Select a calendar:
Filter December Events by Event Type:
SUNMONTUEWEDTHUFRISAT
University Calendar
Events for December
-
PhD Defense - Xue Cai
Tue, Dec 03, 2013 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: GLOBAL ANALYSIS AND MODELING ON DECENTRALIZED INTERNET
PhD Candidate: Xue Cai
Committee:
- John Heidemann (Chair)
- Walter Willinger
- Ramesh Govindan
- Antonio Ortega (EE, Outside)
Time: Tuesday Dec 3 @ 10am-12pm
Location: SAL 222
Abstract:
Better understanding about Internet infrastructure is crucial to improve the reliability, performance, and security of web services. The need for this understanding then drives research in network measurements. Internet measurements explore a variety of data related to a specific topic and then develop approaches to transform data into useful understanding about the topic. This process is not straightforward since available data often only contains indirect information that may appear to have limited connection to the topic.
This body of work asserts that systematic approaches can overcome data limitations to improve understanding about important aspects of the Internet infrastructure. We demonstrate the validity of our thesis statement by providing three specific examples that develop novel approaches and provide novel understanding compared to prior work. In particular, we employ four systematic approachesâstatistical, clustering, modeling, and what-if approachâto understand three important aspects of the Internet: the efficiency and management of IPv4 addresses, the ownership of Autonomous Systems (ASes), and the robustness of web services when facing critical facility disruption. These approaches have addressed a variety of challenges posed by indirect, incomplete, over-fit, noisy and unknown data; they in turn enable us to improve understanding about the Internet.
Each of our three studies explores a different area of the problem space and opens a much larger area of opportunity. The data limitations addressed by our approaches also occur in many other problems. We believe our approaches can inspire future work to solve these problems and in turn provide more useful understanding about the Internet.
Location: Henry Salvatori Computer Science Center (SAL) - 222
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Defense - Peter Pastor
Wed, Dec 18, 2013 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: A Data-Driven Approach to Autonomous Manipulation
Candidate: Peter Pastor
Committee members:
Stefan Schaal (chair)
Gaurav S. Sukhatme
Nicolas Schweighofer (outside member)
Time: December 18, 2013, 10am
Place: Ronald Tutor Hall (RTH), room 422
Abstract:
The problem of an aging society is real and will affect everyone. There will be too few young people that can ensure adequate living conditions for the elderly. Personal robots have the potential to assist in day-to-day tasks whenever there are too few humans to cope with societal needs. However, for personal robots to become useful they need to be able to skillful manipulate objects in their environment. Unfortunately, the problem of autonomous manipulation is very complex and progress towards creating autonomous behaviors seems to have reached a plateau.
In this thesis, we will present a novel way of thinking about movement generation. We argue that movement generation (motor output) and perceptual processing (sensor input) are inseparably intertwined and that the ability to predict sensor information is essential for skillful manipulation. Movement generation without sensor expectations defaults to open-loop execution which is prone to failure in dynamic and unstructured environments. However, predicting sensor information for an increasing number of sensor modalities including force/torque and tactile feedback through physics based modelling is challenging given the variety of objects, the diversity of possible manipulation behaviors, and the uncertainty in the real world. Instead, our approach leverages from a key insight: Movement generation can dictate expected sensor feedback. Similar manipulation movements will give rise to sensory events that are similar to previous ones. Thus, stereotypical movements facilitate to associate and accumulate sensor information from past trials and use these sensor experiences to predict sensor feedback in future trials.
We will call such movements augmented with associated sensor information Associative Skill Memories (ASMs). We will present a coherent data-driven framework for manipulation that implements this paradigm. First, we will introduce a modular movement representation suitable to encode movements along with associated sensor experiences. Second, we will show how stereotypical movements can be learned from demonstrations and refined using trial-and-error learning. Third, we will show how ASMs can be used to monitor task progress, to realize contact reactive manipulation, and to purposefully choose subsequent movements. Finally, we will present a method that can learn forward models for these stereotypical movements.
Location: Ronald Tutor Hall of Engineering (RTH) - 422
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Defense - Jnaneshwar Das
Thu, Dec 19, 2013 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Data-driven Robotic Sampling for Marine Ecosystem Monitoring
Candidate: Jnaneshwar Das
Committee members:
Gaurav S. Sukhatme (chair)
Stefan Schaal
David Caron (outside member)
Time: December 19, 2013, 12 noon
Place: Ronald Tutor Hall (RTH), room 406
Abstract:
Monitoring marine ecosystems is a challenging problem due to complex ocean dynamics and limitations of in-situ sensing. Sensors onboard Autonomous Underwater Vehicles (AUVs) measure environmental and optical properties such as temperature, salinity, and chlorophyll fluorescence in real time. However, studying plankton ecology and community structure requires retrieval of water samples to shore for lab analysis using molecular or morphological methods. This necessitates manual sampling from shipboards or piers -- a resource and time intensive process that makes persistent monitoring of marine ecosystems difficult.
Motivated by advances in AUV technology that allow autonomous retrieval of water samples, we have developed a data-driven robotic sampling paradigm for ecosystem monitoring. We treat microorganism abundance as a hidden feature that can be predicted using a probabilistic regression model trained on past data, with observable environmental parameters as its input. This model is used onboard the AUV to predict microorganism abundance in real time. An online sampling policy uses these predictions to make irrevocable decisions to sequentially collect a fixed number of water samples over a course of a deployment. Learning a probabilistic model facilitates introspection, both online, guiding sampling decisions in an exploration-exploitation setting, and offline, enabling scientists to be aware of the accuracy of the environmental niche of the organisms they are interested in, as captured implicitly in the trained model.
The contributions of this thesis are as follows. First, we explore a challenging science problem in a statistical machine learning setting, enabling the utilization of theoretically sound methods from function approximation, active learning, and online algorithms. Second, we present extensive studies on real field data from a week long campaign in 2005 consisting of 17 consecutive AUV deployments. The empirical evidence affirms the utility of our sampling approach. Third, and most important, we present results from a recent field deployment that targeted a genus of phytoplankton known to cause potentially toxic blooms. A probabilistic regression model was trained on a dataset of lab analyzed water samples from AUV missions carried out during a previous season. This trained model was used on board the AUV to target the phytoplankton of interest, and samples were analyzed on shore. Preliminary lab analysis results are promising, showing abundance of the target organism, and facilitating lab cultures. This is the first time such a field experiment has been carried out in its entirety in a data-driven fashion, in effect 'closing the loop' on a significant and relevant ecosystem monitoring problem.
Although the experimental context for this thesis is marine ecosystem monitoring, our work is well-suited for autonomous and persistent robotic observation of any hidden feature that cannot be measured in-situ, but possesses observable covariates, e.g for soil sample analysis, and surficial geology applications thus opening up the potential for advanced autonomous robotic exploration of unstructured environments that are inaccessible to humans.
Location: Ronald Tutor Hall of Engineering (RTH) - 406
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
