Search

Your search keyword '"Knudson, Matthew"' showing total 39 results
Start Over Author "Knudson, Matthew"
39 results on '"Knudson, Matthew"'

1. Study of Tools for Command and Telemetry Dictionaries

Author

Pires, Craig and Knudson, Matthew D

Subjects
Computer Programming And Software
Abstract

The Command and Telemetry Dictionary is at the heart of space missions. The C&T Dictionary represents all of the information that is exchanged between the various systems both in space and on the ground. Large amounts of ever-changing information has to be disseminated to all for the various systems and sub-systems throughout all phases of the mission. The typical approach of having each sub-system manage it's own information flow, results in a patchwork of methods within a mission. This leads to significant duplication of effort and potential errors. More centralized methods have been developed to manage this data flow. This presentation will compare two tools that have been developed for this purpose, CCDD and SCIMI that were designed to work with the Core Flight System (cFS).

Published
2017

4. Multiagent Flight Control in Dynamic Environments with Cooperative Coevolutionary Algorithms

Author

Knudson, Matthew D, Colby, Mitchell, and Tumer, Kagan

Subjects
Cybernetics, Artificial Intelligence And Robotics, Air Transportation And Safety
Abstract

Dynamic flight environments in which objectives and environmental features change with respect to time pose a difficult problem with regards to planning optimal flight paths. Path planning methods are typically computationally expensive, and are often difficult to implement in real time if system objectives are changed. This computational problem is compounded when multiple agents are present in the system, as the state and action space grows exponentially. In this work, we use cooperative coevolutionary algorithms in order to develop policies which control agent motion in a dynamic multiagent unmanned aerial system environment such that goals and perceptions change, while ensuring safety constraints are not violated. Rather than replanning new paths when the environment changes, we develop a policy which can map the new environmental features to a trajectory for the agent while ensuring safe and reliable operation, while providing 92% of the theoretically optimal performance

Published
2014

5. Multiagent Flight Control in Dynamic Environments with Cooperative Coevolutionary Algorithms

Author

Colby, Mitchell, Knudson, Matthew D, and Tumer, Kagan

Subjects
Cybernetics, Artificial Intelligence And Robotics, Aeronautics (General)
Abstract

Dynamic environments in which objectives and environmental features change with respect to time pose a difficult problem with regards to planning optimal paths through these environments. Path planning methods are typically computationally expensive, and are often difficult to implement in real time if system objectives are changed. This computational problem is compounded when multiple agents are present in the system, as the state and action space grows exponentially with the number of agents in the system. In this work, we use cooperative coevolutionary algorithms in order to develop policies which control agent motion in a dynamic multiagent unmanned aerial system environment such that goals and perceptions change, while ensuring safety constraints are not violated. Rather than replanning new paths when the environment changes, we develop a policy which can map the new environmental features to a trajectory for the agent while ensuring safe and reliable operation, while providing 92% of the theoretically optimal performance.

Published
2014

6. Announced Strategy Types in Multiagent RL for Conflict-Avoidance in the National Airspace

Author

Rebhuhn, Carrie, Knudson, Matthew D, and Tumer, Kagan

Subjects
Behavioral Sciences, Aircraft Communications And Navigation
Abstract

The use of unmanned aerial systems (UAS) in the national airspace is of growing interest to the research community. Safety and scalability of control algorithms are key to the successful integration of autonomous system into a human-populated airspace. In order to ensure safety while still maintaining efficient paths of travel, these algorithms must also accommodate heterogeneity of path strategies of its neighbors. We show that, using multiagent RL, we can improve the speed with which conflicts are resolved in cases with up to 80 aircraft within a section of the airspace. In addition, we show that the introduction of abstract agent strategy types to partition the state space is helpful in resolving conflicts, particularly in high congestion.

Published
2014

14. Abstract 86

Author

Donneys, Alexis, primary, Subramanian, Chitra, additional, Lynn, Jeremy, additional, Urlaub, Kevin, additional, Uygur, Halil Safak, additional, Lalchandani, Keshav, additional, Kovatch, Kevin, additional, Luby, Alexandra, additional, Buchman, Lauren, additional, Nelson, Noah S., additional, Knudson, Matthew, additional, Cohen, Mark S., additional, and Buchman, Steven R., additional

Published
2019
Full Text
View/download PDF

15. Mycobacterium bovis Bacillus Calmette-Guérin-Induced Macrophage Cytotoxicity against Bladder Cancer Cells

Author

Luo, Yi and Knudson, Matthew J.

Subjects
Article Subject
Abstract

Many details of the molecular and cellular mechanisms involved in Mycobacterium bovis bacillus Calmette-Guérin (BCG) immunotherapy of bladder cancer have been discovered in the past decades. However, information on a potential role for macrophage cytotoxicity as an effector mechanism is limited. Macrophages play pivotal roles in the host innate immunity and serve as a first line of defense in mycobacterial infection. In addition to their function as professional antigen-presenting cells, the tumoricidal activity of macrophages has also been studied with considerable interest. Studies have shown that activated macrophages are potent in killing malignant cells of various tissue origins. This review summarizes the current understanding of the BCG-induced macrophage cytotoxicity toward bladder cancer cells with an intention to inspire investigation on this important but underdeveloped research field.

