SlideShare a Scribd company logo
On Self-Sufficiency of Verbal Route Directions for
       Blind Navigation with Prior Exposure

Aliasgar Kutiyanawala
Computer Science Assistive Technology Laboratory
Department of Computer Science
Utah State University
Logan, UT 84322-4205
aliasgar.k@aggiemail.usu.edu

Vladimir Kulyukin
Computer Science Assistive Technology Laboratory
Department of Computer Science
Utah State University
Logan, UT 84322-4205
vladimir.kulyukin@usu.edu

Daniel Bryce
Artificial Intelligence Laboratory
Department of Computer Science
Utah State University
Logan, UT 84322-4205
daniel.bryce@usu.edu

Abstract:
This paper presents a qualitative analysis of self-sufficiency of verbal route directions for
blind navigation in outdoor environments with limited prior exposure.

Introduction:
We define verbal route directions to be self-sufficient if they can be used by independent
visually impaired (VI) travelers to successfully navigate a route from A to B in a given
environment without any electronic aid capable of receiving external signals or any human
assistance [1]. We distinguish self-sufficient route directions from self-sufficient routes. A
self-sufficient route anticipates potential route execution failures and provides either extra
localization actions or contingencies for route repair. Self-sufficient verbal route directions
are complete or partial verbal realizations of self-sufficient routes. We conducted a
preliminary investigation of the self-sufficiency of verbal route directions for outdoor
environments with three completely blind students of Utah State University (USU). In this
study, the generation of routes and route directions was done manually. We selected two
routes on the Utah State University (USU) campus and manually wrote a set of route
directions which we believed to be self-sufficient and then encoded our route directions in
a computer program than ran on a Nokia E70 cellular phone. Furthermore, our
investigation was confined to the case when VI individuals receive prior exposure to the
route they will have to navigate independently. This study models the situation when a
visually impaired student navigates the route once with an O&M instructor or a friend and
then has to navigate the route independently.

Experiment:

Participants:
Three participants were recruited from the local community for the experiment through
phone interviews. Henceforth, they will be referred by fictitious names Alice, Bob and Carl.
All three individuals are completely blind USU students. All self report themselves as
independent travelers with good O&M skills. Alice and Carl are cane users where as Bob is
a dog user. Alice is in her mid thirties and Bob and Carl are in their twenties. All
participants had some familiarity with the Utah State University campus but were not
familiar with the routes that they had to navigate.

Method:
We partially followed the methods of Gaunet and Briffault [2]. Each of the two routes
shown in Figure 1 was manually broken into logical segments and route instructions for
each segment were written by the investigators and then machine-converted into audio
files using a text to speech software. The generated files were loaded on to a Nokia E70
cell phone equipped with a TALKS screen reader. Additional software was written that
allowed participants to browse the instructions.

The purpose of the experiment was explained to the participant and he/she was trained on
using the cell phone. The participant was then taken to the start of a route and walked the
entire route once. This was the training run where the experimenter read the route
instructions for each segment of the route and pointed out the various landmarks to the
participant. The participant was encouraged to ask questions and browse the instructions
on the cell phone.

After completion of the test run the training run (prior exposure), the participant was asked
to walk the route independently using only the instructions provided in the cell phone. The
experimenter followed the participant closely to ensure the participant’s safety and to take
observational notes. If the participant made a mistake (took a wrong turn, did not turn,
etc), the experimenter did not interrupt the participant but allowed him/her to realize
his/her mistake and, whenever possible, correct it. However, if the participant made a
serious deviation (a deviation that, in the experimenter's opinion, could have resulted in an
accident or caused the navigator to become lost) from the route, the experimenter stopped
the participant, explained the error to the participant and brought him/her back onto the
route. The time taken to complete the run was recorded along with the number and type of
mistakes made by the participant and the number of times the participant browsed
instructions for each segment. This procedure was repeated four times per participant per
route. For each participant, the test runs were spread over multiple days with no more than
two test runs per day.

