Repeated human-robot interaction (HRI) requires proactively accounting for humans who continually adapt to evolving beliefs about the robot. Prior frameworks often treat encounters as isolated events, suffering cumulative task performance decay as human perception drifts, or maintain long-term influence through erratic, unpredictable behavior that erodes perceived human trust and relies on computationally unscalable formulations. To address these gaps, we introduce the Belief- Aware Influence and Trust (BAIT) controller. BAIT integrates a hierarchical particle filter, which infers both fast human strategic shifts and slow perceptual belief updates, with a belief-aware Model Predictive Path Integral planner. BAIT explicitly optimizes the trade-off between long-horizon influence and human trust, while enforcing immediate task performance as a strict constraint. Across simulations, a human-subject study, and a real-world GEM vehicle deployments in repeated lane-merging scenarios, BAIT achieves task performance comparable to baselines that optimize long-term influence through unpredictability while yielding significantly higher user trust. The video demonstrating our experiments is available at https://youtu.be/GsPfHRujzVs.

Learning from humans is challenging because people are imperfect teachers. When everyday humans show the robot a new task they want it to perform, humans inevitably make errors (e.g., inputting noisy actions) and provide suboptimal examples (e.g., overshooting the goal). Existing methods often learn by matching some or all of the human's behavior — but this approach is fundamentally limited because the demonstrations themselves are imperfect. In this work we advance offline imitation learning by enabling robots to extrapolate across nearby actions, instead of only considering what the human actually showed. We achieve this by hypothesizing that all of the human's demonstrations are trying to convey an underlying policy, while the noise and sub-optimality within their behaviors obfuscates the data and introduces unintentional complexity. To recover the underlying policy and learn what the human teacher meant, we introduce Counter-BC, a generalized version of behavior cloning. Counter-BC expands the dataset to include actions close to behaviors the human demonstrated (i.e., counterfactual actions that the human teacher could have intended, but did not actually show). During training Counter-BC autonomously modifies the human's demonstrations within this expanded region to reach a simplified policy that explains the underlying trends in the human's dataset. Theoretically, we prove that Counter-BC can extract a simple and similar-to-demonstration policy from imperfect data, multiple users, and teachers of varying skill levels. Empirically, we compare Counter-BC to state-of-the-art alternatives in settings with noisy demonstrations, standardized datasets, and real human teachers. Overall, we find that trying to extrapolate what the human teacher meant by considering nearby actions can lead to more proficient learning from humans. See videos of our work here: https://youtu.be/XaeOZWhTt68

Robot actions influence the decisions of nearby humans. Here influence refers to intentional change: robots influence humans when they shift the human's behavior in a way that helps the robot complete its task. Imagine an autonomous car trying to merge; by proactively nudging into the human's lane, the robot causes human drivers to yield and provide space. Influence is often necessary for seamless interaction. However, if influence is left unregulated and uncontrolled, robots will negatively impact the humans around them. Prior works have begun to address this problem by creating a variety of control algorithms that seek to influence humans. Although these methods are effective in the short-term, they fail to maintain influence over time as the human adapts to the robot's behaviors. In this paper we therefore present an optimization framework that enables robots to purposely regulate their influence over humans across both short-term and long-term interactions. Here the robot maintains its influence by reasoning over a dynamic human model which captures how the robot's current choices will impact the human's future behavior. Our resulting framework serves to unify current approaches: we demonstrate that state-of-the-art methods are simplifications of our underlying formalism. Our framework also provides a principled way to generate influential policies: in the best case the robot exactly solves our framework to find optimal, influential behavior. But when solving this optimization problem becomes impractical, designers can introduce their own simplifications to reach tractable approximations. We experimentally compare our unified framework to state-of-the-art baselines and ablations, and demonstrate across simulations and user studies that this framework is able to successfully influence humans over repeated interactions. See videos of our experiments here: https://youtu.be/nPekTUfUEbo