Published
2010
Full Text
View/download PDF

20. 552 ANTI-IL10-R1 MONOCLONAL ANTIBODY WITH CONCOMITANT BACILLUS CALMETTE-GUERIN (BCG) PREVENTS METASTATIC BLADDER CANCER IN AN IN VIVO MOUSE MODEL

Author

Askeland, Eric J., primary, Newton, Mark R., additional, Bockholt, Nathan A., additional, Knudson, Matthew J., additional, Henning, Jonathan R., additional, Wang, Xu, additional, Askeland, Ryan W., additional, Weady, Peter, additional, Smith, George J., additional, Eisenbraun, Michael D., additional, Fraser, James D., additional, O'Donnell, Michael A., additional, and Luo, Yi, additional

Published
2012
Full Text
View/download PDF

21. Abstract 5390: Anti-IL10-R1 monoclonal antibody with concomitant bacillus calmette-Guérin (BCG) prevents metastatic bladder cancer in an in vivo mouse model

Author

Askeland, Eric, primary, Newton, Mark, additional, Bockholt, Nathan, additional, Knudson, Matthew, additional, Henning, Jonathan, additional, Wang, Xu, additional, Askeland, Ryan, additional, Weady, Peter, additional, Smith, George, additional, Eisenbraun, Michael, additional, Fraser, James, additional, O'Donnell, Michael, additional, and Luo, Yi, additional

Published
2012
Full Text
View/download PDF

28. Mycobacterium bovis Bacillus Calmette-Guérin-Induced Macrophage Cytotoxicity against Bladder Cancer Cells.

Author

Yi Luo and Knudson, Matthew J.

Subjects
*MYCOBACTERIUM bovis, *IMMUNOTHERAPY, *BLADDER cancer, *MACROPHAGES, *MYCOBACTERIAL diseases, *CELL-mediated cytotoxicity
Abstract

Many details of the molecular and cellular mechanisms involved in Mycobacterium bovis bacillus Calmette-Guérin (BCG) immunotherapy of bladder cancer have been discovered in the past decades. However, information on a potential role for macrophage cytotoxicity as an effector mechanism is limited. Macrophages play pivotal roles in the host innate immunity and serve as a first line of defense in mycobacterial infection. In addition to their function as professional antigen-presenting cells, the tumoricidal activity of macrophages has also been studied with considerable interest. Studies have shown that activated macrophages are potent in killing malignant cells of various tissue origins. This review summarizes the current understanding of the BCG-induced macrophage cytotoxicity toward bladder cancer cells with an intention to inspire investigation on this important but underdeveloped research field. [ABSTRACT FROM AUTHOR]

Published
2010
Full Text
View/download PDF

31. Heterogeneous Populations of Learning Agents in the Minority Game

Author

Catteeuw, David, Manderick, Bernard, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

32. Solving Sparse Delayed Coordination Problems in Multi-Agent Reinforcement Learning

Author

De Hauwere, Yann-Michaël, Vrancx, Peter, Nowé, Ann, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

33. Basis Function Discovery Using Spectral Clustering and Bisimulation Metrics

Author

Comanici, Gheorghe, Precup, Doina, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

34. A Convergent Multiagent Reinforcement Learning Approach for a Subclass of Cooperative Stochastic Games

Author

Kemmerich, Thomas, Kleine Büning, Hans, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

35. Reinforcement Learning Transfer via Common Subspaces

Author

Ammar, Haitham Bou, Taylor, Matthew E., Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

36. Leveraging Domain Knowledge to Learn Normative Behavior: A Bayesian Approach

Author

Hosseini, Hadi, Ulieru, Mihaela, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

37. Multi-agent Reinforcement Learning for Simulating Pedestrian Navigation

Author

Martinez-Gil, Francisco, Lozano, Miguel, Fernández, Fernando, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

38. Co-learning Segmentation in Marketplaces

Author

Robinson, Edward, McBurney, Peter, Yao, Xin, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Vrancx, Peter, editor, Knudson, Matthew, editor, and Grześ, Marek, editor

Published
2012
Full Text
View/download PDF

39. Solving sparse delayed coordination problems in multi-agent reinforcement learning

Author

Ann Nowé, Peter Vrancx, Yann-Michaël De Hauwere, Peter, Vrancx, Knudson, Matthew, Marek, Grzes, Computational Modelling, and Informatics and Applied Informatics

Subjects
business.industry, Computer science, Multi-agent system, SIGNAL (programming language), Machine learning, computer.software_genre, artificial intelligence, Reinforcement Learning, Multi-agent Systems, Action (philosophy), Backup, sparse interactions, Reinforcement learning, State space, Coordination game, Artificial intelligence, State (computer science), business, computer
Abstract

One of the main advantages of Reinforcement Learning is the capability of dealing with a delayed reward signal. Using an appropriate backup diagram, rewards are backpropagated through the state space. This allows agents to learn to take the correct action that results in the highest future (discounted) reward, even if that action results in a suboptimal immediate reward in the current state. In a multi-agent environment, agents can use the same principles as in single agent RL, but have to apply them in a complete joint-state-joint-action space to guarantee optimality. Learning in such a state space can however be very slow. In this paper we present our approach for mitigating this problem. Future Coordinating Q-learning (FCQ-learning) detects strategic interactions between agents several timesteps before these interactions occur. FCQ-learning uses the same principles as CQ-learning [3] to detect the states in which interaction is required, but several timesteps before this is reflected in the reward signal. In these states, the algorithm will augment the state information to include information about other agents which is used to select actions. The techniques presented in this paper are the first to explicitly deal with a delayed reward signal when learning using sparse interactions.

Published
2012

Catalog

Books, media, physical & digital resources
See catalog results