LIAM: Multimodal Transformer for Language Instructions, Images, Actions and Semantic Maps

2025/03/15 by Wang, Yihao, Memmesheimer, Raphael, Behnke, Sven
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2503.12230

Abstract

The availability of large language models and open-vocabulary object perception methods enables more flexibility for domestic service robots. The large variability of domestic tasks can be addressed without implementing each task individually by providing the robot with a task description along with appropriate environment information. In this work, we propose LIAM - an end-to-end model that predicts action transcripts based on language, image, action, and map inputs. Language and image inputs are encoded with a CLIP backbone, for which we designed two pre-training tasks to fine-tune its weights and pre-align the latent spaces. We evaluate our method on the ALFRED dataset, a simulator-generated benchmark for domestic tasks. Our results demonstrate the importance of pre-aligning embedding spaces from different modalities and the efficacy of incorporating semantic maps.

Related

• Instruction-Following Agents with Multimodal Transformer
• Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions
• Target-dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots
• Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
• CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models