Learning Implicit Priors for Motion Optimization

04/11/2022
by   Alexander Lambert, et al.
4

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.

READ FULL TEXT

page 1

page 6

page 7

page 15

research
09/08/2022

SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion

Multi-objective optimization problems are ubiquitous in robotics, e.g., ...
research
08/03/2023

Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models

Learning priors on trajectory distributions can help accelerate robot mo...
research
03/23/2022

Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning

In recent years, reinforcement learning (RL) has shown outstanding perfo...
research
02/10/2023

Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding

This paper proposes a probabilistic motion prediction method for long mo...
research
06/09/2023

Motion-DVAE: Unsupervised learning for fast human motion denoising

Pose and motion priors are crucial for recovering realistic and accurate...
research
11/14/2019

Generalized Flexible Hybrid Cable-Driven Robot (HCDR): Modeling, Control, and Analysis

This paper presents a generalized flexible Hybrid Cable-Driven Robot (HC...

Please sign up or login with your details

Forgot password? Click here to reset