Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots

Assistive robots interact with humans and must adapt to different users' preferences to be effective. An easy and effective technique to learn non-expert users' preferences is through rankings of robot behaviors, for example, robot movement trajectories or gestures. Existing techniques focus on generating trajectories for users to rank that maximize the outcome of the preference learning process. However, the generated trajectories do not appear to reflect the user's preference over repeated interactions. In this work, we design an algorithm to generate trajectories for users to rank that we call Covariance Matrix Adaptation Evolution Strategies with Information Gain (CMA-ES-IG). CMA-ES-IG prioritizes the user's experience of the preference learning process. We show that users find our algorithm more intuitive and easier to use than previous approaches across both physical and social robot tasks. This project's code is hosted at github.com/interaction-lab/CMA-ES-IG

Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity

The wider application of end-to-end learning methods to embodied decision-making domains remains bottlenecked by their reliance on a superabundance of training data representative of the target domain. Meta-reinforcement learning (meta-RL) approaches abandon the aim of zero-shot generalization--the goal of standard reinforcement learning (RL)--in favor of few-shot adaptation, and thus hold promise for bridging larger generalization gaps. While learning this meta-level adaptive behavior still requires substantial data, efficient environment simulators approaching real-world complexity are growing in prevalence. Even so, hand-designing sufficiently diverse and numerous simulated training tasks for these complex domains is prohibitively labor-intensive. Domain randomization (DR) and procedural generation (PG), offered as solutions to this problem, require simulators to possess carefully-defined parameters which directly translate to meaningful task diversity--a similarly prohibitive assumption. In this work, we present DIVA, an evolutionary approach for generating diverse training tasks in such complex, open-ended simulators. Like unsupervised environment design (UED) methods, DIVA can be applied to arbitrary parameterizations, but can additionally incorporate realistically-available domain knowledge--thus inheriting the flexibility and generality of UED, and the supervised structure embedded in well-designed simulators exploited by DR and PG. Our empirical results showcase DIVA's unique ability to overcome complex parameterizations and successfully train adaptive agent behavior, far outperforming competitive baselines from prior literature. These findings highlight the potential of such semi-supervised environment design (SSED) approaches, of which DIVA is the first humble constituent, to enable training in realistic simulated domains, and produce more robust and capable adaptive agents.

Algorithmic Scenario Generation as Quality Diversity Optimization

The increasing complexity of robots and autonomous agents that interact with people highlights the critical need for approaches that systematically test them before deployment. This review paper presents a general framework for solving this problem, describes the insights that we have gained from working on each component of the framework, and shows how integrating these components leads to the discovery of a diverse range of realistic and challenging scenarios that reveal previously unknown failures in deployed robotic systems interacting with people.

GPT-Fabric: Folding and Smoothing Fabric by Leveraging Pre-Trained Foundation Models

Fabric manipulation has applications in folding blankets, handling patient clothing, and protecting items with covers. It is challenging for robots to perform fabric manipulation since fabrics have infinite-dimensional configuration spaces, complex dynamics, and may be in folded or crumpled configurations with severe self-occlusions. Prior work on robotic fabric manipulation relies either on heavily engineered setups or learning-based approaches that create and train on robot-fabric interaction data. In this paper, we propose GPT-Fabric for the canonical tasks of fabric folding and smoothing, where GPT directly outputs an action informing a robot where to grasp and pull a fabric. We perform extensive experiments in simulation to test GPT-Fabric against prior state of the art methods for folding and smoothing. We obtain comparable or better performance to most methods even without explicitly training on a fabric-specific dataset (i.e., zero-shot manipulation). Furthermore, we apply GPT-Fabric in physical experiments over 12 folding and 10 smoothing rollouts. Our results suggest that GPT-Fabric is a promising approach for high-precision fabric manipulation tasks.

Designing Robot Identity: The Role of Voice, Clothing, and Task on Robot Gender Perception

Perceptions of gender are a significant aspect of human-human interaction, and gender has wide-reaching social implications for robots deployed in contexts where they are expected to interact with humans. This work explored two flexible modalities for communicating gender in robots--voice and appearance--and we studied their individual and combined influences on a robot's perceived gender. We evaluated the perception of a robot's gender through three video-based studies. First, we conducted a study (n=65) on the gender perception of robot voices by varying speaker identity and pitch. Second, we conducted a study (n=93) on the gender perception of robot clothing designed for two different tasks. Finally, building on the results of the first two studies, we completed a large integrative video-based study (n=273) involving two human-robot interaction tasks. We found that voice and clothing can be used to reliably establish a robot's perceived gender, and that combining these two modalities can have different effects on the robot's perceived gender. Taken together, these results inform the design of robot voices and clothing as individual and interacting components in the perceptions of robot gender.

