Active Learning based on Data Uncertainty and Model Sensitivity

by   Nutan Chen, et al.

Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether the robot has the necessary knowledge to perform the task. Failing to detect missing information often leads to abrupt movements or to collisions with the environment. Active learning can quantify the uncertainty of performing the task and, in general, locate regions of missing information. We introduce a novel algorithm for active learning and demonstrate its utility for generating smooth trajectories. Our approach is based on deep generative models and metric learning in latent spaces. It relies on the Jacobian of the likelihood to detect non-smooth transitions in the latent space, i.e., transitions that lead to abrupt changes in the movement of the robot. When non-smooth transitions are detected, our algorithm asks for an additional demonstration from that specific region. The newly acquired knowledge modifies the data manifold and allows for learning a latent representation for generating smooth movements. We demonstrate the efficacy of our approach on generalising elementary skills, transitioning across different skills, and implicitly avoiding collisions with the environment. For our experiments, we use a simulated pendulum where we observe its motion from images and a 7-DoF anthropomorphic arm.


page 1

page 4

page 6

page 7


Active Learning of Probabilistic Movement Primitives

A Probabilistic Movement Primitive (ProMP) defines a distribution over t...

Learning from Demonstration via Probabilistic Diagrammatic Teaching

Learning for Demonstration (LfD) enables robots to acquire new skills by...

Video2Skill: Adapting Events in Demonstration Videos to Skills in an Environment using Cyclic MDP Homomorphisms

Humans excel at learning long-horizon tasks from demonstrations augmente...

Learning Riemannian Manifolds for Geodesic Motion Skills

For robots to work alongside humans and perform in unstructured environm...

Active Improvement of Control Policies with Bayesian Gaussian Mixture Model

Learning from demonstration (LfD) is an intuitive framework allowing non...

A note on active learning for smooth problems

We show that the disagreement coefficient of certain smooth hypothesis c...

Baby Robot: Improving the Motor Skills of Toddlers

This article introduces "Baby Robot", a robot aiming to improve motor sk...

Please sign up or login with your details

Forgot password? Click here to reset