Learning Implicit Priors for Motion Optimization
Preprint
Abstract
In this paper, we focus on the problem of integrating Energy-based Models (EBM) as guiding priors for motion optimization. EBMs are a set of neural networks that can represent expressive probability density distributions in terms of a Gibbs distribution parameterized by a suitable energy function. Due to their implicit nature, they can easily be integrated as optimization factors or as initial sampling distributions in the motion optimization problem, making them good candidates to integrate data-driven priors in the motion optimization problem. In this work, we present a set of required modeling and algorithmic choices to adapt EBMs into motion optimization. We investigate the benefit of including additional regularizers in the learning of the EBMs to use them with gradient-based optimizers and we present a set of EBM architectures to learn generalizable distributions for manipulation tasks. We present multiple cases in which the EBM could be integrated for motion optimization and evaluate the performance of learned EBMs as guiding priors for both simulated and real robot experiments.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions2021
- Cross-entropy based stochastic optimization of robot trajectories using heteroscedastic continuous-time Gaussian processesRobotics and Autonomous Systems, 2020
- Learning Sampling Distributions for Robot Motion Planning2018
- Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation2018
- Space-time functional gradient optimization for motion planning2014
- Spatiotemporal Learning via Infinite-Dimensional Bayesian Filtering and Smoothing: A Look at Gaussian Process Regression Through Kalman FilteringIEEE Signal Processing Magazine, 2013
- STOMP: Stochastic trajectory optimization for motion planning2011
- An Introduction to MCMC for Machine LearningMachine Learning, 2003
- Probabilistic roadmaps for path planning in high-dimensional configuration spacesIEEE Transactions on Robotics and Automation, 1996
- Correlation functions and computer simulationsNuclear Physics B, 1981