arXiv subjects

Iolanda Leite

Publications and source records attributed to Iolanda Leite.

At least 19 recordsLinked to original sources

arXiv2026

GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes

Robots operating in human environments need memories that capture not only what objects exist and where, but also how people use them over time and how individual interactions compose into goal-directed activities. Existing 4D scene graphs preserve object and place histories but omit activity structure, whereas activity representations are either not grounded in persistent 3D scenes or rely on externally provided event boundaries and object associations. We present GESTO (Grounded Event and Spatio-Temporal memOry), a spatio-temporal memory that couples a persistent 4D scene graph with a two-level hierarchy of atomic human--object interactions and goal-driven events. From an RGB-D observation stream, GESTO automatically extracts timestamped interactions, grounds them to persistent scene entities, groups them into events, and uses event context to refine uncertain object associations. A relation-aware tool-calling agent queries the resulting memory for activity-centric spatio-temporal reasoning. We evaluate GESTO on the reproducible text, binary, and time categories of an existing benchmark, together with 40 new Space2Event and Event2Space queries. GESTO achieves scores of 0.71, 0.75, and 0.70 on the standard categories, approaching a method supplied with ground-truth event and object grounding, while substantially outperforming the same reasoning framework when these inputs are removed. It further achieves 0.73 and 0.75 on Space2Event and Event2Space queries. Ablations show that hierarchical event structure and context-aware grounding refinement provide complementary benefits, supporting activity-grounded hierarchical memory for retrospective reasoning in dynamic human environments.

cs.CV↗

arXiv2026

Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution

Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and \emph{``Flat''} RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4\% vs 51.5\% win rate, $p=0.103$) while both significantly outperform Flat RL trained without skill decomposition. A user study ($n=15$) reveals that 60\% of participants perceive LLM+RL agents as the most human-like ($p=0.027$), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

cs.LG↗

arXiv2026

MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue

Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing (1) a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry, and (2) a two-stage grounding pipeline that explicitly resolves conversational ambiguity before visual localization. The benchmark includes over 4,200 manually verified referring expressions spanning full, partitive, and pronominal types. Our contextual rewriting approach improves grounding performance by 11-22 percentage points on average, with a pure detector (GroundingDINO) reaching 56.7% on pronominals after rewriting, nearly double the best end-to-end baseline. Results demonstrate that decoupling linguistic reasoning from visual perception is more effective than end-to-end approaches for conversational grounding.

cs.CV↗

arXiv2026

A Pairwise Human-Human Interaction Detection and Recognition Framework for Mobile Service Robots

Autonomous mobile service robots, such as lawnmowers or cleaning robots, operating in human-populated environments need to reason about human-human interactions to support safe and socially aware navigation. For such systems, interaction understanding is not primarily a fine-grained recognition problem, but a perception problem under limited sensing quality and computational resources. Many existing approaches focus on holistic group activity recognition, often relying on complex and computationally expensive models that are not well suited for mobile robotic platforms. In this work, we argue that pairwise human interactions constitute a minimal yet sufficient perceptual unit for robot-centric social understanding. We study the problem of identifying interacting person pairs and classifying coarse-grained interaction behaviors sufficient for downstream group-level reasoning and robot decision-making. To this end, we adopt a two-stage framework in which candidate interacting pairs are first identified using lightweight geometric and motion cues, and interaction types are subsequently classified using a relation network. We evaluate the proposed approach on the JRDB dataset, where it achieves competitive performance with reduced computational cost and model size compared to appearance-based methods. Additional experiments on the Collective Activity Dataset (CAD) and zero-shot evaluation on a lawnmower-collected dataset further demonstrate the generalizability of the proposed framework. These results suggest that simple geometric and motion cues provide a practical and efficient basis for interaction-aware perception in mobile service robots. Code is released.

cs.RO↗

arXiv2025

Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots

Understanding how people interact with their surroundings and each other is essential for enabling robots to act in socially compliant and context-aware ways. While 3D Scene Graphs have emerged as a powerful semantic representation for scene understanding, existing approaches largely ignore humans in the scene, also due to the lack of annotated human-environment relationships. Moreover, existing methods typically capture only open-vocabulary relations from single image frames, which limits their ability to model long-range interactions beyond the observed content. We introduce Social 3D Scene Graphs, an augmented 3D Scene Graph representation that captures humans, their attributes, activities and relationships in the environment, both local and remote, using an open-vocabulary framework. Furthermore, we introduce a new benchmark consisting of synthetic environments with comprehensive human-scene relationship annotations and diverse types of queries for evaluating social scene understanding in 3D. The experiments demonstrate that our representation improves human activity prediction and reasoning about human-environment relations, paving the way toward socially intelligent robots.

