TY - GEN
T1 - Automated incline detection for assistive powered wheelchairs
AU - Nejati, Mahdieh
AU - Argall, Brenna Dee
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/11/15
Y1 - 2016/11/15
N2 - This work presents an algorithm for automated real-time ramp detection using 3D point cloud data in the context of shared-control powered wheelchairs. Limitations in the interfaces available to those with severe motor impairments can make basic maneuvering tasks with powered wheelchairs difficult. Although a significant amount of work has been done on obstacle detection and avoidance, much less attention has been given to algorithms for the safe and reliable detection of ramps and inclines; even though navigating these structures is an important part of urban life. We provide an algorithmic solution for accurately detecting traversable inclines for applications with powered wheelchairs using the Point Cloud Library (PCL) within the Robotics Operating System (ROS) framework. All algorithms are implemented first in simulation and later evaluated on data obtained from indoor and outdoor urban environments. We measure the performance of our algorithm with systematic testing on several different ramp structures, observed from varied viewpoints. Results show that our algorithm is successful in detecting the orientation, slope, and width of traversable ramps with up to 100% accuracy and an average detection accuracy of 88%.
AB - This work presents an algorithm for automated real-time ramp detection using 3D point cloud data in the context of shared-control powered wheelchairs. Limitations in the interfaces available to those with severe motor impairments can make basic maneuvering tasks with powered wheelchairs difficult. Although a significant amount of work has been done on obstacle detection and avoidance, much less attention has been given to algorithms for the safe and reliable detection of ramps and inclines; even though navigating these structures is an important part of urban life. We provide an algorithmic solution for accurately detecting traversable inclines for applications with powered wheelchairs using the Point Cloud Library (PCL) within the Robotics Operating System (ROS) framework. All algorithms are implemented first in simulation and later evaluated on data obtained from indoor and outdoor urban environments. We measure the performance of our algorithm with systematic testing on several different ramp structures, observed from varied viewpoints. Results show that our algorithm is successful in detecting the orientation, slope, and width of traversable ramps with up to 100% accuracy and an average detection accuracy of 88%.
UR - http://www.scopus.com/inward/record.url?scp=85002512069&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85002512069&partnerID=8YFLogxK
U2 - 10.1109/ROMAN.2016.7745232
DO - 10.1109/ROMAN.2016.7745232
M3 - Conference contribution
AN - SCOPUS:85002512069
T3 - 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016
SP - 1007
EP - 1012
BT - 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016
Y2 - 26 August 2016 through 31 August 2016
ER -