Institute for Systems Research Technical Reports
Permanent URI for this collection
This archive contains a collection of reports generated by the faculty and students of the Institute for Systems Research (ISR), a permanent, interdisciplinary research unit in the A. James Clark School of Engineering at the University of Maryland. ISR-based projects are conducted through partnerships with industry and government, bringing together faculty and students from multiple academic departments and colleges across the university.
- ItemUsing Metareasoning on a Mobile Ground Robot to Recover from Path Planning Failures(2023-02) Molnar, Sidney; Mueller, Matt; Macpherson, Robert; Rhoads, Lawrence; Herrmann, Jeffrey W.Autonomous mobile ground robots use global and local path planners to determine the routes that they should follow to achieve mission goals while avoiding obstacles. Although many path planners have been developed, no single one is best for all situations. This paper describes metareasoning approaches that enable a robot to select a new path planning algorithm when the current planning algorithm cannot find a feasible solution. We implemented the approaches within a ROS-based autonomy stack and conducted simulation experiments to evaluate their performance in multiple scenarios. The results show that these metareasoning approaches reduce the frequency of failures and reduce the time required to complete the mission.
- ItemData for: Eelbrain: A Python toolkit for time-continuous analysis with temporal response functions(2021) Brodbeck, Christian; Bhattasali, Shohini; Das, Proloy; Simon, Jonathan Z.This dataset accompanies “Eelbrain: A Python toolkit for time-continuous analysis with temporal response functions” (Brodbeck et al., 2021) and is a derivative of the Alice EEG datasets collected at the University of Michigan Computational Neurolinguistics Lab (Bhattasali et al., 2020), licensed under CC BY (https://creativecommons.org/licenses/by/4.0/) and the original work can be found at DOI: 10.7302/Z29C6VNH. The files were converted from the original matlab format to fif format in order to be compatible with Eelbrain. This dataset includes the EEG data for 33 participants, which were used in the example analyses for the paper. The original Alice dataset included data from all 49 participants and participants were excluded due to artifacts and incorrect behavioral responses (for more details see Bhattasali et al., 2020). You can use the Python script data_grab.py at https://github.com/christianbrodbeck/Alice-Eelbrain to download and unzip these files into a specified destination folder.
- ItemDynamic Estimation of Auditory Temporal Response Functions via State-Space Models with Gaussian Mixture Process Noise(PLOS Computational Biology, 2020-08-02) Presacco, Alessandro; Miran, Sina; Fu, Michael; Marcus, Steven; Simon, Jonathan; Babadi, BehtashMEG data used for the "Switching attention" experiment. This set of data refers to the part of the "forced" switching of attention
- ItemDynamic Estimation of Auditory Temporal Response Functions via State-Space Models with Gaussian Mixture Process Noise(PLOS Computational Biology, 2020-08-02) Presacco, Alessandro; Miran, Sina; Fu, Michael; Marcus, Steven; Jonathan, Simon; Babadi, BetashMEG data used for the "Switching attention" experiment
- ItemData-driven Metareasoning for Collaborative Autonomous Systems(2020-01) Herrmann, JeffreyWhen coordinating their actions to accomplish a mission, the agents in a multi-agent system may use a collaboration algorithm to determine which agent performs which task. This paper describes a novel data-driven metareasoning approach that generates a metareasoning policy that the agents can use whenever they must collaborate to assign tasks. This metareasoning approach collects data about the performance of the algorithms at many decision points and uses this data to train a set of surrogate models that can estimate the expected performance of different algorithms. This yields a metareasoning policy that, based on the current state of the system, estimated the algorithms’ expected performance and chose the best one. For a ship protection scenario, computational results show that one version of the metareasoning policy performed as well as the best component algorithm but required less computational effort. The proposed data-driven metareasoning approach could be a promising tool for developing policies to control multi-agent autonomous systems.