Page 76 |
Save page Remove page | Previous | 76 of 151 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
2 3 4 5 6 7 8 9 10 11 12
0
0.05
0.1
0.15
0.2
0.25
0.3
0.35
Time (hours)
Aggregation metric
mean
std
Figure 3.14: Performance of the realistic drifter system with the extended low-level controller
under different Ttrust. Every point is based on 100 simulation runs. The black curve represents
the mean value and the green curves represent the standard deviation of the aggregation metric at
every point.
Considering high ship operation costs, such clustering can significantly facilitate the process of
collection of drifters.
Finally, we demonstrate an example of a complete deployment scenario, where drifters are
dropped at one position (marked with a green cross), then spread all over the area during 90 days
(Fig. 3.16 left) and finally aggregate over the last 90 days (Fig. 3.16 right). Although we have
quite a good aggregation (more than a half of drifters assembled), the seemingly low score in this
scenario ( 0:31) reflects the fact that the rest of the drifters are either lost or completely spread
through the area due to external forcing (in the particular case of Fig. 3.16: 10 lost, 3 outliers).
Performance under Noisy Estimation
In this section, we finally evaluate the system’s performance under estimation noise. We assume
estimations of velocities are acquired from GPS data solely. As mentioned above in 3.3.3, modern
61
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 76 |
| Full text | 2 3 4 5 6 7 8 9 10 11 12 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 Time (hours) Aggregation metric mean std Figure 3.14: Performance of the realistic drifter system with the extended low-level controller under different Ttrust. Every point is based on 100 simulation runs. The black curve represents the mean value and the green curves represent the standard deviation of the aggregation metric at every point. Considering high ship operation costs, such clustering can significantly facilitate the process of collection of drifters. Finally, we demonstrate an example of a complete deployment scenario, where drifters are dropped at one position (marked with a green cross), then spread all over the area during 90 days (Fig. 3.16 left) and finally aggregate over the last 90 days (Fig. 3.16 right). Although we have quite a good aggregation (more than a half of drifters assembled), the seemingly low score in this scenario ( 0:31) reflects the fact that the rest of the drifters are either lost or completely spread through the area due to external forcing (in the particular case of Fig. 3.16: 10 lost, 3 outliers). Performance under Noisy Estimation In this section, we finally evaluate the system’s performance under estimation noise. We assume estimations of velocities are acquired from GPS data solely. As mentioned above in 3.3.3, modern 61 |
