usc-bbdl / usc-bbdl.github.io

Website for the Brain Body Dynamics Lab
http://valerolab.org
1 stars 4 forks source link

Publication info - Ali 3 #86

Open marjanin opened 4 years ago

marjanin commented 4 years ago

Delete all nonrelevant information from this template when submitting your issue request:

Publication


Title: The utility of tactile force to autonomous learning of in-hand manipulation is task-dependent
Link: https://arxiv.org/pdf/2002.02418
Abstract: Tactile sensors provide information that can be used to learn and execute manipulation tasks. Different tasks, however, might require different levels of sensory information; which in turn likely affect learning rates and performance. This paper evaluates the role of tactile information on autonomous learning of manipulation with a simulated 3-finger tendon-driven hand. We compare the ability of the same learning algorithm (Proximal Policy Optimization, PPO) to learn two manipulation tasks (rolling a ball about the horizontal axis with and without rotational stiffness) with three levels of tactile sensing: no sensing, 1D normal force, and 3D force vector. Surprisingly, and contrary to recent work on manipulation, adding 1D force-sensing did not always improve learning rates compared to no sensing---likely due to whether or not normal force is relevant to the task. Nonetheless, even though 3D force-sensing increases the dimensionality of the sensory input---which would in general hamper algorithm convergence---it resulted in faster learning rates and better performance. We conclude that, in general, sensory input is useful to learning only when it is relevant to the task---as is the case of 3D force-sensing for in-hand manipulation against gravity. Moreover, the utility of 3D force-sensing can even offset the added computational cost of learning with higher-dimensional sensory input.
Authors: R Mir, A Marjaninejad, FJ Valero-Cuevas
BibTex: @article{mir2020utility,
  title={The utility of tactile force to autonomous learning of in-hand manipulation is task-dependent},
  author={Mir, Romina and Marjaninejad, Ali and Valero-Cuevas, Francisco J},
  journal={arXiv preprint arXiv:2002.02418},
  year={2020}
}
Year: 2020
Journal: ArXiv              

``
 ## NOTE:
The format of the Author section is very important to the design of the site. If there’s no supplemental material, just leave it blank.
bc commented 4 years ago

pdf

bc commented 4 years ago

2002.02418.pdf is this one ok?