Today's robots attempt to learn new tasks by imitating human examples. These robots watch the human complete the task, and then try to match the actions taken by the human expert. However, this standard approach to visual imitation learning is fundamentally limited: the robot observes what the human does, but not why the human chooses those behaviors. Without understanding which features of the system or environment factor into the human's decisions, robot learners often misinterpret the human's examples. In practice, this results in causal confusion, inefficient learning, and robot policies that fail when the environment changes. We therefore propose a shift in perspective: instead of asking human teachers just to show what actions the robot should take, we also enable humans to intuitively indicate why they made those decisions. Under our paradigm human teachers attach markers to task-relevant objects and use natural language prompts to describe their state representation. Our proposed algorithm, CIVIL, leverages this augmented demonstration data to filter the robot's visual observations and extract a feature representation that aligns with the human teacher. CIVIL then applies these causal features to train a transformer-based policy that – when tested on the robot – is able to emulate human behaviors without being confused by visual distractors or irrelevant items. Our simulations and real-world experiments demonstrate that robots trained with CIVIL learn both what actions to take and why to take those actions, resulting in better performance than state-of-the-art baselines. From the human's perspective, our user study reveals that this new training paradigm actually reduces the total time required for the robot to learn the task, and also improves the robot's performance in previously unseen scenarios. See videos at our project website: https://civil2025.github.io

Imitation learning enables robots to learn new tasks from human examples. One fundamental limitation while learning from humans is causal confusion. Causal confusion occurs when the robot’s observations include both task-relevant and extraneous information: for instance, a robot’s camera might see not only the intended goal, but also clutter and changes in lighting within its environment. Because the robot does not know which aspects of its observations are important a priori, it often misinterprets the human’s examples and fails to learn the desired task. To address this issue, we highlight that — while the robot learner may not know what to focus on — the human teacher does. In this paper we propose that the human proactively marks key parts of their task with small, lightweight beacons. Under our framework (RECON) the human attaches these beacons to task-relevant objects before providing demonstrations: as the human shows examples of the task, beacons track the position of marked objects. We then harness this offline beacon data to train a task-relevant state embedding. Specifically, we embed the robot’s observations to a latent state that is correlated with the measured beacon readings: in practice, this causes the robot to autonomously filter out extraneous observations and make decisions based on features learned from the beacon data. Our simulations and a real robot experiment suggest that this framework for human-placed beacons mitigates causal confusion. Indeed, we find that using RECON significantly reduces the number of demonstrations needed to convey the task, lowering the overall time required for human teaching. See videos here: https://youtu.be/oy85xJvtLSU

We often assume that robots which collaborate with humans should behave in ways that are transparent (e.g., legible, explainable). These transparent robots intentionally choose actions that convey their internal state to nearby humans: for instance, a transparent robot might exaggerate its trajectory to indicate its goal. But while transparent behavior seems beneficial for human-robot interaction, is it actually optimal? In this paper we consider collaborative settings where the human and robot have the same objective, and the human is uncertain about the robot's type (i.e., the robot's internal state). We extend a recursive combination of Bayesian Nash equilibrium and the Bellman equation to solve for optimal robot policies. Interestingly, we discover that it is not always optimal for collaborative robots to be transparent; instead, human and robot teams can sometimes achieve higher rewards when the robot is opaque. In contrast to transparent robots, opaque robots select actions that withhold information from the human. Our analysis suggests that opaque behavior becomes optimal when either (a) human-robot interactions have a short time horizon or (b) users are slow to learn from the robot's actions. We extend this theoretical analysis to user studies across 43 total participants in both online and in-person settings. We find that -- during short interactions -- users reach higher rewards when working with opaque partners, and subjectively rate opaque robots as about equal to transparent robots. See videos of our experiments here: https://youtu.be/u8q1Z7WHUuI

Assistive robot arms can help humans by partially automating their desired tasks. Consider an adult with motor impairments controlling an assistive robot arm to eat dinner. The robot can reduce the number of human inputs - and how precise those inputs need to be - by recognizing what the human wants (e.g., a fork) and assisting for that task (e.g., moving towards the fork). Prior research has largely focused on learning the human's task and providing meaningful assistance. But as the robot learns and assists, we also need to ensure that the human understands the robot's intent (e.g., does the human know the robot is reaching for a fork?). In this paper, we study the effects of communicating learned assistance from the robot back to the human operator. We do not focus on the specific interfaces used for communication. Instead, we develop experimental and theoretical models of a) how communication changes the way humans interact with assistive robot arms, and b) how robots can harness these changes to better align with the human's intent. We first conduct online and in-person user studies where participants operate robots that provide partial assistance, and we measure how the human's inputs change with and without communication. With communication, we find that humans are more likely to intervene when the robot incorrectly predicts their intent, and more likely to release control when the robot correctly understands their task. We then use these findings to modify an established robot learning algorithm so that the robot can correctly interpret the human's inputs when communication is present. Our results from a second in-person user study suggest that this combination of communication and learning outperforms assistive systems that isolate either learning or communication. See videos here: https://youtu.be/BET9yuVTVU4

