Uncertainty Averse Pushing with Model Predictive Path Integral Control
arXiv:1710.04005 · doi:10.1109/HUMANOIDS.2017.8246918
Abstract
Planning robust robot manipulation requires good forward models that enable robust plans to be found. This work shows how to achieve this using a forward model learned from robot data to plan push manipulations. We explore learning methods (Gaussian Process Regression, and an Ensemble of Mixture Density Networks) that give estimates of the uncertainty in their predictions. These learned models are utilised by a model predictive path integral (MPPI) controller to plan how to push the box to a goal location. The planner avoids regions of high predictive uncertainty in the forward model. This includes both inherent uncertainty in dynamics, and meta uncertainty due to limited data. Thus, pushing tasks are completed in a robust fashion with respect to estimated uncertainty in the forward model and without the need of differentiable cost functions. We demonstrate the method on a real robot, and show that learning can outperform physics simulation. Using simulation, we also show the ability to plan uncertainty averse paths.
Humanoids 2017. Supplementary video: https://youtu.be/LjYruxwxkPM
References in corpus (2)
Cited by in corpus (8)
- Robust Model Predictive Path Integral Control: Analysis and Performance Guarantees
- Learning to Guide: Guidance Law Based on Deep Meta-learning and Model Predictive Path Integral Control
- Biased-MPPI: Informing Sampling-Based Model Predictive Control by Fusing Ancillary Controllers
- Combining Coarse and Fine Physics for Manipulation using Parallel-in-Time Integration
- Synthesize Dexterous Nonprehensile Pregrasp for Ungraspable Objects
- Parareal with a Learned Coarse Model for Robotic Manipulation
- Robust Physics-Based Manipulation by Interleaving Open and Closed-Loop Execution
- Self-Adapting Recurrent Models for Object Pushing from Learning in Simulation