Observations and Results:
Figure 2 shows graphs of the time taken by each participant to complete each test run of
routes A and B respectively. As expected, the completion time decreases with the number
of runs, which could be attributed to the increase in the participant's familiarity with the
route. The one exception to this trend was Bob's third run for route A. Bob relied heavily
on his dog and since there was a gap of a few days between Bob's second and third run, his
dog had forgotten the route. It was also observed that participant's frequency of accessing
route information decreased with the number of runs. All three participants almost never
accessed the route directions on the cell phone during the final run.

Figure 3 shows the graphs of the number of errors performed by each participant during
the test runs of route A and route B respectively. The number of errors performed while
navigating the route also decreases with the runs. Most of the errors made by the
participants were undershoot/overshoot errors where the participant either took the turn
too early or too late. A likely explanation for this behavior is that there were a lot of small
pathways breaking off from the main route and it was easy to get confused and take a
wrong path. There was also a location near the library where a sidewalk progressed to a
small open area which the participants had to cross to pick up the sidewalk on the other
side. Most errors were made at this location in the first and second runs. At the third and
fourth runs, the participants learned to cross the area.

Our observations and subsequent interviews with the participants made us conclude that
the problem was with our route directions. Thus, the errors could have been prevented by
issuing better route instructions that warned the participants about the possibility of
making those errors. It would have been beneficial to issue more specific localization and
repair route instructions for the participants to avoid making the errors or to detect
mistakes and then take appropriate corrective measures to get back on the route. If a route
segment has multiple pathways breaking off from one side, it may be better to have
instructions that ask the traveler to walk on the other side.

Although our instructions provided distance information for each route segment, Alice said
that she could not keep track of how far she had moved and so this information was of no
use to her. On the other hand, Carl was able to use the distance information very well. He
would walk the majority of the segment really quickly and start to look for the turns only
near the end of the path segment. This observation leads us to conclude that some amount
of cognitive modeling would be helpful for we want to automate the generation of self-
sufficient routes [3]. At the very least, the cognitive model should contain information on
the utility of distance information for the traveler.

Conclusion:
Visually impaired navigators can navigate a route successfully if they are provided with
route instructions for each segment of the route. The amount of time required for
navigating a route and the number of errors made in navigation decreases with the
familiarity with that route. It was also observed that some potential error situations could
be avoided by issuing warnings and error detection and correction mechanisms to the user.

References:

[1] Nicholson, J., Kulyukin, V., and Marston, J. (2009). Building Route-Based Maps for the
Visually Impaired from Natural Language Route Descriptions. To appear in Proceedings of
the 24-th International Cartographic Conference (ICC 2009), Santiago, Chile, November
2009.

[2] Gaunet, F., and Briffault, X. Exploring the functional specifications of a localized
wayfinding verbal aid for blind pedestrians: Simple and structured urban areas. Human-
Computer Interaction 20, 3 (2005), 267–314.

[3] Crandall, B., Klein, G., Hoffman, R. (2006). Working Minds: A Practioner’s Guide to
Cognitive Task Analysis. The MIT Press, Cambridge, MA.
Figure 1: Route A (in blue) and Route B (in red)

Image Description: This figure shows route A and route B on the Utah State University
campus.




        Figure 2: Time Taken to Complete Each Run of Route A and Route B

Image Description: This figure shows the time taken by each participant to complete each
run of Route A and Route B. It can be observed that the time taken to complete each run
decreases with the number of runs.
Figure 3: Number of Errors for Each Run of Route A and Route B

Image Description: This figure shows the number of errors made by each participant in
each run of Route A and Route B. It can be observed that the number of errors decreases
with the number of runs.

More Related Content

Similar to On Self-Sufficiency of Verbal Route Directions for Blind Navigation with Prior Exposure

A Wearable Two-Sensor O&M Device for Blind College Students
A Wearable Two-Sensor O&M Device for Blind College StudentsA Wearable Two-Sensor O&M Device for Blind College Students
A Wearable Two-Sensor O&M Device for Blind College Students
Vladimir Kulyukin
 
Toward Blind Travel Support through Verbal Route Directions: A Path Inference...
Toward Blind Travel Support through Verbal Route Directions: A Path Inference...Toward Blind Travel Support through Verbal Route Directions: A Path Inference...
Toward Blind Travel Support through Verbal Route Directions: A Path Inference...
Vladimir Kulyukin
 
Narrative Map Augmentation with Automated Landmark Extraction and Path Inference
Narrative Map Augmentation with Automated Landmark Extraction and Path InferenceNarrative Map Augmentation with Automated Landmark Extraction and Path Inference
Narrative Map Augmentation with Automated Landmark Extraction and Path Inference
Vladimir Kulyukin
 
The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...
The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...
The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...
Vladimir Kulyukin
 
Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...
Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...
Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...
Kasra Mokhtari
 
IRJET- Study on Pedestrian Crossing Behaviour at Intersections
IRJET-  	  Study on Pedestrian Crossing Behaviour at IntersectionsIRJET-  	  Study on Pedestrian Crossing Behaviour at Intersections
IRJET- Study on Pedestrian Crossing Behaviour at Intersections
IRJET Journal
 
Changes In Driver Behavior Resulting From Ped Countdowns
Changes In Driver Behavior Resulting From Ped CountdownsChanges In Driver Behavior Resulting From Ped Countdowns
Changes In Driver Behavior Resulting From Ped Countdownsbrianhuey
 
Ut 2014 presentation
Ut 2014 presentation Ut 2014 presentation
Ut 2014 presentation
KelwynDsouza1
 
Expanding Usage of Cellular Phones -1991
Expanding Usage of Cellular Phones -1991Expanding Usage of Cellular Phones -1991
Expanding Usage of Cellular Phones -1991Dominique Mintz
 
Barbeau enabling better mobility through innovations for mobile devices - o...
Barbeau   enabling better mobility through innovations for mobile devices - o...Barbeau   enabling better mobility through innovations for mobile devices - o...
Barbeau enabling better mobility through innovations for mobile devices - o...
Sean Barbeau
 
The human element
The human elementThe human element
The human elementblasterdude
 
INTELLIGENT BLIND STICK
INTELLIGENT BLIND STICKINTELLIGENT BLIND STICK
INTELLIGENT BLIND STICK
AM Publications
 
MODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONS
MODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONSMODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONS
MODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONS
IRJET Journal
 
15 ite árboles&zd
15 ite árboles&zd15 ite árboles&zd
15 ite árboles&zd
Sierra Francisco Justo
 
Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...
Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...
Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...
IJAEMSJORNAL
 
IRJET- Pedestrian Risk Analysis at Uncontrolled Midblock
IRJET- Pedestrian Risk Analysis at Uncontrolled MidblockIRJET- Pedestrian Risk Analysis at Uncontrolled Midblock
IRJET- Pedestrian Risk Analysis at Uncontrolled Midblock
IRJET Journal
 
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
Sean Barbeau
 

Similar to On Self-Sufficiency of Verbal Route Directions for Blind Navigation with Prior Exposure (20)

A Wearable Two-Sensor O&M Device for Blind College Students
A Wearable Two-Sensor O&M Device for Blind College StudentsA Wearable Two-Sensor O&M Device for Blind College Students
A Wearable Two-Sensor O&M Device for Blind College Students
 
Toward Blind Travel Support through Verbal Route Directions: A Path Inference...
Toward Blind Travel Support through Verbal Route Directions: A Path Inference...Toward Blind Travel Support through Verbal Route Directions: A Path Inference...
Toward Blind Travel Support through Verbal Route Directions: A Path Inference...
 
