Susan L. Epstein

ICAPS Conference 2021 Conference Paper

Hierarchical Freespace Planning for Navigation in Unfamiliar Worlds

• Raj Korpan
• Susan L. Epstein

Autonomous navigation in a large, complex space requires a spatial model, but the construction of a detailed map is costly. This paper demonstrates how two kinds of exploration support an alternative to metric mapping, one that facilitates robust hierarchical path planning. High-level exploration builds a global spatial model whose connectivity supports an effective, efficient, freespace planner, while low-level, target-driven exploration addresses areas where the global model lacks knowledge. Empirical results demonstrate successful and efficient travel in three challenging worlds.

AAMAS Conference 2018 Conference Paper

Online Learning for Crowd-sensitive Path Planning

• Anoop Aroor
• Susan L. Epstein
• Raj Korpan

In crowded environments, the shortest path for an autonomous robot navigator may not be the best choice — another plan that avoids crowded areas might be preferable. Such a crowd-sensitive path planner, however, requires knowledge about the crowd’s global behavior. This paper formulates a Bayesian approach that relies only on an onboard range scanner to learn a global crowd model online. Two new algorithms, CUSUM-A* and Risk-A*, use local observations to continuously update the crowd model. CUSUM-A* tracks the spatio-temporal changes in the crowd; Risk-A* adjusts for changes in navigation cost due to human-robot interactions. Extensive evaluation in a challenging simulated environment demonstrates that both algorithms generate plans that significantly reduce their proximity to moving obstacles, and thereby protect people from actuator error and inspire their trust in the robot.

AIJ Journal 2015 Journal Article

Wanted: Collaborative intelligence

• Susan L. Epstein

Although the original vision for artificial intelligence was the simulation of (implicitly human) intelligence, research has gradually shifted to autonomous systems that compete with people. The resultant popular attitude toward artificial intelligence, we argue here, is by turns disdain, grudging acceptance, and fear. That attitude not only limits our work's potential, but also imperils its support. This paper proposes a constructive alternative: the development of collaborative intelligence. As envisioned here, a collaborative intelligence does not require encyclopedic command and need not be limited to a single problem. The necessary components of a collaborative intelligence are nearly at hand, and the key issues readily identified. As a first step, this paper proposes three challenging but accessible problems that would both change the public perception of artificial intelligence and spur substantive research to advance our science.

AAMAS Conference 2013 Conference Paper

HRTeam: A Framework to Support Research on Human/Multi-Robot Interaction

• Elizabeth Sklar
• Simon Parsons
• A. Tuna Özgelen
• Eric Schneider
• Michael Costantino
• Susan L. Epstein

The HRTeam framework supports research on discovering and evaluating methods for addressing a range of issues in human/multi-robot team interaction. Three sample tasks illustrate the methods currently being investigated: mission selection, dictated by a human operator; collision avoidance, taught by a human trainer; and targeted exploration, jointly achieved with a human collaborator. Physical and simulated multi-robot environments are used to support this research.

SoCS Conference 2012 Conference Paper

Adaptive Parallelization for Constraint Satisfaction Search

• Xi Yun
• Susan L. Epstein

This paper introduces two adaptive paradigms that parallelize search for solutions to constraint satisfaction problems. Both are intended for any sequential solver that uses contention-oriented variable-ordering heuristics and restart strategies. Empirical results demonstrate that both paradigms improve the search performance of an underlying sequential solver, and also solve challenging problems left open after recent solver competitions.

AAAI Conference 2004 Conference Paper

Learning and Applying Competitive Strategies

• Esther Lock
• Susan L. Epstein

Learning reusable sequences can support the development of expertise in many domains, either by improving decisionmaking quality or decreasing execution speed. This paper introduces and evaluates a method to learn action sequences for generalized states from prior problem experience. From experienced sequences, the method induces the context that underlies a sequence of actions. Empirical results indicate that the sequences and contexts learned for a class of problems are actually those deemed important by experts for that particular class, and can be used to select appropriate action sequences when solving problems there.

AAAI Conference 1999 Conference Paper

Game Playing: The Next Moves

• Susan L. Epstein
• Hunter College

Computer programs now play many board games as well or better than the most expert humans. Human players, however, learn, plan, allocate resources, and integrate multiple streams of knowledge. This paper highlights recent achievements in game playing, describes some cognitively- oriented work, and poses three related challenge problems for the AI community.

AIJ Journal 1998 Journal Article

Pragmatic navigation: reactivity, heuristics, and search

• Susan L. Epstein

FORR (FOr the Right Reasons) is an architecture for learning and problem solving that integrates a possibly incomplete and overlapping set of solution methods to address complex problems. Each method, although it represents some facet of domain expertise, may vary in reliability and speed. The principal contribution of this paper is the extension of FORR to include situation-based behavior (the serial testing of known, triggered techniques for problem solving in a domain) with reactivity and heuristic reasoning. FORR categorizes methods as reactive, heuristic, or situationbased, and addresses problem solving with one category of methods at a time. A hierarchical reasoner first has the opportunity to react correctly. If no ready reaction is computed, the reasoner activates a set of reactive triggers for time-limited search procedures tailored to specific situations. If they, too, fail to produce a response, the reasoner resorts to collaboration among heuristic rationales. All three components reference knowledge learned from experience. In a series of experiments, this architecture is shown to be effective and efficient. Ablation experiments demonstrate how each component plays an important role in problem solving. Additional contributions of this paper include a FORR-based, pragmatic, cognitively plausible approach to navigation with learned heuristic approximations that describe two-dimensional territory and travel experience through it, and a careful study of how situation-based behavior, reactivity, and heuristics interact there. Empirical evidence demonstrates that the resultant system is both effective and efficient, and guidelines for generalization to other domains are provided.

AAAI Conference 1998 Conference Paper

Toward Design as Collaboration

• Susan L. Epstein