Shoichi Hasegawa

Saki Hashimoto, Shoichi Hasegawa, Tomochika Ishikawa et al.

Robots operating in domestic and office environments must understand object ownership to correctly execute instructions such as ``Bring me my cup.'' However, ownership cannot be reliably inferred from visual features alone. To address this gap, we propose Active Ownership Learning (ActOwL), a framework that enables robots to actively generate and ask ownership-related questions to users. ActOwL employs a probabilistic generative model to select questions that maximize information gain, thereby acquiring ownership knowledge efficiently to improve learning efficiency. Additionally, by leveraging commonsense knowledge from Large Language Models (LLM), objects are pre-classified as either shared or owned, and only owned objects are targeted for questioning. Through experiments in a simulated home environment and a real-world laboratory setting, ActOwL achieved significantly higher ownership clustering accuracy with fewer questions than baseline methods. These findings demonstrate the effectiveness of combining active inference with LLM-guided commonsense reasoning, advancing the capability of robots to acquire ownership knowledge for practical and socially appropriate task execution.

Kento Murata, Shoichi Hasegawa, Tomochika Ishikawa et al.

It is crucial to efficiently execute instructions such as "Find an apple and a banana" or "Get ready for a field trip," which require searching for multiple objects or understanding context-dependent commands. This study addresses the challenging problem of determining which robot should be assigned to which part of a task when each robot possesses different situational on-site knowledge-specifically, spatial concepts learned from the area designated to it by the user. We propose a task planning framework that leverages large language models (LLMs) and spatial concepts to decompose natural language instructions into subtasks and allocate them to multiple robots. We designed a novel few-shot prompting strategy that enables LLMs to infer required objects from ambiguous commands and decompose them into appropriate subtasks. In our experiments, the proposed method achieved 47/50 successful assignments, outperforming random (28/50) and commonsense-based assignment (26/50). Furthermore, we conducted qualitative evaluations using two actual mobile manipulators. The results demonstrated that our framework could handle instructions, including those involving ad hoc categories such as "Get ready for a field trip," by successfully performing task decomposition, assignment, sequential planning, and execution.

Alfonso Balandra, Shoichi Hasegawa

We want to understand the human capabilities to perceive amplitude similarities between a haptic and an audio signal. So, four psychophysical experiments were performed. Three of them measured the asynchrony JND (Just Noticeable Difference) at the signals' attack, release and decay, while the forth experiment measured the amplitude decrease on the middle of the signal. All the experiments used a combination of the constant stimulus and staircase methods to present two stimuli, while the participants' (N=12) task was to identify which of the two stimuli was synchronized. The audiotactile stimulus was defined using an stereo audio signal with an ADSR (Attack Decay Sustain Release) envelope. The partial results reveal JNDs for temporal asynchrony of: 54ms for attack, 265ms for decay and 57ms for release. Also the results reveal an amplitude decrease JND of 25\%. Although for decay the results were to disperse, therefore we suspect that the participants were not able to the changes on the haptic signal.