cs.CV↗

arXiv2025

Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games

Reinforcement Learning (RL) in games has gained significant momentum in recent years, enabling the creation of different agent behaviors that can transform a player's gaming experience. However, deploying RL agents in production environments presents two key challenges: (1) designing an effective reward function typically requires an RL expert, and (2) when a game's content or mechanics are modified, previously tuned reward weights may no longer be optimal. Towards the latter challenge, we propose an automated approach for iteratively fine-tuning an RL agent's reward function weights, based on a user-defined language based behavioral goal. A Language Model (LM) proposes updated weights at each iteration based on this target behavior and a summary of performance statistics from prior training rounds. This closed-loop process allows the LM to self-correct and refine its output over time, producing increasingly aligned behavior without the need for manual reward engineering. We evaluate our approach in a racing task and show that it consistently improves agent performance across iterations. The LM-guided agents show a significant increase in performance from $9\%$ to $74\%$ success rate in just one iteration. We compare our LM-guided tuning against a human expert's manual weight design in the racing task: by the final iteration, the LM-tuned agent achieved an $80\%$ success rate, and completed laps in an average of $855$ time steps, a competitive performance against the expert-tuned agent's peak $94\%$ success, and $850$ time steps.

cs.AI↗

arXiv2025

FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions

Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user preferences while still being able to perform the original task. However, collecting preferences for the adaptation process in robotics is often challenging and time-consuming. In this work we explore the adaptation of pre-trained robots in the low-preference-data regime. We show that, in this regime, recent adaptation approaches suffer from catastrophic reward forgetting (CRF), where the updated reward model overfits to the new preferences, leading the agent to become unable to perform the original task. To mitigate CRF, we propose to enhance the original reward model with a small number of parameters (low-rank matrices) responsible for modeling the preference adaptation. Our evaluation shows that our method can efficiently and effectively adjust robotic behavior to human preferences across simulation benchmark tasks and multiple real-world robotic tasks.

cs.RO↗

arXiv2025

Expectations, Explanations, and Embodiment: Attempts at Robot Failure Recovery

Expectations critically shape how people form judgments about robots, influencing whether they view failures as minor technical glitches or deal-breaking flaws. This work explores how high and low expectations, induced through brief video priming, affect user perceptions of robot failures and the utility of explanations in HRI. We conducted two online studies ($N=600$ total participants); each replicated two robots with different embodiments, Furhat and Pepper. In our first study, grounded in expectation theory, participants were divided into two groups, one primed with positive and the other with negative expectations regarding the robot's performance, establishing distinct expectation frameworks. This validation study aimed to verify whether the videos could reliably establish low and high-expectation profiles. In the second study, participants were primed using the validated videos and then viewed a new scenario in which the robot failed at a task. Half viewed a version where the robot explained its failure, while the other half received no explanation. We found that explanations significantly improved user perceptions of Furhat, especially when participants were primed to have lower expectations. Explanations boosted satisfaction and enhanced the robot's perceived expressiveness, indicating that effectively communicating the cause of errors can help repair user trust. By contrast, Pepper's explanations produced minimal impact on user attitudes, suggesting that a robot's embodiment and style of interaction could determine whether explanations can successfully offset negative impressions. Together, these findings underscore the need to consider users' expectations when tailoring explanation strategies in HRI. When expectations are initially low, a cogent explanation can make the difference between dismissing a failure and appreciating the robot's transparency and effort to communicate.

cs.RO↗

arXiv2025

Ice-Breakers, Turn-Takers and Fun-Makers: Exploring Robots for Groups with Teenagers

Successful, enjoyable group interactions are important in public and personal contexts, especially for teenagers whose peer groups are important for self-identity and self-esteem. Social robots seemingly have the potential to positively shape group interactions, but it seems difficult to effect such impact by designing robot behaviors solely based on related (human interaction) literature. In this article, we take a user-centered approach to explore how teenagers envisage a social robot "group assistant". We engaged 16 teenagers in focus groups, interviews, and robot testing to capture their views and reflections about robots for groups. Over the course of a two-week summer school, participants co-designed the action space for such a robot and experienced working with/wizarding it for 10+ hours. This experience further altered and deepened their insights into using robots as group assistants. We report results regarding teenagers' views on the applicability and use of a robot group assistant, how these expectations evolved throughout the study, and their repeat interactions with the robot. Our results indicate that each group moves on a spectrum of need for the robot, reflected in use of the robot more (or less) for ice-breaking, turn-taking, and fun-making as the situation demanded.

