Ergodic Exploration using Tensor Train: Applications in Insertion Tasks
Authors:
- Suhan ShettySSSuhan Shetty
- João SilvérioJSJoão Silvério
- Sylvain CalinonSCSylvain Calinon
Preprint
Abstract
In robotics, ergodic control extends the tracking principle by specifying a probability distribution over an area to cover instead of a trajectory to track. The original problem is formulated as a spectral multiscale coverage problem, typically requiring the spatial distribution to be decomposed as Fourier series. This approach does not scale well to control problems requiring exploration in search space of more than 2 dimensions. To address this issue, we propose the use of tensor trains, a recent low-rank tensor decomposition technique from the field of multilinear algebra. The proposed solution is efficient, both computationally and storage-wise, hence making it suitable for its online implementation in robotic systems. The approach is applied to a peg-in-hole insertion task requiring full 6D end-effector poses, implemented with a 7-axis Franka Emika Panda robot. In this experiment, ergodic exploration allows the task to be achieved without requiring the use of force/torque sensors.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Parallel cross interpolation for high-precision calculation of high-dimensional integralsComputer Physics Communications, 2020
- Tutorial on the generation of ergodic trajectories with projection‐based gradient descentIET Cyber-Physical Systems: Theory & Applications, 2019
- A chaotic dynamical system that paints and samplesIFAC-PapersOnLine, 2017
- An Approach for Imitation Learning on Riemannian ManifoldsIEEE Robotics and Automation Letters, 2017
- Literature survey on low rank approximation of matricesLinear and Multilinear Algebra, 2016
- Intuitive peg-in-hole assembly strategy with a compliant manipulator2013
- A literature survey of low‐rank tensor approximation techniquesGAMM-Mitteilungen, 2013
- Metrics for ergodicity and design of ergodic dynamics for multi-agent systemsPhysica D: Nonlinear Phenomena, 2011
- TT-cross approximation for multidimensional arraysLinear Algebra and its Applications, 2010
- Applied Multiway Data Analysis2007