EL3DD: Extended Latent 3D Diffusion for Language Conditioned Multitask Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bode, Jonas, Memmesheimer, Raphael, Behnke, Sven
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913063620313088
author Bode, Jonas
Memmesheimer, Raphael
Behnke, Sven
author_facet Bode, Jonas
Memmesheimer, Raphael
Behnke, Sven
contents Acting in human environments is a crucial capability for general-purpose robots, necessitating a robust understanding of natural language and its application to physical tasks. This paper seeks to harness the capabilities of diffusion models within a visuomotor policy framework that merges visual and textual inputs to generate precise robotic trajectories. By employing reference demonstrations during training, the model learns to execute manipulation tasks specified through textual commands within the robot's immediate environment. The proposed research aims to extend an existing model by leveraging improved embeddings, and adapting techniques from diffusion models for image generation. We evaluate our methods on the CALVIN dataset, proving enhanced performance on various manipulation tasks and an increased long-horizon success rate when multiple tasks are executed in sequence. Our approach reinforces the usefulness of diffusion models and contributes towards general multitask manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EL3DD: Extended Latent 3D Diffusion for Language Conditioned Multitask Manipulation
Bode, Jonas
Memmesheimer, Raphael
Behnke, Sven
Robotics
Artificial Intelligence
Machine Learning
Acting in human environments is a crucial capability for general-purpose robots, necessitating a robust understanding of natural language and its application to physical tasks. This paper seeks to harness the capabilities of diffusion models within a visuomotor policy framework that merges visual and textual inputs to generate precise robotic trajectories. By employing reference demonstrations during training, the model learns to execute manipulation tasks specified through textual commands within the robot's immediate environment. The proposed research aims to extend an existing model by leveraging improved embeddings, and adapting techniques from diffusion models for image generation. We evaluate our methods on the CALVIN dataset, proving enhanced performance on various manipulation tasks and an increased long-horizon success rate when multiple tasks are executed in sequence. Our approach reinforces the usefulness of diffusion models and contributes towards general multitask manipulation.
title EL3DD: Extended Latent 3D Diffusion for Language Conditioned Multitask Manipulation
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2511.13312