Learning Implicit Priors for Motion Optimization

Motion optimization is an effective framework for generating smooth and safe trajectories for robotic manipulation tasks. However, it suffers from local optima that hinder its applicability, especially for multi-objective tasks. In this paper, we study this problem in light of the integration of Energy-Based Models (EBM) as guiding priors in motion optimization. EBMs are probabilistic models with unnormalized energy functions that represent expressive multimodal distributions. Due to their implicit nature, EBMs can easily be integrated as data-driven factors or initial sampling distributions in the motion optimization problem. This work presents a set of necessary modeling and algorithmic choices to effectively learn and integrate EBMs into motion optimization. We present a set of EBM architectures for learning generalizable distributions over trajectories that are important for the subsequent deployment of EBMs. Moreover, we investigate the benefit of including smoothness regularization in the learning process to improve motion optimization. In addition to gradient-based solvers, we also propose a stochastic method for trajectory optimization with learned EBMs. We provide extensive empirical results in a set of representative tasks against competitive baselines that demonstrate the superiority of EBMs as priors in motion optimization scaling up to 7 -dof robot pouring that can be easily transferred to the real robotic system. Videos and additional details are available at https://sites.google.com/view/implicit-priors.

Authors

• Julen Urain
• An T. Le 0001
• Alexander Lambert
• Georgia Chalvatzaki
• Byron Boots
• Jan Peters 0001

Keywords

• Stochastic processes
• Probabilistic logic
• Task analysis
• Optimization
• Trajectory optimization
• Intelligent robots
• Videos
• Implicit Priors
• Optimization Problem
• Optimization Method
• Bimodal
• Probabilistic Model
• Choice Of Model
• Energy Function
• Manipulation Tasks
• Stochastic Method
• Robot Manipulator
• Choice Of Algorithm
• Robotic Tasks
• Smooth Trajectory
• Implicit Nature
• Energy-based Model
• Smoothness Regularization
• Objective Function
• Cost Function
• Markov Chain Monte Carlo
• Stochastic Optimization
• Path Planning
• Distribution Of Trajectories
• Inverse Reinforcement Learning
• Obstacle Avoidance
• Trajectory Optimization Problem
• Gradient-based Optimization
• Configuration Space
• Robot Motion
• Gaussian Process