.png){kind=icon}
返回
Ergodic Exploration Using Tensor Train: Applications in Insertion Tasks
.png){kind=icon}
OA
AI
DOI：10.1109/TRO.2021.3087317.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 two 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 storagewise, hence making it suitable for its online implementation in robotic systems. The approach is applied to a peg-in-hole insertion task requiring full 6-D end-effector poses, implemented with a seven-axis Franka Emika Panda robot. In this experiment, ergodic exploration allows the task to be achieved without requiring the use of force/torque sensors.
Keyword:
Tensors
Task analysis
Trajectory
Measurement
End effectors
Dynamical systems
Robot sensing systems
Ergodic control
learning from demonstration
low-rank approximation
peg-in-hole insertion task
tensor factorization
tensor methods
tensor train (TT)
期刊
IF:
10.5
论文数:
3.3K
被引数:
2.8W
机构
引用论文
An ESR study of co-ordination modes in copper(II) complexes of l-serine in aqueous solution at ligand excess above pH 7.png)
Polyhedron
PolyhedronIF0
PREAI
分享收藏Parallel cross interpolation for high-precision calculation of high-dimensional integrals用于高精度计算高维积分的并行交叉插值
OAAI
OAAI分享收藏
查看更多内容