Search Results for author:
Found 35 papers, 8 papers with code
A System For Robot Concept Learning Through Situated Dialogue
We evaluate the system by comparing learning efficiency to a human baseline in a collaborative reference resolution task and show that the system is effective and efficient in learning new concepts, and that it can informatively generate explanations about its behavior.
It’s About Time: Turn-Entry Timing For Situated Human-Robot Dialogue
Turn-entry timing is an important requirement for conversation, and one that spoken dialogue systems largely fail at.
Social Norms Guide Reference Resolution
Humans use natural language, vision, and context to resolve referents in their environment.
Generating Explanations of Action Failures in a Cognitive Robotic Architecture
We then describe an evaluation that can be extended to further study the effects of varying the explanation templates.
NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds
To this end, we introduce NovelGym, a flexible and adaptable ecosystem designed to simulate gridworld environments, serving as a robust platform for benchmarking reinforcement learning (RL) and hybrid planning and learning agents in open-world contexts.
A principled approach to model validation in domain generalization
Domain generalization aims to learn a model with good generalization ability, that is, the learned model should not only perform well on several seen domains but also on unseen domains with different data distributions.
Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments
Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to be able to guarantee satisfactory task performance.
Trade-off between reconstruction loss and feature alignment for domain generalization
To deal with challenging settings in DG where both data and label of the unseen domain are not available at training time, the most common approach is to design the classifiers based on the domain-invariant representation features, i. e., the latent representations that are unchanged and transferable between domains.
Joint covariate-alignment and concept-alignment: a framework for domain generalization
Particularly, our framework proposes to jointly minimize both the covariate-shift as well as the concept-shift between the seen domains for a better performance on the unseen domain.
RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments
We propose RAPid-Learn: Learning to Recover and Plan Again, a hybrid planning and learning method, to tackle the problem of adapting to sudden and unexpected changes in an agent's environment (i. e., novelties).
NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds
In order for artificial agents to successfully perform tasks in changing environments, they must be able to both detect and adapt to novelty.
Conditional entropy minimization principle for learning domain invariant representation features
Invariance-principle-based methods such as Invariant Risk Minimization (IRM), have recently emerged as promising approaches for Domain Generalization (DG).
Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model
Dialogue agents that interact with humans in situated environments need to manage referential ambiguity across multiple modalities and ask for help as needed.
Barycentric-alignment and reconstruction loss minimization for domain generalization
To bridge this gap between theory and practice, we introduce a new upper bound that is free of terms having such dual dependence, resulting in a fully optimizable risk upper bound for the unseen domain.
Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver
The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of properties, and developing them.
How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus
Intelligent agents that are confronted with novel concepts in situated environments will need to ask their human teammates questions to learn about the physical world.
SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning
Symbolic planning models allow decision-making agents to sequence actions in arbitrary ways to achieve a variety of goals in dynamic domains.
Reasoning Requirements for Indirect Speech Act Interpretation
We perform a corpus analysis to develop a representation of the knowledge and reasoning used to interpret indirect speech acts.
Developing a Corpus of Indirect Speech Act Schemas
Resolving Indirect Speech Acts (ISAs), in which the intended meaning of an utterance is not identical to its literal meaning, is essential to enabling the participation of intelligent systems in peoples{'} everyday lives.
Generating Justifications for Norm-Related Agent Decisions
We present an approach to generating natural language justifications of decisions derived from norm-based reasoning.
Engaging in Dialogue about an Agent's Norms and Behaviors
We present a set of capabilities allowing an agent planning with moral and social norms represented in temporal logic to respond to queries about its norms and behaviors in natural language, and for the human user to add and remove norms directly in natural language.
Augmenting Robot Knowledge Consultants with Distributed Short Term Memory
In previous work, we developed a Consultant Framework that facilitates modality-agnostic access to information distributed across a set of heterogeneously represented knowledge sources.
Sensitivity to Input Order: Evaluation of an Incremental and Memory-Limited Bayesian Cross-Situational Word Learning Model
We present a variation of the incremental and memory-limited algorithm in (Sadeghi et al., 2017) for Bayesian cross-situational word learning and evaluate the model in terms of its functional performance and its sensitivity to input order.
Quasi-Dilemmas for Artificial Moral Agents
In this paper we describe moral quasi-dilemmas (MQDs): situations similar to moral dilemmas, but in which an agent is unsure whether exploring the plan space or the world may reveal a course of action that satisfies all moral requirements.
Pardon the Interruption: Managing Turn-Taking through Overlap Resolution in Embodied Artificial Agents
Speech overlap is a common phenomenon in natural conversation and in task-oriented interactions.
Interpretable Apprenticeship Learning with Temporal Logic Specifications
Recent work has addressed using formulas in linear temporal logic (LTL) as specifications for agents planning in Markov Decision Processes (MDPs).
Referring Expression Generation under Uncertainty: Algorithm and Evaluation Framework
For situated agents to effectively engage in natural-language interactions with humans, they must be able to refer to entities such as people, locations, and objects.
AI Challenges in Human-Robot Cognitive Teaming
Among the many anticipated roles for robots in the future is that of being a human teammate.
The MacGyver Test - A Framework for Evaluating Machine Resourcefulness and Creative Problem Solving
Current measures of machine intelligence are either difficult to evaluate or lack the ability to test a robot's problem-solving capacity in open worlds.
Creating POS Tagging and Dependency Parsing Experts via Topic Modeling
Part of speech (POS) taggers and dependency parsers tend to work well on homogeneous datasets but their performance suffers on datasets containing data from different genres.
Disfluent but effective? A quantitative study of disfluencies and conversational moves in team discourse
The purpose of this paper is to address those gaps in the following ways: (1) investigate which properties of task-oriented discourse correspond with effective performance in human teams, and (2) discuss how and to what extent these properties can be utilized in spoken dialogue systems.
Enabling Basic Normative HRI in a Cognitive Robotic Architecture
Collaborative human activities are grounded in social and moral norms, which humans consciously and subconsciously use to guide and constrain their decision-making and behavior, thereby strengthening their interactions and preventing emotional and physical harm.
