A5044523801- Social Robot Interaction and HRI
- Speech and dialogue systems
- AI-based Problem Solving and Planning
- Multi-Agent Systems and Negotiation
- Ethics and Social Impacts of AI
- Natural Language Processing Techniques
- Reinforcement Learning in Robotics
- Psychology of Moral and Emotional Judgment
- Topic Modeling
- Logic, Reasoning, and Knowledge
- Multimodal Machine Learning Applications
- AI in Service Interactions
- Robotics and Automated Systems
- Evolutionary Game Theory and Cooperation
- Robot Manipulation and Learning
- Neuroethics, Human Enhancement, Biomedical Innovations
- Semantic Web and Ontologies
- Human-Automation Interaction and Safety
- Robotic Path Planning Algorithms
- Modular Robots and Swarm Intelligence
- Domain Adaptation and Few-Shot Learning
- Bayesian Modeling and Causal Inference
- Computability, Logic, AI Algorithms
- EEG and Brain-Computer Interfaces
- Language and cultural evolution
Tufts University
2015-2024
Human Media
2015-2024
DEVCOM Army Research Laboratory
2022
United States Army Combat Capabilities Development Command
2022
University of Rochester
2022
Colorado School of Mines
2018
Indiana University
1998-2016
National Institute for Physiological Sciences
2016
Columbia University
2014
University of Copenhagen
2014
It is commonly believed that race perceived through another's facial features, such as skin color. In the present research, we demonstrate cues to social status often surround a face systematically change perception of its race. Participants categorized faces varied along White–Black morph continua and were presented with high-status or low-status attire. Low-status attire increased likelihood categorization Black, whereas White; this influence grew stronger became more ambiguous (Experiment...
Moral norms play an essential role in regulating human interaction. With the growing sophistication and proliferation of robots, it is important to understand how ordinary people apply moral robot agents make judgments about their behavior. We report first comparison people's (of permissibility, wrongness, blame) agents. Two online experiments (total N = 316) found that compared with agents, were more strongly expected take action sacrifices one person for good many (a "utilitarian" choice),...
The uncanny valley has become synonymous with the uneasy feeling of viewing an animated character or robot that looks imperfectly human. Although previous experiments have focused on relations among a character's visual elements, current experiment examines whether mismatch in human realism face and voice causes it to be evaluated as eerie. results support this hypothesis.
Robots that can be given instructions in spoken language need to able parse a natural utterance quickly, determine its meaning, generate goal representation from it, check whether the new conflicts with existing goals, and if acceptable, produce an action sequence achieve (ideally being sensitive goals). In this paper, we describe integrated robotic architecture above steps by translating incrementally simultaneously into formal logical description languages, which used both reason about...
Social-psychological processes in humans will play an important role long-term human-robot interactions. This study investigates people's perceptions of social presence robots during (relatively) short Findings indicate that males tend to think the robot as more human-like and accordingly show some evidence "social facilitation" on arithmetic task well socially desirable responding a survey administered by robot. In contrast, females saw machine-like, exhibited less robot's survey, were not...
We present the broad outlines of a roadmap toward human‐level artificial general intelligence (henceforth, AGI). begin by discussing AGI in general, adopting pragmatic goal for its attainment and necessary foundation characteristics requirements. An initial capability landscape will be presented, drawing on major themes from developmental psychology illuminated mathematical, physiological, information‐processing perspectives. The challenge identifying appropriate tasks environments measuring...
Recent proposals for how robots should talk to people when they give advice suggest that the same strategies humans employ with other are effective as well. However, evidence is exclusively based on people's observation of robot giving humans. Hence, it not clear whether results still apply actually participate in real interactions robots. We address this shortcoming a novel systematic mixed-methods study where we both survey-based subjective and brain-based objective measures (using...
Functional near infrared spectroscopy (NIRS) is a relatively new technique complimentary to EEG for the development of brain-computer interfaces (BCIs). NIRS-based systems detecting various cognitive and affective states such as mental emotional stress have already been demonstrated in range adaptive human-computer interaction (HCI) applications. However, before NIRS-BCIs can be used reliably realistic HCI settings, substantial challenges oncerning signal processing modeling must addressed....
Sex robots are gaining a remarkable amount of attention in current discussions about technology and the future human relationships. To help understand what kinds relationships people will have with these robots, empirical data people's views sex is needed. We report results first systematic survey that asks appropriateness value acceptable forms they can take, degree to which using them counts as sex. The show consistent difference uses for women men found be appropriate, less more inclined...
This article presents a new research area called interactive task learning (ITL), in which an agent actively tries to learn not just how perform better but the actual definition of through natural interaction with human instructor while attempting task. The authors provide analysis desiderata for ITL systems, review related work, and discussion possible application areas systems.
With robotics rapidly advancing, more effective human–robot interaction is increasingly needed to realize the full potential of robots for society. While spoken language must be part solution, our ability provide capabilities still very limited. In this article, based on report an interdisciplinary workshop convened by National Science Foundation, we identify key scientific and engineering advances enable with robotics. We make 25 recommendations, involving eight general themes: putting...
There is recent evidence that males and females view robots differently, from the way are conceptualized, to humans respond when they interact with them. In this paper, we further explore gender-based differences in human-robot interaction. Moreover, provide first available for sex-related reactions gendered synthetic voices either disembodied or physically embodied within a robot. Results indicate physical embodiment perceived entity gender may human characteristics pre-experimental...
We propose that any robots collaborate with, look after, or help humans-in short, social robots-must have moral competence. But what does competence consist of? offer a framework for attempts to be comprehensive in capturing capacities make humans morally competent and therefore represent candidates robot. posit human consists of four broad components: (1) A system norms the language concepts needed communicate about these norms; (2) cognition affect; (3) decision making action; (4)...
This paper describes the Brainput system, which learns to identify brain activity patterns occurring during multitasking. It provides a continuous, supplemental input stream an interactive human-robot uses this information modify its behavior better support demonstrates that we can use non-invasive methods detect signals coming from users naturally and effortlessly generate while using computer system. If used with care, additional lead systems respond appropriately changes in user's state....
In three studies we found further evidence for a previously discovered Human-Robot (HR) asymmetry in moral judgments: that people blame robots more inaction than action dilemma but humans the identical (where allows four persons to die and sacrifices one save four). Importantly, people's representation of "robot" making these decisions appears be mechanical robot. For when manipulated pictorial display verbally described robot, showed HR only judgments about mechanical-looking not humanoid...
Morality is a fundamentally human trait that permeates all levels of society, from basic etiquette and normative expectations social groups, to formalized legal principles upheld by societies. Hence, future interactive AI systems, in particular, cognitive systems on robots deployed settings, will have meet expectations, for otherwise these system risk causing harm. While the interest machine ethics has increased rapidly recent years, there are only very few current efforts community...
Soft robots promise an exciting design trajectory in the field of robotics and human-robot interaction (HRI), promising more adaptive, resilient movement within environments as well a safer, sensitive interface for objects or agents robot encounters. In particular, tactile HRI is critical dimension designers to consider, especially given onrush assistive companion into our society. this article, we propose surface important set ethical challenges soft meet. Tactile strongly suggests that...
Converging evidence from psychology, human factors, management and organizational science, other related fields suggests that humans working in teams employ shared mental models to represent use pertinent information about the task, equipment, team members, their roles. In particular, are used interact efficiently with members track progress terms of goals, subgoals, achieved planned states, as well team-related factors. Although much literature on has focused quantifying success can them...