When autonomous vehicles (AVs) share the road with human drivers, the complexity of the interaction significantly increases. Both the AV and the human-driven car need to infer the behaviors of other road users to make their own decisions. In this paper, we study a scenario in which human-driven cars attempt to block AVs while the AVs aim to overtake human-driven cars. This setting plans for the worst-case scenario in which other agents are adversarial. Previous works have developed theoretical frameworks that enable robots to find an optimal and safe trajectory in an adversarial setting. In this paper, we explore three of these frameworks: Hamilton-Jacobi reachability, game-theoretic approaches, and reinforcement learning. We then construct the corresponding overtaken controllers and compare their performances. The robot needs to consider both collision avoidance and task realization. Therefore, the way it infers human behavior is crucial. Our results suggest that game-theoretic methods are able to find optimized and safe trajectories more successfully and faster than other approaches.

When humans interact with robots influence is inevitable. Consider an autonomous car driving near a human: the speed and steering of the autonomous car will affect how the human drives. Prior works have developed frameworks that enable robots to influence humans towards desired behaviors. But while these approaches are effective in the short-term (i.e., the first few human-robot interactions), here we explore long-term influence (i.e., repeated interactions between the same human and robot). Our central insight is that humans are dynamic: people adapt to robots, and behaviors which are influential now may fall short once the human learns to anticipate the robot's actions. With this insight, we experimentally demonstrate that a prevalent game-theoretic formalism for generating influential robot behaviors becomes less effective over repeated interactions. Next, we propose three modifications to Stackelberg games that make the robot's policy both influential and unpredictable. We finally test these modifications across simulations and user studies: our results suggest that robots which purposely make their actions harder to anticipate are better able to maintain influence over long-term interaction. See videos here: https://youtu.be/ydO83cgjZ2Q

Studio coursework that focuses on real-world problems and stakeholder collaboration is an integral component of interdisciplinary design education. In the wake of the COVID-19 pandemic and increased interest in flexible models of content delivery, we conceptualize the studio course as central to interdisciplinary undergraduate education. Leveraging the pandemic as an opportunity, we argue that changes to studio coursework have created new modalities for design education. By focusing on adaptive, iterative studio coursework during each year of the undergraduate degree, we allow for hybridization of undergraduate design coursework. We present an example of the studio-centred model in action at a large polytechnic university in the United States. Our results may be beneficial to educators and practitioners interested in anchoring undergraduate curricula within interdisciplinary studio work, and for ensuring that interdisciplinary studios are able to respond to the twenty-first-century life skills essential for producing competitive graduates on the global market. We present studio-centred coursework as a model for hybridizing design education. We emphasize collaboration and discovery as key skills to develop in undergraduates. We develop this model through: (1) collaborating with industry partners to determine problem spaces and mentor students; (2) building interdisciplinary teams of students and faculty and (3) hybridizing lecture-based disciplinary coursework. We anchor our results with three years of programme assessment data. By integrating faculty, students and industry partners within the studio-centred model, this study demonstrates how hybridized design-led education can equip students for interdisciplinary collaboration as they progress towards their career goals. Furthermore, we provide discussion on how these competencies are evaluated by stakeholders as desirable skills. Students’ overall positive responses to the studio-centred coursework are captured in our quantitative data. Stakeholder responses come via focus groups held once per semester. Using studio coursework to centre design curricula allows for increased hybridization of the curriculum, as students use studio courses and capstones to apply knowledge, develop projects and attain professional mentorship. Emphasis on societal impact guides students to emphasize the broader impacts of their designs. Using quantitative and qualitative data, we provide a model that integrates research and education in undergrad curricula using a studio-centred model.

Liquids sloshing around in vessels produce unique unmistakable tactile sensations of handling fluids in daily life, laboratory environments, and industrial contexts. Providing nuanced congruent tactile sensations would enrich interactions of handling fluids in virtual reality (VR). To this end, we introduce Geppetteau, a novel string-driven weight-shifting mechanism capable of providing a continuous spectrum of perceivable tactile sensations of handling virtual liquids in VR vessels. Geppetteau’s weight-shifting actuation system can be housed in 3D-printable shells, adapting to varying vessel shapes and sizes. A variety of different fluid behaviors can be felt using our haptic interface. In this work, Geppetteau assumes the shape of conical, spherical, cylindrical, and cuboid flasks, widening the range of augmentable shapes beyond the state-of-the-art of existing mechanical systems.

