DeepAI AI Chat
Log In Sign Up

Feature Disentanglement of Robot Trajectories

by   Matias Valdenegro-Toro, et al.

Modeling trajectories generated by robot joints is complex and required for high level activities like trajectory generation, clustering, and classification. Disentagled representation learning promises advances in unsupervised learning, but they have not been evaluated in robot-generated trajectories. In this paper we evaluate three disentangling VAEs (β-VAE, Decorr VAE, and a new β-Decorr VAE) on a dataset of 1M robot trajectories generated from a 3 DoF robot arm. We find that the decorrelation-based formulations perform the best in terms of disentangling metrics, trajectory quality, and correlation with ground truth latent features. We expect that these results increase the use of unsupervised learning in robot control.


page 4

page 9

page 10

page 11

page 12


Unsupervised Learning of slow features for Data Efficient Regression

Research in computational neuroscience suggests that the human brain's u...

Adversarial Generation of Informative Trajectories for Dynamics System Identification

Dynamic System Identification approaches usually heavily rely on the evo...

Using In-Game Shot Trajectories to Better Understand Defensive Impact in the NBA

As 3-point shooting in the NBA continues to increase, the importance of ...

Foothold Evaluation Criterion for Dynamic Transition Feasibility for Quadruped Robots

To traverse complex scenarios reliably a legged robot needs to move its ...

Generation Drawing/Grinding Trajectoy Based on Hierarchical CVAE

In this study, we propose a method to model the local and global feature...

A Preliminary Study of Disentanglement With Insights on the Inadequacy of Metrics

Disentangled encoding is an important step towards a better representati...

Multi-Vehicle Trajectories Generation for Vehicle-to-Vehicle Encounters

Generating multi-vehicle trajectories analogous to these in real world c...