Sequential Discrete Action Selection via Blocking Conditions and Resolutions

In this work, we introduce a strategy that frames the sequential action selection problem for robots in terms of resolving \textit{blocking conditions}, i.e., situations that impede progress on an action en route to a goal. This strategy allows a robot to make one-at-a-time decisions that take in pertinent contextual information and swiftly adapt and react to current situations. We present a first instantiation of this strategy that combines a state-transition graph and a zero-shot Large Language Model (LLM). The state-transition graph tracks which previously attempted actions are currently blocked and which candidate actions may resolve existing blocking conditions. This information from the state-transition graph is used to automatically generate a prompt for the LLM, which then uses the given context and set of possible actions to select a single action to try next. This selection process is iterative, with each chosen and executed action further refining the state-transition graph, continuing until the agent either fulfills the goal or encounters a termination condition. We demonstrate the effectiveness of our approach by comparing it to various LLM and traditional task-planning methods in a testbed of simulation experiments. We discuss the implications of our work based on our results.

REACT: Two Datasets for Analyzing Both Human Reactions and Evaluative Feedback to Robots Over Time

Recent work in Human-Robot Interaction (HRI) has shown that robots can leverage implicit communicative signals from users to understand how they are being perceived during interactions. For example, these signals can be gaze patterns, facial expressions, or body motions that reflect internal human states. To facilitate future research in this direction, we contribute the REACT database, a collection of two datasets of human-robot interactions that display users' natural reactions to robots during a collaborative game and a photography scenario. Further, we analyze the datasets to show that interaction history is an important factor that can influence human reactions to robots. As a result, we believe that future models for interpreting implicit feedback in HRI should explicitly account for this history. REACT opens up doors to this possibility in the future.

That's Mine! Learning Ownership Relations and Norms for Robots

The ability for autonomous agents to learn and conform to human norms is crucial for their safety and effectiveness in social environments. While recent work has led to frameworks for the representation and inference of simple social rules, research into norm learning remains at an exploratory stage. Here, we present a robotic system capable of representing, learning, and inferring ownership relations and norms. Ownership is represented as a graph of probabilistic relations between objects and their owners, along with a database of predicate-based norms that constrain the actions permissible on owned objects. To learn these norms and relations, our system integrates (i) a novel incremental norm learning algorithm capable of both one-shot learning and induction from specific examples, (ii) Bayesian inference of ownership relations in response to apparent rule violations, and (iii) percept-based prediction of an object's likely owners. Through a series of simulated and real-world experiments, we demonstrate the competence and flexibility of the system in performing object manipulation tasks that require a variety of norms to be followed, laying the groundwork for future research into the acquisition and application of social norms.

How to be Helpful? Implementing Supportive Behaviors for Human-Robot Collaboration

The field of Human-Robot Collaboration (HRC) has seen a considerable amount of progress in the recent years. Although genuinely collaborative platforms are far from being deployed in real-world scenarios, advances in control and perception algorithms have progressively popularized robots in manufacturing settings, where they work side by side with human peers to achieve shared tasks. Unfortunately, little progress has been made toward the development of systems that are proactive in their collaboration, and autonomously take care of some of the chores that compose most of the collaboration tasks. In this work, we present a collaborative system capable of assisting the human partner with a variety of supportive behaviors in spite of its limited perceptual and manipulation capabilities and incomplete model of the task. Our framework leverages information from a high-level, hierarchical model of the task. The model, that is shared between the human and robot, enables transparent synchronization between the peers and understanding of each other's plan. More precisely, we derive a partially observable Markov model from the high-level task representation. We then use an online solver to compute a robot policy, that is robust to unexpected observations such as inaccuracies of perception, failures in object manipulations, as well as discovers hidden user preferences. We demonstrate that the system is capable of robustly providing support to the human in a furniture construction task.