How to Build a Pre-trained Multimodal model for Simultaneously Chatting and Decision-making?
Keywords: vision language action model; decision making; autonomous driving; multimodal
TL;DR: We propose an approach to build a pre-trained multimodal model for simultaneously chatting and decision-making.
Abstract: Existing large pre-trained models typically map text input to text output in an end-to-end manner, such as ChatGPT, or map a segment of text input to a hierarchy of action decisions, such as OpenVLA. However, humans can simultaneously generate text and actions when receiving specific input signals. For example, a driver can make precise driving decisions while conversing with a friend in the passenger seat. Motivated by this observation, we consider the following question in this work: is it possible to construct a pre-trained model that can provide both language interaction and precise decision-making capabilities in dynamic open scenarios. We provide a definitive answer to this question by developing a new model architecture termed Visual Language Action model for Chatting and Decision Making (VLA4CD), and further demonstrating its performance in challenging automonous driving tasks. We build VLA4CD on the basis of transformer-based LLM architecture. Specifically, we leverage LoRA to fine-tune a pre-trained LLM with data of multiple modalities covering language, visual, and action. Unlike the existing LoRA operations used for LLM fine-tuning, we have designed new computational modules and training cost functions for VLA4CD. These designs enable VLA4CD to provide continuous-valued action decisions while outputting text responses. In contrast, existing LLMs can only output text responses, and current VLA models can only output action decisions. Moreover, these VLA models handle action data by discretizing and then tokenizing the discretized actions, a method unsuitable for complex decision-making tasks involving high-dimensional continuous-valued action vectors, such as autonomous driving. The extensive experimental results on the closed-loop autonomous driving platform CARLA validate that: (1) the model construction method we proposed is effective; (2) compared to the state-of-the-art VLA model, VLA4CD can provide more accurate real-time decision-making while retaining the text interaction capability inherent to LLMs.
Primary Area: applications to robotics, autonomy, planning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2963
Loading