cs.RO↗

arXiv2025

BT-ACTION: A Test-Driven Approach for Modular Understanding of User Instruction Leveraging Behaviour Trees and LLMs

Natural language instructions are often abstract and complex, requiring robots to execute multiple subtasks even for seemingly simple queries. For example, when a user asks a robot to prepare avocado toast, the task involves several sequential steps. Moreover, such instructions can be ambiguous or infeasible for the robot or may exceed the robot's existing knowledge. While Large Language Models (LLMs) offer strong language reasoning capabilities to handle these challenges, effectively integrating them into robotic systems remains a key challenge. To address this, we propose BT-ACTION, a test-driven approach that combines the modular structure of Behavior Trees (BT) with LLMs to generate coherent sequences of robot actions for following complex user instructions, specifically in the context of preparing recipes in a kitchen-assistance setting. We evaluated BT-ACTION in a comprehensive user study with 45 participants, comparing its performance to direct LLM prompting. Results demonstrate that the modular design of BT-ACTION helped the robot make fewer mistakes and increased user trust, and participants showed a significant preference for the robot leveraging BT-ACTION. The code is publicly available at https://github.com/1Eggbert7/BT_LLM.

cs.RO↗

arXiv2025

Let's move on: Topic Change in Robot-Facilitated Group Discussions

Robot-moderated group discussions have the potential to facilitate engaging and productive interactions among human participants. Previous work on topic management in conversational agents has predominantly focused on human engagement and topic personalization, with the agent having an active role in the discussion. Also, studies have shown the usefulness of including robots in groups, yet further exploration is still needed for robots to learn when to change the topic while facilitating discussions. Accordingly, our work investigates the suitability of machine-learning models and audiovisual non-verbal features in predicting appropriate topic changes. We utilized interactions between a robot moderator and human participants, which we annotated and used for extracting acoustic and body language-related features. We provide a detailed analysis of the performance of machine learning approaches using sequential and non-sequential data with different sets of features. The results indicate promising performance in classifying inappropriate topic changes, outperforming rule-based approaches. Additionally, acoustic features exhibited comparable performance and robustness compared to the complete set of multimodal features. Our annotated data is publicly available at https://github.com/ghadj/topic-change-robot-discussions-data-2024.

cs.RO↗

arXiv2025

Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs

Long-term planning for robots operating in domestic environments poses unique challenges due to the interactions between humans, objects, and spaces. Recent advancements in trajectory planning have leveraged vision-language models (VLMs) to extract contextual information for robots operating in real-world environments. While these methods achieve satisfying performance, they do not explicitly model human activities. Such activities influence surrounding objects and reshape spatial constraints. This paper presents a novel approach to trajectory planning that integrates human preferences, activities, and spatial context through an enriched 3D scene graph (3DSG) representation. By incorporating activity-based relationships, our method captures the spatial impact of human actions, leading to more context-sensitive trajectory adaptation. Preliminary results demonstrate that our approach effectively assigns costs to spaces influenced by human activities, ensuring that the robot trajectory remains contextually appropriate and sensitive to the ongoing environment. This balance between task efficiency and social appropriateness enhances context-aware human-robot interactions in domestic settings. Future work includes implementing a full planning pipeline and conducting user studies to evaluate trajectory acceptability.

cs.RO↗

arXiv2025

The Impact of VR and 2D Interfaces on Human Feedback in Preference-Based Robot Learning

Aligning robot navigation with human preferences is essential for ensuring comfortable, and predictable robot movement in shared spaces. While preference-based learning methods, such as reinforcement learning from human feedback (RLHF), enable this alignment, the choice of the preference collection interface may influence the process. Traditional 2D interfaces provide structured views but lack spatial depth, whereas immersive VR offers richer perception, potentially affecting preference articulation. This study systematically examines how the interface modality impacts human preference collection and navigation policy alignment. We introduce a novel dataset of 2,325 human preference queries collected through both VR and 2D interfaces, revealing significant differences in user experience, preference consistency, and policy outcomes. Our findings highlight the trade-offs between immersion, perception, and preference reliability, emphasizing the importance of interface selection in preference-based robot learning. The dataset is available to support future research.

