the task. Clinicians and caregivers will also be able to remotely access the schedule in order to add new tasks and learn of difficulties and successes.


The Solo system has four components:

The Cognition Manager consists of a Schedule Sequencer that manages the client’s schedule, and an Instruction Sequencer that manages the sequence of steps within a task. The Schedule Sequencer is based on the Adversarial Planner [5] and the Instruction Sequencer is based on RAPS (I/NET Inc, Chicago IL). The Schedule Sequencer makes individual tasks “active” at the appropriate time and rearranges the schedule if it becomes apparent that more time is required for a particular task. The Instruction Sequencer presents the current active task, providing subsequent steps as the user progresses through the task. It can automatically alter the sequence of steps in response to problems or based on client responses.

The Activity Assistant receives information from the Cognition Manager related to the current step of the active task. Based on this information, it dynamically generates a web page which presents this information to the client. The Activity Assistant makes this dynamically generated web page available over the internet. The client can direct a standard web browser on his or her PDA or other device to the page generated for him or her by the Activity Assistant. As the client progresses through the task, his or her web browser remains directed to the same web address. The Activity Assistant dynamically changes the web page at this address to reflect the current step in the task as further information is provided by the Cognition Manager. The Activity Assistant also collects information based on the client’s response and/or the passage of time, and reports this information to the Cognition Manager.

The Design Assistant allows caregivers to define the steps necessary to complete an activity. The user interface is being designed to support caregivers both with and without skills in task analysis. A caregiver who is familiar with a client's typical difficulties will be able to incorporate contingency planning in the task so that clients can recover from common errors. The Design Assistant will also allow the caregiver to compose the client's daily schedule.


Currently, Solo includes preliminary versions of the Design Assistant, the Cognition Manager’s Instruction Sequencer, and the Activity Assistant. This version will be used in a series of clinical trials described below. Meanwhile, the Schedule Sequencer is being integrated into the Cognition Manager.


Initial tests of the Solo system will include both clinical trials and usability trials. Clinical trials will include three participants with a history of acquired cognitive impairments. The goal of the clinical trials will be to demonstrate that the cueing and guidance provided by a clinician can be transferred to Solo, thereby increasing the possibility that the patient will be able to engage in these activities independently.

For each participant, one activity will be selected for intervention. During intervention sessions, each participant will be provided with an iPaq handheld computer (HP, Palo Alto CA). This device will be used to present instructions developed with the Design Assistant and served by a prototype version of the Activity Assistant. The messages will be based on a task analysis of the activity, and will be much the same as those that would otherwise be offered by a clinician.

For every activity or behavior, data will be collected including: a) time to task completion; b) number of sequencing errors; c) number of sub-task omission errors; and d) number of interventions required from the therapist. Performance of the target activity using Solo will be compared to baseline performance. Based on the specific client and targeted activity, typical hypotheses may be: a) time to completion will be shorter; b) sequencing errors will be fewer; c) errors during performance of sub-tasks will be fewer; d) sub-task omissions will be fewer; d) therapist interventions will be fewer, or e) the targeted behavior will occur more or less frequently, depending on clinically identified goals. Results will be used to inform system revisions and guide subsequent enhancements.

Usability trials by clinicians familiar with instructional requirements are planned to assess the extent to which the Design Assistant is both functional and usable. Twenty-four clinicians will be recruited for usability trials. Features of the system will be demonstrated and clinicians will have the opportunity to perform sample activities such as defining a task or entering schedule information. Participants will then rate the software. Performance measures include (1) usability ratings; (2) learning time; and (3) completion time for tasks such as creating an activity or schedule.


  1. Kime, S., Lamb, D., & Wilson, B. (1995). Use of a comprehensive program of external cueing to enhance procedural memory in a patient with dense amnesia. Brain Injury, 10:17-25.
  2. Kirsch, N.L., Shenton, M., Spirl, E., Rowan, J., Simpson, R., Schreckenghost, D. & LoPresti, E. (2004). Web-based assistive technology interventions for cognitive impairments after traumatic brain injury: A selective review and two cases studies. Rehabilitation Psychology, 49(3):200-212.
  3. Davies, D.K., Stock S.E., Wehmeyer M.L. (2004). A Palmtop Computer-Based Intelligent Aid for Individuals with Intellectual Disabilities to Increase Independent Decision Making. Research & Practice for Persons with Severe Disabilities, 28(4):182-193.
  4. Levinson, R. (1997). PEAT: The planning and execution assistant and training system. Journal of Head Trauma Rehabilitation, 12(2).
  5. Elsaesser, C., & MacMillan, T.R. (1991). Representation and Algorithms for Multiagent Adversarial Planning. Technical Report MTR-91W000207. MITRE, Wash. D.C.


This research is funded by a Phase I Small Business Innovation Research grant from the NIH National Institute of Child Health and Human Development (# 5 R43 HD44277-02).

Author Contact Information:

Edmund LoPresti, Ph.D.
AT Sciences
160 N. Craig St. Suite 117
Pittsburgh, PA 15213
Phone: 412-687-1181
Fax: 412-687-1181
E-mail: edlopresti@at-sciences.com