Narrative Map Augmentation with Automated Landmark Extraction and Path Inference
Narrative Map Augmentation with Automated Landmark Extraction and Path InferenceNarrative Map Augmentation with Automated Landmark Extraction and Path Inference
Narrative Map Augmentation with Automated Landmark Extraction and Path Inference
 
The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...
The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...
The Blind Leading the Blind: Toward Collaborative Online Route Information Ma...
 
1203
12031203
1203
 
071203
071203071203
071203
 
Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...
Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...
Pedestrian Density Based Path Recognition and Risk Prediction for Autonomous ...
 
IRJET- Study on Pedestrian Crossing Behaviour at Intersections
IRJET-  	  Study on Pedestrian Crossing Behaviour at IntersectionsIRJET-  	  Study on Pedestrian Crossing Behaviour at Intersections
IRJET- Study on Pedestrian Crossing Behaviour at Intersections
 
Changes In Driver Behavior Resulting From Ped Countdowns
Changes In Driver Behavior Resulting From Ped CountdownsChanges In Driver Behavior Resulting From Ped Countdowns
Changes In Driver Behavior Resulting From Ped Countdowns
 
Ut 2014 presentation
Ut 2014 presentation Ut 2014 presentation
Ut 2014 presentation
 
Expanding Usage of Cellular Phones -1991
Expanding Usage of Cellular Phones -1991Expanding Usage of Cellular Phones -1991
Expanding Usage of Cellular Phones -1991
 
Living Cully Walks Report
Living Cully Walks ReportLiving Cully Walks Report
Living Cully Walks Report
 
Barbeau enabling better mobility through innovations for mobile devices - o...
Barbeau   enabling better mobility through innovations for mobile devices - o...Barbeau   enabling better mobility through innovations for mobile devices - o...
Barbeau enabling better mobility through innovations for mobile devices - o...
 
The human element
The human elementThe human element
The human element
 
INTELLIGENT BLIND STICK
INTELLIGENT BLIND STICKINTELLIGENT BLIND STICK
INTELLIGENT BLIND STICK
 
MODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONS
MODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONSMODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONS
MODELLING OF PEDESTRIAN GAP ACCEPTANCE BEHAVIOUR AT UNCONTROLLED INTERSECTIONS
 
15 ite árboles&zd
15 ite árboles&zd15 ite árboles&zd
15 ite árboles&zd
 
Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...
Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...
Awareness on Road Signs and Markings of Drivers and Passengers along Maharlik...
 
IRJET- Pedestrian Risk Analysis at Uncontrolled Midblock
IRJET- Pedestrian Risk Analysis at Uncontrolled MidblockIRJET- Pedestrian Risk Analysis at Uncontrolled Midblock
IRJET- Pedestrian Risk Analysis at Uncontrolled Midblock
 
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
2015 Transportation Research Forum Webinar - Enabling Better Mobility Through...
 

More from Vladimir Kulyukin

Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...
Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...
Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...
Vladimir Kulyukin
 
Generalized Hamming Distance
Generalized Hamming DistanceGeneralized Hamming Distance
Generalized Hamming Distance
Vladimir Kulyukin
 
Adapting Measures of Clumping Strength to Assess Term-Term Similarity
Adapting Measures of Clumping Strength to Assess Term-Term SimilarityAdapting Measures of Clumping Strength to Assess Term-Term Similarity
Adapting Measures of Clumping Strength to Assess Term-Term Similarity
Vladimir Kulyukin
 
A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...
A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...
A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...
Vladimir Kulyukin
 
Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...
Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...
Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...
Vladimir Kulyukin
 
Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...
Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...
Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...
Vladimir Kulyukin
 
Text Skew Angle Detection in Vision-Based Scanning of Nutrition Labels
Text Skew Angle Detection in Vision-Based Scanning of Nutrition LabelsText Skew Angle Detection in Vision-Based Scanning of Nutrition Labels
Text Skew Angle Detection in Vision-Based Scanning of Nutrition Labels
Vladimir Kulyukin
 
Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...
Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...
Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...
Vladimir Kulyukin
 
