Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Ruoxuan, Hu, Di, Ma, Wenke, Li, Xuelong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914987712184320
author Feng, Ruoxuan
Hu, Di
Ma, Wenke
Li, Xuelong
author_facet Feng, Ruoxuan
Hu, Di
Ma, Wenke
Li, Xuelong
contents Humans possess a remarkable talent for flexibly alternating to different senses when interacting with the environment. Picture a chef skillfully gauging the timing of ingredient additions and controlling the heat according to the colors, sounds, and aromas, seamlessly navigating through every stage of the complex cooking process. This ability is founded upon a thorough comprehension of task stages, as achieving the sub-goal within each stage can necessitate the utilization of different senses. In order to endow robots with similar ability, we incorporate the task stages divided by sub-goals into the imitation learning process to accordingly guide dynamic multi-sensory fusion. We propose MS-Bot, a stage-guided dynamic multi-sensory fusion method with coarse-to-fine stage understanding, which dynamically adjusts the priority of modalities based on the fine-grained state within the predicted current stage. We train a robot system equipped with visual, auditory, and tactile sensors to accomplish challenging robotic manipulation tasks: pouring and peg insertion with keyway. Experimental results indicate that our approach enables more effective and explainable dynamic fusion, aligning more closely with the human fusion process than existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2408_01366
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation
Feng, Ruoxuan
Hu, Di
Ma, Wenke
Li, Xuelong
Robotics
Computer Vision and Pattern Recognition
Humans possess a remarkable talent for flexibly alternating to different senses when interacting with the environment. Picture a chef skillfully gauging the timing of ingredient additions and controlling the heat according to the colors, sounds, and aromas, seamlessly navigating through every stage of the complex cooking process. This ability is founded upon a thorough comprehension of task stages, as achieving the sub-goal within each stage can necessitate the utilization of different senses. In order to endow robots with similar ability, we incorporate the task stages divided by sub-goals into the imitation learning process to accordingly guide dynamic multi-sensory fusion. We propose MS-Bot, a stage-guided dynamic multi-sensory fusion method with coarse-to-fine stage understanding, which dynamically adjusts the priority of modalities based on the fine-grained state within the predicted current stage. We train a robot system equipped with visual, auditory, and tactile sensors to accomplish challenging robotic manipulation tasks: pouring and peg insertion with keyway. Experimental results indicate that our approach enables more effective and explainable dynamic fusion, aligning more closely with the human fusion process than existing methods.
title Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.01366