Name
Abstract | ||
|---|---|---|
We present a system which can automatically home an upper torso humanoid robot so that its true joint angles are known using only information from a depth camera, coupled with incremental encoders. This means that extra components, such as absolute encoders, resolvers, homing switches etc., are not needed. This in turn means that the cost of the system may be reduced and reliability improved as potential component failures are eliminated. The system uses exploratory moves to locate the robot's end effector and to measure the pose of the robot's wrist frame in camera space. Multiple measurements of the wrist frame pose are combined together in a kinematic calibration step to obtain the true joint angles and thus home the robot. We conduct experiments to explore the accuracy and reliability of our homing system, both in simulation and on a physical robotic platform. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1007/978-3-662-43645-5_13 | Lecture Notes in Artificial Intelligence |
Field | DocType | Volume |
Resolver,Torso,Computer vision,Robot calibration,Simulation,Computer science,Robot end effector,Encoder,Artificial intelligence,Robot,Optical flow,Humanoid robot | Conference | 8069 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
6 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alan Broun | 1 | 10 | 1.63 |
| Chris Beck | 2 | 3 | 1.10 |
| Tony Pipe | 3 | 171 | 24.02 |
| Majid Mirmehdi | 4 | 955 | 96.94 |
| Chris Melhuish | 5 | 747 | 87.61 |