Effective Nutrition Label Use on Smartphones
Effective Nutrition Label Use on SmartphonesEffective Nutrition Label Use on Smartphones
Effective Nutrition Label Use on Smartphones
Vladimir Kulyukin
 
An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...
An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...
An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...
Vladimir Kulyukin
 
An Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the Cloud
An Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the CloudAn Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the Cloud
An Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the Cloud
Vladimir Kulyukin
 
Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...
Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...
Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...
Vladimir Kulyukin
 
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vladimir Kulyukin
 
Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...
Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...
Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...Vladimir Kulyukin
 
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vladimir Kulyukin
 
Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...
Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...
Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...Vladimir Kulyukin
 
Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...
Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...
Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...Vladimir Kulyukin
 
Wireless Indoor Localization with Dempster-Shafer Simple Support Functions
Wireless Indoor Localization with Dempster-Shafer Simple Support FunctionsWireless Indoor Localization with Dempster-Shafer Simple Support Functions
Wireless Indoor Localization with Dempster-Shafer Simple Support Functions
Vladimir Kulyukin
 
RFID in Robot-Assisted Indoor Navigation for the Visually Impaired
RFID in Robot-Assisted Indoor Navigation for the Visually ImpairedRFID in Robot-Assisted Indoor Navigation for the Visually Impaired
RFID in Robot-Assisted Indoor Navigation for the Visually Impaired
Vladimir Kulyukin
 
RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...
RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...
RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...
Vladimir Kulyukin
 

More from Vladimir Kulyukin (20)

Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...
Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...
Digitizing Buzzing Signals into A440 Piano Note Sequences and Estimating Fora...
 
Generalized Hamming Distance
Generalized Hamming DistanceGeneralized Hamming Distance
Generalized Hamming Distance
 
Adapting Measures of Clumping Strength to Assess Term-Term Similarity
Adapting Measures of Clumping Strength to Assess Term-Term SimilarityAdapting Measures of Clumping Strength to Assess Term-Term Similarity
Adapting Measures of Clumping Strength to Assess Term-Term Similarity
 
A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...
A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...
A Cloud-Based Infrastructure for Caloric Intake Estimation from Pre-Meal Vide...
 
Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...
Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...
Exploring Finite State Automata with Junun Robots: A Case Study in Computabil...
 
Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...
Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...
Image Blur Detection with 2D Haar Wavelet Transform and Its Effect on Skewed ...
 
Text Skew Angle Detection in Vision-Based Scanning of Nutrition Labels
Text Skew Angle Detection in Vision-Based Scanning of Nutrition LabelsText Skew Angle Detection in Vision-Based Scanning of Nutrition Labels
Text Skew Angle Detection in Vision-Based Scanning of Nutrition Labels
 
Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...
Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...
Vision-Based Localization and Scanning of 1D UPC and EAN Barcodes with Relaxe...
 
Effective Nutrition Label Use on Smartphones
Effective Nutrition Label Use on SmartphonesEffective Nutrition Label Use on Smartphones
Effective Nutrition Label Use on Smartphones
 
An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...
An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...
An Algorithm for Mobile Vision-Based Localization of Skewed Nutrition Labels ...
 
An Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the Cloud
An Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the CloudAn Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the Cloud
An Algorithm for In-Place Vision-Based Skewed 1D Barcode Scanning in the Cloud
 
Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...
Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...
Skip Trie Matching: A Greedy Algorithm for Real-Time OCR Error Correction on ...
 
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
 
Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...
Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...
Skip Trie Matching for Real Time OCR Output Error Correction on Android Smart...
 
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
Vision-Based Localization & Text Chunking of Nutrition Fact Tables on Android...
 
Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...
Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...
Eye-Free Barcode Detection on Smartphones with Niblack's Binarization and Sup...
 
Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...
Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...
Eyesight Sharing in Blind Grocery Shopping: Remote P2P Caregiving through Clo...
 
