Page 51 |
Save page Remove page | Previous | 51 of 151 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
alternative approach where each drifter uses in situ measurements of ocean currents to make control
decisions.
A control strategy for rendezvous with multiple drifters is presented in [Ouimet and Cort´es,
2014]. Although their targeted application of aggregating multiple drifters is similar, they use a
different approach, where the ocean dynamics is represented by internal wave models with known
parameters. In contrast, we assume no explicit knowledge about the dynamics of the ocean, except
the vertical component of the flow, which we assume to be zero. In Jouffroy et al. [2013b] the
target application is to control the absolute position of a drifter in a coastal scenario, where the
drifter can anchor itself at the sea bottom if necessary. As an extension, the deep ocean scenario
for a single drifter is examined under idealized conditions (the drifter is assumed to have instant
estimates of currents at the present location, the ocean currents are assumed to be stationary
and to span the plane positively). The external forcing by current flow fields and its impact on
the control of underactuated robotic systems is furthermore addressed by Kwok and Mart´ınez
[2010] for a coverage task with self-propelled vehicles of bounded velocity in a river environment
and by Michini et al. [2014] for tasks of tracking coherent structures on flows with autonomous
underwater vehicles in the ocean.
3.2 Single Drifter Control
In this section we aim to provide preliminary investigation of the quality of ROMS model for long
horizon predictions and possible control strategies of a single drifter in idealistic scenarios.
36
Object Description
| Title | Data scarcity in robotics: leveraging structural priors and representation learning |
| Author | Molchanov, Artem |
| Author email | a.molchanov86@gmail.com;molchano@usc.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2020-05-11 |
| Date submitted | 2020-08-11 |
| Date approved | 2020-08-11 |
| Restricted until | 2020-08-11 |
| Date published | 2020-08-11 |
| Advisor (committee chair) | Sukhatme, Gaurav Suhas |
| Advisor (committee member) |
Ayanian, Nora Culbertson, Heather Gupta, Satyandra K. |
| Abstract | Recent advances in Artificial Intelligence have benefited significantly from access to large pools of data accompanied in many cases by labels, ground truth values, or perfect demonstrations. In robotics, however, such data are scarce or absent completely. Overcoming this issue is a major barrier to move robots from structured laboratory settings to the unstructured real world. In this dissertation, by leveraging structural priors and representation learning, we provide several solutions when data required to operate robotics systems is scarce or absent. ❧ In the first part of this dissertation we study sensory feedback scarcity. We show how to use high-dimensional alternative sensory modalities to extract data when primary sensory sources are absent. In a robot grasping setting, we address the problem of contact localization and solve it using multi-modal tactile feedback as the alternative source of information. We leverage multiple tactile modalities provided by electrodes and hydro-acoustic sensors to structure the problem as spatio-temporal inference. We employ the representational power of neural networks to acquire the complex mapping between tactile sensors and the contact locations. We also investigate scarce feedback due to the high cost of measurements. We study this problem in a challenging field robotics setting where multiple severely underactuated aquatic vehicles need to be coordinated. We show how to leverage collaboration among the vehicles and the spatio-temporal smoothness of the ocean currents as a prior to densify feedback about ocean currents in order to acquire better controllability. ❧ In the second part of this dissertation, we investigate scarcity of the data related to the desired task. We develop a method to efficiently leverage simulated dynamics priors to perform sim-to-real transfer of a control policy when no data about the target system is available. We investigate this problem in the scenario of sim-to-real transfer of low-level stabilizing quadrotor control policies. We demonstrate that we can learn robust policies in simulation and transfer them to the real system while acquiring no samples from the real quadrotor. Finally, we consider the general problem of learning a model with a very limited number of samples using meta-learned losses. We show how such losses can encode a prior structure about families of tasks to create well-behaved loss landscapes for efficient model optimization. We demonstrate the efficiency of our approach for learning policies and dynamics models in multiple robotics settings. |
| Keyword | robotics; machine learning; artificial intelligence |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Provenance | Electronically uploaded by the author |
| Type | texts |
| Legacy record ID | usctheses-m |
| Contributing entity | University of Southern California |
| Rights | Molchanov, Artem |
| Physical access | The author retains rights to his/her dissertation, thesis or other graduate work according to U.S. copyright law. Electronic access is being provided by the USC Libraries in agreement with the author, as the original true and official version of the work, but does not grant the reader permission to use the work if the desired use is covered by copyright. It is the author, as rights holder, who must provide use permission if such use is covered by copyright. The original signature page accompanying the original submission of the work to the USC Libraries is retained by the USC Libraries and a copy of it may be obtained by authorized requesters contacting the repository e-mail address given. |
| Repository name | University of Southern California Digital Library |
| Repository address | USC Digital Library, University of Southern California, University Park Campus MC 7002, 106 University Village, Los Angeles, California 90089-7002, USA |
| Repository email | cisadmin@lib.usc.edu |
| Filename | etd-MolchanovA-8923.pdf |
| Archival file | Volume13/etd-MolchanovA-8923.pdf |
Description
| Title | Page 51 |
| Full text | alternative approach where each drifter uses in situ measurements of ocean currents to make control decisions. A control strategy for rendezvous with multiple drifters is presented in [Ouimet and Cort´es, 2014]. Although their targeted application of aggregating multiple drifters is similar, they use a different approach, where the ocean dynamics is represented by internal wave models with known parameters. In contrast, we assume no explicit knowledge about the dynamics of the ocean, except the vertical component of the flow, which we assume to be zero. In Jouffroy et al. [2013b] the target application is to control the absolute position of a drifter in a coastal scenario, where the drifter can anchor itself at the sea bottom if necessary. As an extension, the deep ocean scenario for a single drifter is examined under idealized conditions (the drifter is assumed to have instant estimates of currents at the present location, the ocean currents are assumed to be stationary and to span the plane positively). The external forcing by current flow fields and its impact on the control of underactuated robotic systems is furthermore addressed by Kwok and Mart´ınez [2010] for a coverage task with self-propelled vehicles of bounded velocity in a river environment and by Michini et al. [2014] for tasks of tracking coherent structures on flows with autonomous underwater vehicles in the ocean. 3.2 Single Drifter Control In this section we aim to provide preliminary investigation of the quality of ROMS model for long horizon predictions and possible control strategies of a single drifter in idealistic scenarios. 36 |
