Abstract | ||
---|---|---|
An accurate motion model is an important component in modern-day robotic systems, but building such a model for a complex system often requires an appreciable amount of manual effort. In this paper we present a motion model representation, the Dynamic Gaussian Mixture Model (DGMM), that alleviates the need to manually design the form of a motion model, and provides a direct means of incorporating auxiliary sensory data into the model. This representation and its accompanying algorithms are validated experimentally using an 8-legged kinematically complex robot, as well as a standard benchmark dataset. The presented method not only learns the robot's motion model, but also improves the model's accuracy by incorporating information about the terrain surrounding the robot. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/IROS.2009.5354026 | IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems |
Keywords | DocType | Volume |
accurate motion model,direct mean,motion model,complex system,motion model representation,appreciable amount,dynamic motion,accompanying algorithm,legged robot,auxiliary sensory data,dynamic gaussian mixture model,8-legged kinematically complex robot,robot kinematics,gaussian mixture model,gaussian processes,probability density function,mobile robots,simultaneous localization and mapping,data models,mathematical model,motion control | Conference | abs/1005.5035 |
ISBN | Citations | PageRank |
978-1-4244-3804-4 | 2 | 0.43 |
References | Authors | |
12 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mark Edgington | 1 | 49 | 5.93 |
Yohannes Kassahun | 2 | 109 | 11.23 |
Frank Kirchner | 3 | 143 | 24.53 |