Wireless Indoor Localization with Dempster-Shafer Simple Support Functions
Wireless Indoor Localization with Dempster-Shafer Simple Support FunctionsWireless Indoor Localization with Dempster-Shafer Simple Support Functions
Wireless Indoor Localization with Dempster-Shafer Simple Support Functions
 
RFID in Robot-Assisted Indoor Navigation for the Visually Impaired
RFID in Robot-Assisted Indoor Navigation for the Visually ImpairedRFID in Robot-Assisted Indoor Navigation for the Visually Impaired
RFID in Robot-Assisted Indoor Navigation for the Visually Impaired
 
RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...
RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...
RoboCart: Toward Robot-Assisted Navigation of Grocery Stores by the Visually ...
 

Recently uploaded

Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Ana Luísa Pinho
 
Toxic effects of heavy metals : Lead and Arsenic
Toxic effects of heavy metals : Lead and ArsenicToxic effects of heavy metals : Lead and Arsenic
Toxic effects of heavy metals : Lead and Arsenic
sanjana502982
 
S.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary levelS.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary level
ronaldlakony0
 
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
yqqaatn0
 
Mudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdf
Mudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdfMudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdf
Mudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdf
frank0071
 
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
David Osipyan
 
GBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture MediaGBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture Media
Areesha Ahmad
 
DMARDs Pharmacolgy Pharm D 5th Semester.pdf
DMARDs Pharmacolgy Pharm D 5th Semester.pdfDMARDs Pharmacolgy Pharm D 5th Semester.pdf
DMARDs Pharmacolgy Pharm D 5th Semester.pdf
fafyfskhan251kmf
 
Lateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensiveLateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensive
silvermistyshot
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Sérgio Sacani
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
Richard Gill
 
GBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram StainingGBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram Staining
Areesha Ahmad
 
Chapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisisChapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisis
tonzsalvador2222
 
Phenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvementPhenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvement
IshaGoswami9
 
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
University of Maribor
 
Deep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless ReproducibilityDeep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless Reproducibility
University of Rennes, INSA Rennes, Inria/IRISA, CNRS
 
Seminar of U.V. Spectroscopy by SAMIR PANDA
 Seminar of U.V. Spectroscopy by SAMIR PANDA Seminar of U.V. Spectroscopy by SAMIR PANDA
Seminar of U.V. Spectroscopy by SAMIR PANDA
SAMIR PANDA
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
Columbia Weather Systems
 
bordetella pertussis.................................ppt
bordetella pertussis.................................pptbordetella pertussis.................................ppt
bordetella pertussis.................................ppt
kejapriya1
 
Nutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technologyNutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technology
Lokesh Patil
 

Recently uploaded (20)

Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
 
Toxic effects of heavy metals : Lead and Arsenic
Toxic effects of heavy metals : Lead and ArsenicToxic effects of heavy metals : Lead and Arsenic
Toxic effects of heavy metals : Lead and Arsenic
 
S.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary levelS.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary level
 
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
 
Mudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdf
Mudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdfMudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdf
Mudde & Rovira Kaltwasser. - Populism - a very short introduction [2017].pdf
 
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
 
GBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture MediaGBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture Media
 
DMARDs Pharmacolgy Pharm D 5th Semester.pdf
DMARDs Pharmacolgy Pharm D 5th Semester.pdfDMARDs Pharmacolgy Pharm D 5th Semester.pdf
DMARDs Pharmacolgy Pharm D 5th Semester.pdf
 
Lateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensiveLateral Ventricles.pdf very easy good diagrams comprehensive
Lateral Ventricles.pdf very easy good diagrams comprehensive
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
 
GBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram StainingGBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram Staining
 
Chapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisisChapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisis
 
Phenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvementPhenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvement
 
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
Remote Sensing and Computational, Evolutionary, Supercomputing, and Intellige...
 
