The objective of this work is to develop a negative obstacle detection algorithm for a robotic wheelchair. Negative obstacles — depressions in the surrounding terrain including descending stairwells, and curb drop-offs — present highly dangerous navigation scenarios because they exhibit wide characteristic variability, are perceptible only at close distances, and are difficult to detect at normal operating speeds. Negative obstacle detection on robotic wheelchairs could greatly increase the safety of the devices.
The approach presented in this paper uses measurements from a single-scan laser range-finder and a microprocessor to detect negative obstacles. A real-time algorithm was developed that monitors time-varying changes in the measured distances and functions through the assumption that sharp increases in this monitored value represented a detected negative obstacle.
It was found that LiDAR sensors with slight beam divergence and significant error produced impressive obstacle detection accuracy, detecting controlled examples of negative obstacles with 88% accuracy for 6 cm obstacles and above on a robotic development platform and 90% accuracy for 7.5 cm obstacles and above on a robotic wheelchair. The implementation of this algorithm could prevent life-changing injuries to robotic wheelchair users caused by negative obstacles.
Electroencephalogram-based Brain Controlled Robotic Wheelchair