Project-based educational environment that focuses on real-world problems and crosssector collaboration instills students' learning pathways with the proficiency to move from the domain-specific to the domain-general knowledge. We conceptualize a project-based curriculum model as central to undergraduate education. Focusing on iterative design and development during each year of the undergraduate degree allows for further enrichment of the undergraduate curriculum. We present a case study of a project-based model in action within Virginia Tech, a large public polytechnic university in the United States. Working with seventy-five industry partners serving as project mentors and twenty-seven transdisciplinary faculty, we discuss methodology key to ensure student learning and project outcomes within this model, including embedding industry partners within project teams, developing transdisciplinary project teams, and encouraging just-in-time implementation of disciplinary knowledge.

This experience report presents an example of an industry-academic partnership between seventy-five industry partners and transdisciplinary faculty at a large polytechnic university. We examine how program stakeholders determined instructional needs, designed one-credit technical communication modules responsive to those needs, and collaborated with industry partners, faculty from multiple disciplines, and program administrators to embed these modules within the program's studio and capstone coursework. The experience report closes with implications for developing new coursework in technical communication.

Recent workforce disruptions highlight the need for just-in-time competency acquisition. Developing cyber-human tools that incorporate both human guidance and artificial intelligence may shorten learning and provide better career-upskilling pathways. Deconstructing degree programs to provide adaptive pathways of multi-modal micro-experiences offers greater flexibility. To implement such learning programming, the Calhoun Discovery Program (CDP) at Virginia Tech and its industry and non-profit partners are developing an adaptive education model based on Integrative Professional and Personal Competencies (IPPCs) for Industry 4.0. We argue that implementing whole-person-development-focused curricula that uses heterogeneous analytics and adaptive pathways can increase learners' mobility within current and future economies. With our partners, we have developed real-world applied problem solving experiences to prepare transdisciplinary learners to work collaboratively on Industry 4.0 applications promoting sustainable and equitable development. This paper defines IPPCs and elaborates how they are integrated in the CDP through Problem-based Learning Experiences (PBLE), research and just-in-time modules. We note program outcomes over the first two years or operations and the generalizable takeaways of IPPC-based learning. Next, we describe computer-assisted tools we will develop to help us standardize and scale this learning model and summarize what the learning cycle looks like in our model. We conclude by sketching prospects for scaling this approach to K-12, industry and other settings.

Current VR/AR systems are unable to reproduce the physical sensation of fluid vessels, due to the shifting nature of fluid motion. To this end, we introduce SWISH, an ungrounded mixed-reality interface, capable of affording the users a realistic haptic sensation of fluid behaviors in vessels. The chief mechanism behind SWISH is in the use of virtual reality tracking and motor actuation to actively relocate the center of gravity of a handheld vessel, emulating the moving center of gravity of a handheld vessel that contains fluid. In addition to solving challenges related to reliable and efficient motor actuation, our SWISH designs place an emphasis on reproducibility, scalability, and availability to the maker culture. Our virtual-to-physical coupling uses Nvidia Flex's Unity integration for virtual fluid dynamics with a 3D printed augmented vessel containing a motorized mechanical actuation system. To evaluate the effectiveness and perceptual efficacy of SWISH, we conduct a user study with 24 participants, 7 vessel actions, and 2 virtual fluid viscosities in a virtual reality environment. In all cases, the users on average reported that the SWISH bucket generates accurate tactile sensations for the fluid behavior. This opens the potential for multi-modal interactions with programmable fluids in virtual environments for chemistry education, worker training, and immersive entertainment.

Mixed-reality haptic devices introduce a gateway to otherwise intangible virtual content, creating a life-like immersive experience. Congruent haptic sensation requires faithful integration of visual stimuli and perceived tactile sensation. Unfortunately, current commercial mixed-reality systems are unable to reproduce the physical sensation of fluid vessels, due to the shifting nature of fluid motion. To this end, we introduce SWISH, a novel type of ungrounded mixed-reality system, capable of affording the users a realistic haptic sensation of fluid behavior. We also present solutions to prominent challenges of rendering haptic fluid behavior, especially in coordinate translation and virtual adaptation to physical limitation. Our virtual-to-physical coupling uses Nvidia Flex's Unreal Engine integration, wirelessly controlling a motorized mechanical actuation system housed in a plastic "vessel''. In this paper we discuss the current state of SWISH and present results from our preliminary user study, followed by a description of our future planned phases.