Deep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless ReproducibilityDeep Software Variability and Frictionless Reproducibility
Deep Software Variability and Frictionless Reproducibility
 
Seminar of U.V. Spectroscopy by SAMIR PANDA
 Seminar of U.V. Spectroscopy by SAMIR PANDA Seminar of U.V. Spectroscopy by SAMIR PANDA
Seminar of U.V. Spectroscopy by SAMIR PANDA
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
 
bordetella pertussis.................................ppt
bordetella pertussis.................................pptbordetella pertussis.................................ppt
bordetella pertussis.................................ppt
 
Nutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technologyNutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technology
 

On Self-Sufficiency of Verbal Route Directions for Blind Navigation with Prior Exposure

  • 1. On Self-Sufficiency of Verbal Route Directions for Blind Navigation with Prior Exposure Aliasgar Kutiyanawala Computer Science Assistive Technology Laboratory Department of Computer Science Utah State University Logan, UT 84322-4205 aliasgar.k@aggiemail.usu.edu Vladimir Kulyukin Computer Science Assistive Technology Laboratory Department of Computer Science Utah State University Logan, UT 84322-4205 vladimir.kulyukin@usu.edu Daniel Bryce Artificial Intelligence Laboratory Department of Computer Science Utah State University Logan, UT 84322-4205 daniel.bryce@usu.edu Abstract: This paper presents a qualitative analysis of self-sufficiency of verbal route directions for blind navigation in outdoor environments with limited prior exposure. Introduction: We define verbal route directions to be self-sufficient if they can be used by independent visually impaired (VI) travelers to successfully navigate a route from A to B in a given environment without any electronic aid capable of receiving external signals or any human assistance [1]. We distinguish self-sufficient route directions from self-sufficient routes. A self-sufficient route anticipates potential route execution failures and provides either extra localization actions or contingencies for route repair. Self-sufficient verbal route directions are complete or partial verbal realizations of self-sufficient routes. We conducted a preliminary investigation of the self-sufficiency of verbal route directions for outdoor environments with three completely blind students of Utah State University (USU). In this study, the generation of routes and route directions was done manually. We selected two routes on the Utah State University (USU) campus and manually wrote a set of route directions which we believed to be self-sufficient and then encoded our route directions in a computer program than ran on a Nokia E70 cellular phone. Furthermore, our investigation was confined to the case when VI individuals receive prior exposure to the route they will have to navigate independently. This study models the situation when a visually impaired student navigates the route once with an O&M instructor or a friend and then has to navigate the route independently. Experiment: Participants: Three participants were recruited from the local community for the experiment through phone interviews. Henceforth, they will be referred by fictitious names Alice, Bob and Carl.
  • 2. All three individuals are completely blind USU students. All self report themselves as independent travelers with good O&M skills. Alice and Carl are cane users where as Bob is a dog user. Alice is in her mid thirties and Bob and Carl are in their twenties. All participants had some familiarity with the Utah State University campus but were not familiar with the routes that they had to navigate. Method: We partially followed the methods of Gaunet and Briffault [2]. Each of the two routes shown in Figure 1 was manually broken into logical segments and route instructions for each segment were written by the investigators and then machine-converted into audio files using a text to speech software. The generated files were loaded on to a Nokia E70 cell phone equipped with a TALKS screen reader. Additional software was written that allowed participants to browse the instructions. The purpose of the experiment was explained to the participant and he/she was trained on using the cell phone. The participant was then taken to the start of a route and walked the entire route once. This was the training run where the experimenter read the route instructions for each segment of the route and pointed out the various landmarks to the participant. The participant was encouraged to ask questions and browse the instructions on the cell phone. After completion of the test run the training run (prior exposure), the participant was asked to walk the route independently using only the instructions provided in the cell phone. The experimenter followed the participant closely to ensure the participant’s safety and to take observational notes. If the participant made a mistake (took a wrong turn, did not turn, etc), the experimenter did not interrupt the participant but allowed him/her to realize his/her mistake and, whenever possible, correct it. However, if the participant made a serious deviation (a deviation that, in the experimenter's opinion, could have