Learning to Navigate Robotic Wheelchairs from Demonstration: Is Training in Simulation Viable?

2019 ◽  
Author(s):  
Mohammed Kutbi ◽  
Yizhe Chang ◽  
Bo Sun ◽  
Philippos Mordohai
Keyword(s):  
Robotic Wheelchairs

Negative Obstacle Detection Using LiDAR Sensors for a Robotic Wheelchair

2018 ◽  
Author(s):  
Taylor E. Baum ◽  
Kelilah L. Wolkowicz ◽  
Joseph P. Chobot ◽  
Sean N. Brennan
Keyword(s):  
Time Algorithm ◽  
Detection Algorithm ◽  
Obstacle Detection ◽  
Detection Accuracy ◽  
Time Varying ◽  
Wheelchair Users ◽  
Development Platform ◽  
Robotic Wheelchairs ◽  
Robotic Wheelchair ◽  
Negative Obstacle

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.

scholarly journals A Multi-Agent Control Architecture for a Robotic Wheelchair

2006 ◽  
Vol 3 (3) ◽  
pp. 179-189 ◽  
Author(s):  
C. Galindo ◽  
A. Cruz-Martin ◽  
J. L. Blanco ◽  
J. A. Fernńndez-Madrigal ◽  
J. Gonzalez
Keyword(s):  
Reinforcement Learning ◽  
Control Architecture ◽  
Daily Lives ◽  
Multi Agent ◽  
Human Skills ◽  
Overall Performance ◽  
Agent Control ◽  
Robotic Wheelchairs ◽  
Assistant Robots ◽  
Robotic Wheelchair

Assistant robots like robotic wheelchairs can perform an effective and valuable work in our daily lives. However, they eventually may need external help from humans in the robot environment (particularly, the driver in the case of a wheelchair) to accomplish safely and efficiently some tricky tasks for the current technology, i.e. opening a locked door, traversing a crowded area, etc. This article proposes a control architecture for assistant robots designed under a multi-agent perspective that facilitates the participation of humans into the robotic system and improves the overall performance of the robot as well as its dependability. Within our design, agents have their own intentions and beliefs, have different abilities (that include algorithmic behaviours and human skills) and also learn autonomously the most convenient method to carry out their actions through reinforcement learning. The proposed architecture is illustrated with a real assistant robot: a robotic wheelchair that provides mobility to impaired or elderly people.

scholarly journals Exploring Interaction Design Considerations for Trustworthy Language-Capable Robotic Wheelchairs in Virtual Reality

2020 ◽  
Author(s):  
Thomas Williams
Keyword(s):  
Virtual Reality ◽  
Mobile Robots ◽  
Interaction Design ◽  
Human Robot Interaction ◽  
Robot Interaction ◽  
Physical Movement ◽  
Design Considerations ◽  
Robotic Wheelchairs ◽  
Proactive Communication ◽  
User Trust

In previous work, researchers in Human-Robot Interaction (HRI) have demonstrated that user trust in robots depends on effective and transparent communication. This may be particularly true forrobots used for transportation, due to user reliance on such robots for physical movement and safety. In this paper, we present the design of an experiment examining the importance of proactive communication by robotic wheelchairs, as compared to non-vehicular mobile robots, within a Virtual Reality (VR) environment. Furthermore, we describe the specific advantages – and limitations – of conducting this type of HRI experiment in VR.

A Novel Walking-Aid for Paralytic Patients Caused due to Stroke

2015 ◽  
Vol 813-814 ◽  
pp. 938-942
Author(s):  
V. Indra Tej ◽  
G. Sasank ◽  
M. Asish ◽  
M. Nitheesh ◽  
Anjan Kumar Dash
Keyword(s):  
Motor Learning ◽  
Dc Motor ◽  
Active Participation ◽  
The Body ◽  
Paretic Limb ◽  
Wheel Chair ◽  
Robotic Wheelchairs ◽  
Hemiplegic Patient ◽  
Walking Aid

The aim of this project is to fabricate an economical walking aid for Paralytic patients caused due to a stroke. The Paralysis caused due to stroke is referred as Hemiplegia or Hemiparesis. In general these patients walk with the assistance of another person. The patient first moves his unaffected leg as the assistant holds him firmly to give him support. Then the assistant pushes the impaired leg of the patient with his own leg while supporting him with his hands. In this way walking is achieved for the hemiplegic patient. To eliminate human assistance, the patient can also use a wheel chair to move from one place to another, especially the Autonomous Robotic Wheelchairs (ARW) that are being used these days. However, in order to gain back his motor capabilities, he should promote the use of hemi paretic limb during functional tasks. Active participation is critical to the motor learning and recovery. So designing a mechanism which enables movements on paralyzed body is crucial for functioning of other parts of the body as this prevents blood stagnation due to continuous rest given to specific parts. A DC motor along with some pulleys are used for actuating the leg and a telescopic tripod wheeled balancing support is used for providing counter-torque that helps the person from falling down on paralyzed side.

Sign in / Sign up

Export Citation Format

Share Document