A probabilistic data-driven model for planar pushing
This work addresses the challenge of predicting stochastic outcomes in robotic pushing tasks, which is incremental as it applies a novel method to a known bottleneck in robotics.
The paper tackles the problem of modeling planar pushing interactions by predicting both the most likely outcome and its variability, achieving accurate models that outperform analytical ones with less than 100 samples and saturate performance with under 1000 samples.
This paper presents a data-driven approach to model planar pushing interaction to predict both the most likely outcome of a push and its expected variability. The learned models rely on a variation of Gaussian processes with input-dependent noise called Variational Heteroscedastic Gaussian processes (VHGP) that capture the mean and variance of a stochastic function. We show that we can learn accurate models that outperform analytical models after less than 100 samples and saturate in performance with less than 1000 samples. We validate the results against a collected dataset of repeated trajectories, and use the learned models to study questions such as the nature of the variability in pushing, and the validity of the quasi-static assumption.