Projects

At any given time, we have multiple active projects ongoing in the Lab or affiliated with the lab. An overview of the projects is given here. For more details on selected project, click on the links below or use the “Projects” menu.

Intelligent, real-world agent control

Several of our projects center around intelligent, high-level control of autonomous or semi-autonomous agents. These include:

  • Orca – focuses on intelligence, reactive, context-sensitive control of real-world agents, including autonomous underwater vehicles (AUVs) and land robots, and softbots. (MS, PhD, Capstone project opportunities.)
  • Context-mediated behavior (CMB) – focuses on representing and reasoning about contextual knowledge for intelligent agents to allow them to automatically behave appropriately for their context; overlaps with Orca, CoDA, others. (MS, PhD, Capstone project opportunities.)
  • Context-driven behavior – this is form of/extension to CMB that uses plan and context projection to help agents decide how to achieve their goals and to behave in a fashion plausibly like humans. (PhD project of Chris Wilson)
  • ACP/ACRO – focuses on intelligent, appropriate commitment in reactive planning, enabling an agent to intelligently commit to future actions to avoid plan failure and replanning; the ACRO planner is the first implementation of ACP. (PhD project of Erik Albert; on hold)

Deep learning

  • Context-dependent deep learning (CDDL) – How can contextual reasoning (e.g., CMB, above), be used to help deep-learning systems? (MS, PhD, Capstone project opportunities.)
  • Seabird nesting survey – this uses deep-learning (e.g., Mask R-CNNs) to identify seabirds and their nests from aerial (plane, drone) imagery. (Project of Alex Revello and collaborators in Wildlife Ecology; project opportunities exist here, too).

Multiagent systems (MAS)

Our primary MAS research project is CoDA, whose major focus is autonomous organization, operation, and reorganization of real-world multiagent systems. Its initial domain is controlling autonomous oceanographic sampling networks (AOSNs; CoDA = Cooperative Distributed AOSN Control), which are groups of AUVs and other instrument platforms that cooperate to return long-term data from an area of interest in the ocean. (MS, PhD, Capstone project opportunities.)

Subprojects/foci and related projects include:

  • Context-sensitive MAS organization/reorganization – focuses on developing ways to collaboratively design organizations for different contexts, noticing when the organization needs to be changed, and agreeing on a joint context for the agents involved; overlaps with the CMB project.
  • Cooperation protocol development – focuses on developing protocols to allow agents to self-organize, cooperate, and reorganize.
  • Game engine-based simulation for AUVs and multi-AUV systems – focuses on using the game engines, such as Unity and Unreal, in realistic simulation testbeds for single agents and multiagent systems. (Possible senior project, masters opportunities)
  • Multi-fidelity simulation – focuses on developing a simulator for CoDA that can handle high-level, low-resolution through low-level, high-resolution simulations, with various parts of the modeled system possibly present in different resolutions. Current version uses CLIPS for high-level simulation, CADCON for low-level simulation; next generation will use Lisa and the game engine-based simulator, above. (Possible senior project, masters opportunities)

Computational ecology

  • Predator-prey modeling – small-scale modeling of predator-prey interaction, in particular the important players in early marine fouling community succession, nudibranchs (sea slugs) and hydroids. (Capstone project opportunities.)
  • Estuary modeling – the MEME (Maine Ecosystem Model for Estuaries) project, currently on hiatus, focuses on extending the predator-prey modeling project to the level of an entire estuary to model how early community succession impacts ecosystem structure. (MS, PhD, Capstone project opportunities.)
  • CASFish – focuses on ecosystem modeling for fisheries management. This is a large, multidisciplinary, multi-organization project that MaineSAIL is involved in. The project is centered primarily in the School of Marine Sciences at UMaine, but also involves researchers from MaineSAIL (R.M. Turner), UMA, Unity College, the Darling Center, Colby College, and elsewhere. (On hiatus.)

Computer science education

  • K-12: Teaching programming to elementary students. A past project taught 3rd through 5th graders programming using Alice and Scratch (R.M. Turner,E.H. Turner, and Jaimi Allen [MS’10], Adi Levy Conlogue [MS’13]).

  • College: Long-term study focusing on how to recruit and retain computer science students, particularly women and minorities, using a rigorous, non-programming introduction to computer science in the first year. Part of this has resulted in the creation of a locally-required course, COS 140: Foundations of Computer Science, for which a textbook has been published.

Literate programming for interpreted languages

The LP/Lisp project focuses on developing literate programming tools for interpreted languages (e.g., Lisp). Traditional literate programming tools (e.g., noweb) are not appropriate for such languages due to the different workflow of the programmers (i.e., interactive use of an interpreter with no required compile phase). Versions of the LP/Lisp tool are released for others to use; see the “Software” menu item above. (Completed.)