Learning of skid-steered kinematic and dynamic models for motion planning
| Autor: | Brandon M. Reese, Alonzo Kelly, Neal Seegmiller, Nikhil Gupta, Camilo Ordonez, Emmanuel G. Collins |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Artificial neural network Computer science General Mathematics Control engineering 02 engineering and technology Slip (materials science) Kalman filter Kinematics 021001 nanoscience & nanotechnology Computer Science Applications Computer Science::Robotics 020901 industrial engineering & automation Control and Systems Engineering Robot Turning radius Motion planning Curvilinear motion 0210 nano-technology Software Simulation ComputingMethodologies_COMPUTERGRAPHICS Slip (vehicle dynamics) |
| Zdroj: | Robotics and Autonomous Systems. 95:207-221 |
| ISSN: | 0921-8890 |
| DOI: | 10.1016/j.robot.2017.05.014 |
| Popis: | Modeling of the motion of a skid-steered robot is challenging since slippage and skidding is inherent to this type of platform and it requires high torques to perform curvilinear motion. If the ground–robot interaction and torque requirements are not captured properly, motion planners will sometimes generate trajectories that are not achievable by the robot. Important motion planning applications that rely heavily in these models, include energy efficient and momentum based planning. However, these models change as the terrain surface varies. To cope with this issue, this paper presents a methodology to perform online learning of such models. It combines detailed slip and terramechanic-based dynamic models of wheel–terrain interaction with online learning via Extended Kalman filtering (to update the kinematic model) and an efficient neural network formulation (to update the dynamic model). The proposed approach experimentally demonstrates the importance of the joint utilization of the learned vehicle models in the context of energy efficient motion planning. In particular, the slip-enhanced kinematic models are used to efficiently provide estimates of robot pose and the dynamic models are employed to generate energy estimates and minimum turn radius constraints. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect