AdaptiveCollisionHand

AdaptiveCollisionHand

Download (72.7 MB)

---

Description

Abstract

Assistive robots are increasingly being envisioned as an aid to the elderly and disabled. However controlling a robotic system with a potentially large amount of Degrees of Freedom (DOF) in a safe and reliable way is not an easy task, even without limitations in the mobility of the upper extremities. Shared control has been proposed as a way of aiding disabled users in controlling mobility aids such as assistive wheelchairs, by using the sensors of the robotic platform to predict the user’s intent and assist in navigation. Assistive manipulators, that aim to perform physical Daily Life Activities (DLA), is a more complex problem however. The problem arise from the exponential increase in the size of the state-space with DOF and the increased level of accuracy required for manipulation. Another complication is the potential need for adapting the system to each user’s abilities and disabilities. This calls for good experimental practices to ensure repeatability, reproducibility, and steady progress. The work presented here attempts to model the complete system for assistive manipulators, and in the context of this model define metrics and good practices for benchmarking shared control for such robots. An adaptive shared control approach for limiting collisions during teleoperation is used as a case study.

Links

• Article link
• Multimedia extensions

Citation

@Inproceedings{Stoelen2012,
author={Stoelen, M.F. and Tejada, V.F. and Huete, A.J. and Bonsignorio, F. and Balaguer, C.},
booktitle={Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on},
title={Benchmarking shared control for assistive manipulators: From controllability to the speed-accuracy trade-off},
year={2012},
pages={4386-4391},
doi={10.1109/IROS.2012.6385847},
ISSN={2153-0858}}

---

Data sets

All Cartesian trajectories. All trial-level results. Development of neural network weight matrices over time. Matlab examples for loading trajectories, plotting the trial-level results and visualizing the development of the neural network weights. See [AdaptiveCollisionHand-DataSets].

---

Code

Complete set of executables, Linux 32 and 64 bit. Tested on Ubuntu 10.04 for 32 bit and 11.04 for 64 bit. See [AdaptiveCollisionHand-Code].

---

Hardware

Simulated robot only. Multi-core desktop computer, Intel Core 2 Duo @ 3.0 GHz used here. 3DConnexion SpaceNavigator 6 DOF input device.

---

Method

Example video, pre and post experiment questionnaires, consent form with participant instructions. See [AdaptiveCollisionHand-Method].

---

About the maintainer

• Name: Martin F. Stoelen
• Institution: RoboticsLab, Universidad Carlos III de Madrid (UC3M), Spain
• Contact: mstoelen at ing.uc3m.es
• Website: http://roboticslab.uc3m.es

---

[Home] [ExperimentalPapers]