resulted in an accident or caused the navigator to become lost) from the route, the experimenter stopped the participant, explained the error to the participant and brought him/her back onto the route. The time taken to complete the run was recorded along with the number and type of mistakes made by the participant and the number of times the participant browsed instructions for each segment. This procedure was repeated four times per participant per route. For each participant, the test runs were spread over multiple days with no more than two test runs per day. Observations and Results: Figure 2 shows graphs of the time taken by each participant to complete each test run of routes A and B respectively. As expected, the completion time decreases with the number of runs, which could be attributed to the increase in the participant's familiarity with the route. The one exception to this trend was Bob's third run for route A. Bob relied heavily on his dog and since there was a gap of a few days between Bob's second and third run, his dog had forgotten the route. It was also observed that participant's frequency of accessing route information decreased with the number of runs. All three participants almost never accessed the route directions on the cell phone during the final run. Figure 3 shows the graphs of the number of errors performed by each participant during the test runs of route A and route B respectively. The number of errors performed while navigating the route also decreases with the runs. Most of the errors made by the participants were undershoot/overshoot errors where the participant either took the turn too early or too late. A likely explanation for this behavior is that there were a lot of small pathways breaking off from the main route and it was easy to get confused and take a wrong path. There was also a location near the library where a sidewalk progressed to a small open area which the participants had to cross to pick up the sidewalk on the other
  • 3. side. Most errors were made at this location in the first and second runs. At the third and fourth runs, the participants learned to cross the area. Our observations and subsequent interviews with the participants made us conclude that the problem was with our route directions. Thus, the errors could have been prevented by issuing better route instructions that warned the participants about the possibility of making those errors. It would have been beneficial to issue more specific localization and repair route instructions for the participants to avoid making the errors or to detect mistakes and then take appropriate corrective measures to get back on the route. If a route segment has multiple pathways breaking off from one side, it may be better to have instructions that ask the traveler to walk on the other side. Although our instructions provided distance information for each route segment, Alice said that she could not keep track of how far she had moved and so this information was of no use to her. On the other hand, Carl was able to use the distance information very well. He would walk the majority of the segment really quickly and start to look for the turns only near the end of the path segment. This observation leads us to conclude that some amount of cognitive modeling would be helpful for we want to automate the generation of self- sufficient routes [3]. At the very least, the cognitive model should contain information on the utility of distance information for the traveler. Conclusion: Visually impaired navigators can navigate a route successfully if they are provided with route instructions for each segment of the route. The amount of time required for navigating a route and the number of errors made in navigation decreases with the familiarity with that route. It was also observed that some potential error situations could be avoided by issuing warnings and error detection and correction mechanisms to the user. References: [1] Nicholson, J., Kulyukin, V., and Marston, J. (2009). Building Route-Based Maps for the Visually Impaired from Natural Language Route Descriptions. To appear in Proceedings of the 24-th International Cartographic Conference (ICC 2009), Santiago, Chile, November 2009. [2] Gaunet, F., and Briffault, X. Exploring the functional specifications of a localized wayfinding verbal aid for blind pedestrians: Simple and structured urban areas. Human- Computer Interaction 20, 3 (2005), 267–314. [3] Crandall, B., Klein, G., Hoffman, R. (2006). Working Minds: A Practioner’s Guide to Cognitive Task Analysis. The MIT Press, Cambridge, MA.
  • 4. Figure 1: Route A (in blue) and Route B (in red) Image Description: This figure shows route A and route B on the Utah State University campus. Figure 2: Time Taken to Complete Each Run of Route A and Route B Image Description: This figure shows the time taken by each participant to complete each run of Route A and Route B. It can be observed that the time taken to complete each run decreases with the number of runs.
  • 5. Figure 3: Number of Errors for Each Run of Route A and Route B Image Description: This figure shows the number of errors made by each participant in each run of Route A and Route B. It can be observed that the number of errors decreases with the number of runs.