Using Causal Trees to Estimate Personalized Task Difficulty in Post-Stroke Individuals

Adaptive training programs are crucial for recovery post stroke. However, developing programs that automatically adapt depends on quantifying how difficult a task is for a specific individual at a particular stage of their recovery. In this work, we propose a method that automatically generates regions of different task difficulty levels based on an individual's performance. We show that this technique explains the variance in user performance for a reaching task better than previous approaches to estimating task difficulty.

Guidance Graph Optimization for Lifelong Multi-Agent Path Finding

We study how to use guidance to improve the throughput of lifelong Multi-Agent Path Finding (MAPF). Previous studies have demonstrated that while incorporating guidance, such as highways, can accelerate MAPF algorithms, this often results in a trade-off with solution quality. In addition, how to generate good guidance automatically remains largely unexplored, with current methods falling short of surpassing manually designed ones. In this work, we introduce the directed guidance graph as a versatile representation of guidance for lifelong MAPF, framing Guidance Graph Optimization (GGO) as the task of optimizing its edge weights. We present two GGO algorithms to automatically generate guidance for arbitrary lifelong MAPF algorithms and maps. The first method directly solves GGO by employing CMA-ES, a black-box optimization algorithm. The second method, PIU, optimizes an update model capable of generating guidance, demonstrating the ability to transfer optimized guidance graphs to larger maps with similar layouts. Empirically, we show that (1) our guidance graphs improve the throughput of three representative lifelong MAPF algorithms in four benchmark maps, and (2) our update model can generate guidance graphs for as large as $93 \times 91$ maps and as many as 3000 agents.

Singing the Body Electric: The Impact of Robot Embodiment on User Expectations

Users develop mental models of robots to conceptualize what kind of interactions they can have with those robots. The conceptualizations are often formed before interactions with the robot and are based only on observing the robot's physical design. As a result, understanding conceptualizations formed from physical design is necessary to understand how users intend to interact with the robot. We propose to use multimodal features of robot embodiments to predict what kinds of expectations users will have about a given robot's social and physical capabilities. We show that using such features provides information about general mental models of the robots that generalize across socially interactive robots. We describe how these models can be incorporated into interaction design and physical design for researchers working with socially interactive robots.

A metric for characterizing the arm nonuse workspace in poststroke individuals using a robot arm

An over-reliance on the less-affected limb for functional tasks at the expense of the paretic limb and in spite of recovered capacity is an often-observed phenomenon in survivors of hemispheric stroke. The difference between capacity for use and actual spontaneous use is referred to as arm nonuse. Obtaining an ecologically valid evaluation of arm nonuse is challenging because it requires the observation of spontaneous arm choice for different tasks, which can easily be influenced by instructions, presumed expectations, and awareness that one is being tested. To better quantify arm nonuse, we developed the Bimanual Arm Reaching Test with a Robot (BARTR) for quantitatively assessing arm nonuse in chronic stroke survivors. The BARTR is an instrument that utilizes a robot arm as a means of remote and unbiased data collection of nuanced spatial data for clinical evaluations of arm nonuse. This approach shows promise for determining the efficacy of interventions designed to reduce paretic arm nonuse and enhance functional recovery after stroke. We show that the BARTR satisfies the criteria of an appropriate metric for neurorehabilitative contexts: it is valid, reliable, and simple to use.

The RoSiD Tool: Empowering Users to Design Multimodal Signals for Human-Robot Collaboration

Robots that cooperate with humans must be effective at communicating with them. However, people have varied preferences for communication based on many contextual factors, such as culture, environment, and past experience. To communicate effectively, robots must take those factors into consideration. In this work, we present the Robot Signal Design (RoSiD) tool to empower people to easily self-specify communicative preferences for collaborative robots. We show through a participatory design study that the RoSiD tool enables users to create signals that align with their communicative preferences, and we illuminate how this tool can be further improved.