Large language models (LLMs) have been shown to exhibit a wide range of capabilities, such as writing robot code from language commands -- enabling non-experts to direct robot behaviors, modify them based on feedback, or compose them to perform new tasks. However, these capabilities (driven by in-context learning) are limited to short-term interactions, where users' feedback remains relevant for only as long as it fits within the context size of the LLM, and can be forgotten over longer interactions. In this work, we investigate fine-tuning the robot code-writing LLMs, to remember their in-context interactions and improve their teachability i.e., how efficiently they adapt to human inputs (measured by average number of corrections before the user considers the task successful). Our key observation is that when human-robot interactions are viewed as a partially observable Markov decision process (in which human language inputs are observations, and robot code outputs are actions), then training an LLM to complete previous interactions is training a transition dynamics model -- that can be combined with classic robotics techniques such as model predictive control (MPC) to discover shorter paths to success. This gives rise to Language Model Predictive Control (LMPC), a framework that fine-tunes PaLM 2 to improve its teachability on 78 tasks across 5 robot embodiments -- improving non-expert teaching success rates of unseen tasks by 26.9% while reducing the average number of human corrections from 2.4 to 1.9. Experiments show that LMPC also produces strong meta-learners, improving the success rate of in-context learning new tasks on unseen robot embodiments and APIs by 31.5%. See videos, code, and demos at: https://robot-teaching.github.io/.

The physical design of a robot suggests expectations of that robot's functionality for human users and collaborators. When those expectations align with the true capabilities of the robot, interaction with the robot is enhanced. However, misalignment of those expectations can result in an unsatisfying interaction. This paper uses Mechanical Turk to evaluate user expectation through the use of design metaphors as applied to a wide range of robot embodiments. The first study (N=382) associates crowd-sourced design metaphors to different robot embodiments. The second study (N=803) assesses initial social expectations of robot embodiments. The final study (N=805) addresses the degree of abstraction of the design metaphors and the functional expectations projected on robot embodiments. Together, these results can guide robot designers toward aligning user expectations with true robot capabilities, facilitating positive human-robot interaction.

Infants with a variety of complications at or before birth are classified as being at risk for developmental delays (AR). As they grow older, they are followed by healthcare providers in an effort to discern whether they are on a typical or impaired developmental trajectory. Often, it is difficult to make an accurate determination early in infancy as infants with typical development (TD) display high variability in their developmental trajectories both in content and timing. Studies have shown that spontaneous movements have the potential to differentiate typical and atypical trajectories early in life using sensors and kinematic analysis systems. In this study, machine learning classification algorithms are used to take inertial movement from wearable sensors placed on an infant for a day and predict if the infant is AR or TD, thus further establishing the connection between early spontaneous movement and developmental trajectory.

Extended school absence during K-12 education can have anegative impact on both the educational and social development of a child. Mobile Remote Presence (MRP) can helpenable continued access to K-12 education for children withhealth challenges. However, most MRP platforms are targetedtowards adult users in domains such as the workplace.The importance of social interaction and engagement in K-12 education creates a unique set of needs and challenges foran MRP platform. In this work, we discuss the benefits ofMRP usage for K-12 education, ongoing challenges for MRPacross domains, and the requirements of an MRP platform forthe classroom.

This abstract describes the development of algorithms for personalized anxiety reduction feedback for use by a robot buddy interacting with a child about to receive intravenous therapy (an IV insertion). This three-phase study is currently being conducted; it consists of two data collections to determine domain-specific approaches, followed by the full study with personalized anxiety-reducing feedback. Participants receiving personalized feedback will be compared to participants with a non-personalized robot (to control for novelty) and a no robot condition (baseline control).

Socially assistive robotics (SAR) has the potential to combinethe massive replication and standardization of computertechnology with the benefits of learning in a social and tangible(hands-on) context. We are developing HRI methodsfor SAR systems designed to supplement the efforts of humanteachers to personalize education in the classroom. Thisabstract defines and proposes solutions to the computationalchallenges inherent in accomplishing differentiated and personalizededucation utilizing SAR in real-world classrooms. We aim to design robotic systems that are compelling, assistchildren in achieving educational goals, and mitigate developmentalchallenges in a classroom context. To do so, ourapproach must be deeply informed by the needs of our targetusers, children, at all stages of development, and mustadapt to a variety of special needs. In this abstract, we discussmotivation and computational methods for personalizedSAR systems for general, special needs, and mixed multichildeducation contexts. We focus on the personalizationand adaptation of curriculum, feedback, and robot character.

We present an approach for enabling in-home service robots to follow natural language commands from non-expert users, with a particular focus on spatial language understanding. Specifically, we propose an extension to the semantic field model of spatial prepositions that enables the representation of dynamic spatial relations involving paths. The relevance of the proposed methodology to interactive robot learning is discussed, and the paper concludes with a description of how we plan to integrate and evaluate our proposed model with end-users.

Developments in sophisticated mobile physiological sensors have presented many novel opportunities for monitoring coaching of individuals. In this work, we investigate the ability to utilize physiological data to recognize the state ofa user while exercising. We discuss recognition of user state using data suchas heart rate, respiration rate, and activity level. We also discuss the development of a motivational agent which utilizes the physiological data to help encourage a user during an exercise routine.

It has been demonstrated that people have a tendency to adapt both their linguistic representations and physical Communication is often required between agents as they actions in response to those they are interacting with, i.e., attempt to solve collaborative multi-agent tasks. This is they tend to formulate behavior and speech that will be particularly true in conditions in which an agent is working salient and sensible to a collaborating partner (Whittaker alongside a human--clearly, conventional electronic 2003). Collaboration in humans occurs via a process in communication is not feasible in this scenario; rather, these which people align their linguistic representations of the agents, including humans, must take advantage of physical environment allowing for more effective communicative communication in the shared context to confer necessary behavior. This alignment is achieved via a process in information. As an agent observes the actions of the others, which local alignment of environmental representations, it must modify its own behavior accordingly.