We introduce GEOTACT, a robotic manipulation method capable of retrieving
objects buried in granular media. This is a challenging task due to the need to
interact with granular media, and doing so based exclusively on tactile
feedback, since a buried object can be completely hidden from vision. Tactile
feedback is in itself challenging in this context, due to ubiquitous contact
with the surrounding media, and the inherent noise level induced by the tactile
readings. To address these challenges, we use a learning method trained
end-to-end with simulated sensor noise. We show that our problem formulation
leads to the natural emergence of learned pushing behaviors that the
manipulator uses to reduce uncertainty and funnel the object to a stable grasp
despite spurious and noisy tactile readings. We also introduce a training
curriculum that enables learning these behaviors in simulation, followed by
zero-shot transfer to real hardware. To the best of our knowledge, GEOTACT is
the first method to reliably retrieve a number of different objects from a
granular environment, doing so on real hardware and with integrated tactile
sensing. Videos and additional information can be found at
this https URL

GEOTACT 是一种能够从颗粒介质中挖掘出埋藏物体的机器人操控方法，通过纯粹依靠触觉反馈与颗粒介质交互，以及通过学习方法训练来降低噪音干扰，并成功在真实硬件上实现了从颗粒环境中可靠地获取不同物体的目标。

基于触觉的颗粒介质中物体检索

Tactile-based Object Retrieval From Granular Media

The jamming scenario of disordered media, formulated about 10 years ago, has
in recent years been advanced by analyzing model systems of granular media.
This has led to various new concepts that are increasingly being explored in in
a variety of systems. This chapter contains an introductory review of these
recent developments and provides an outlook on their applicability to different
physical systems and on future directions. The first part of the paper is
devoted to an overview of the findings for model systems of frictionless
spheres, focussing on the excess of low-frequency modes as the jamming point is
approached. Particular attention is paid to a discussion of the cross-over
frequency and length scales that govern this approach. We then discuss the
effects of particle asphericity and static friction, the applicability to
bubble models for wet foams in which the friction is dynamic, the dynamical
arrest in colloids, and the implications for molecular glasses.

对颗粒材料模型进行研究所发现的新概念，包括粒子形状等对其物理特性的影响及其在不同物理系统中的适用性和未来研究方向的初步综述。