22 citations · 77 across the 18 of their papers we have counts for
9 papers · 1 filter
Daily Assistive View Control Learning of Low-Cost Low-Rigidity Robot via Large-Scale Vision-Language Model
Kento Kawaharazuka, Naoaki Kanazawa, Yoshiki Obinata +2
In this study, we develop a simple daily assistive robot that controls its own vision according to linguistic instructions. The robot performs several daily tasks such as recording…
Binary State Recognition by Robots using Visual Question Answering of Pre-Trained Vision-Language Model
Kento Kawaharazuka, Yoshiki Obinata, Naoaki Kanazawa +2
Recognition of the current state is indispensable for the operation of a robot. There are various states to be recognized, such as whether an elevator door is open or closed, wheth…
Semantic Scene Difference Detection in Daily Life Patroling by Mobile Robots using Pre-Trained Large-Scale Vision-Language Model
Yoshiki Obinata, Kento Kawaharazuka, Naoaki Kanazawa +7
It is important for daily life support robots to detect changes in their environment and perform tasks. In the field of anomaly detection in computer vision, probabilistic and deep…
Recognition of Heat-Induced Food State Changes by Time-Series Use of Vision-Language Model for Cooking Robot
Naoaki Kanazawa, Kento Kawaharazuka, Yoshiki Obinata +2
Cooking tasks are characterized by large changes in the state of the food, which is one of the major challenges in robot execution of cooking tasks. In particular, cooking using a…
A method for Selecting Scenes and Emotion-based Descriptions for a Robot's Diary
Aiko Ichikura, Kento Kawaharazuka, Yoshiki Obinata +2
In this study, we examined scene selection methods and emotion-based descriptions for a robot's daily diary. We proposed a scene selection method and an emotion description method…
Automatic Diary Generation System including Information on Joint Experiences between Humans and Robots
Aiko Ichikura, Kento Kawaharazuka, Yoshiki Obinata +3
In this study, we propose an automatic diary generation system that uses information from past joint experiences with the aim of increasing the favorability for robots through shar…
Foundation Model based Open Vocabulary Task Planning and Executive System for General Purpose Service Robots
Yoshiki Obinata, Naoaki Kanazawa, Kento Kawaharazuka +4
This paper describes a strategy for implementing a robotic system capable of performing General Purpose Service Robot (GPSR) tasks in robocup@home. The GPSR task is that a real rob…
VQA-based Robotic State Recognition Optimized with Genetic Algorithm
Kento Kawaharazuka, Yoshiki Obinata, Naoaki Kanazawa +2
State recognition of objects and environment in robots has been conducted in various ways. In most cases, this is executed by processing point clouds, learning images with annotati…
Robotic Applications of Pre-Trained Vision-Language Models to Various Recognition Behaviors
Kento Kawaharazuka, Yoshiki Obinata, Naoaki Kanazawa +2
In recent years, a number of models that learn the relations between vision and language from large datasets have been released. These models perform a variety of tasks, such as an…