cs.HC↗

arXiv2025

Humans Coexist, So Must Embodied Artificial Agents

This paper introduces the concept of coexistence for embodied artificial agents and argues that it is a prerequisite for long-term, in-the-wild interaction with humans. Contemporary embodied artificial agents excel in static, predefined tasks but fall short in dynamic and long-term interactions with humans. On the other hand, humans can adapt and evolve continuously, exploiting the situated knowledge embedded in their environment and other agents, thus contributing to meaningful interactions. We take an interdisciplinary approach at different levels of organization, drawing from biology and design theory, to understand how human and non-human organisms foster entities that coexist within their specific environments. Finally, we propose key research directions for the artificial intelligence community to develop coexisting embodied agents, focusing on the principles, hardware and learning methods responsible for shaping them.

cs.LG↗

arXiv2025

What Can You Say to a Robot? Capability Communication Leads to More Natural Conversations

When encountering a robot in the wild, it is not inherently clear to human users what the robot's capabilities are. When encountering misunderstandings or problems in spoken interaction, robots often just apologize and move on, without additional effort to make sure the user understands what happened. We set out to compare the effect of two speech based capability communication strategies (proactive, reactive) to a robot without such a strategy, in regard to the user's rating of and their behavior during the interaction. For this, we conducted an in-person user study with 120 participants who had three speech-based interactions with a social robot in a restaurant setting. Our results suggest that users preferred the robot communicating its capabilities proactively and adjusted their behavior in those interactions, using a more conversational interaction style while also enjoying the interaction more.

cs.RO↗

arXiv2025

How do Humans take an Object from a Robot: Behavior changes observed in a User Study

To facilitate human-robot interaction and gain human trust, a robot should recognize and adapt to changes in human behavior. This work documents different human behaviors observed while taking objects from an interactive robot in an experimental study, categorized across two dimensions: pull force applied and handedness. We also present the changes observed in human behavior upon repeated interaction with the robot to take various objects.

cs.RO↗

arXiv2024

STREAK: Streaming Network for Continual Learning of Object Relocations under Household Context Drifts

In real-world settings, robots are expected to assist humans across diverse tasks and still continuously adapt to dynamic changes over time. For example, in domestic environments, robots can proactively help users by fetching needed objects based on learned routines, which they infer by observing how objects move over time. However, data from these interactions are inherently non-independent and non-identically distributed (non-i.i.d.), e.g., a robot assisting multiple users may encounter varying data distributions as individuals follow distinct habits. This creates a challenge: integrating new knowledge without catastrophic forgetting. To address this, we propose STREAK (Spatio Temporal RElocation with Adaptive Knowledge retention), a continual learning framework for real-world robotic learning. It leverages a streaming graph neural network with regularization and rehearsal techniques to mitigate context drifts while retaining past knowledge. Our method is time- and memory-efficient, enabling long-term learning without retraining on all past data, which becomes infeasible as data grows in real-world interactions. We evaluate STREAK on the task of incrementally predicting human routines over 50+ days across different households. Results show that it effectively prevents catastrophic forgetting while maintaining generalization, making it a scalable solution for long-term human-robot interactions.

cs.RO↗

arXiv2024

A Model-Agnostic Approach for Semantically Driven Disambiguation in Human-Robot Interaction

Ambiguities are inevitable in human-robot interaction, especially when a robot follows user instructions in a large, shared space. For example, if a user asks the robot to find an object in a home environment with underspecified instructions, the object could be in multiple locations depending on missing factors. For instance, a bowl might be in the kitchen cabinet or on the dining room table, depending on whether it is clean or dirty, full or empty, and the presence of other objects around it. Previous works on object search have assumed that the queried object is immediately visible to the robot or have predicted object locations using one-shot inferences, which are likely to fail for ambiguous or partially understood instructions. This paper focuses on these gaps and presents a novel model-agnostic approach leveraging semantically driven clarifications to enhance the robot's ability to locate queried objects in fewer attempts. Specifically, we leverage different knowledge embedding models, and when ambiguities arise, we propose an informative clarification method, which follows an iterative prediction process. The user experiment evaluation of our method shows that our approach is applicable to different custom semantic encoders as well as LLMs, and informative clarifications improve performances, enabling the robot to locate objects on its first attempts. The user experiment data is publicly available at https://github.com/IrmakDogan/ExpressionDataset.

cs.RO↗