Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation

TL;DR

LMM-3DP is a framework that combines large multimodal model planners with 3D skill policies, enabling robots to perform complex manipulation tasks with improved accuracy and success rates in real-world environments.

Contribution

This work introduces LMM-3DP, a novel integration of LMM-based high-level planning with 3D feature field-based low-level control for robotic manipulation.

Findings

1.45x increase in low-level control success rate

1.5x improvement in high-level planning accuracy

Effective real-world kitchen environment performance

Abstract

The recent advancements in visual reasoning capabilities of large multimodal models (LMMs) and the semantic enrichment of 3D feature fields have expanded the horizons of robotic capabilities. These developments hold significant potential for bridging the gap between high-level reasoning from LMMs and low-level control policies utilizing 3D feature fields. In this work, we introduce LMM-3DP, a framework that can integrate LMM planners and 3D skill Policies. Our approach consists of three key perspectives: high-level planning, low-level control, and effective integration. For high-level planning, LMM-3DP supports dynamic scene understanding for environment disturbances, a critic agent with self-feedback, history policy memorization, and reattempts after failures. For low-level control, LMM-3DP utilizes a semantic-aware 3D feature field for accurate manipulation. In aligning high-level and low-level control for robot actions, language embeddings representing the high-level policy are jointly attended with the 3D feature field in the 3D transformer for seamless integration. We extensively evaluate our approach across multiple skills and long-horizon tasks in a real-world kitchen environment. Our results show a significant 1.45x success rate increase in low-level control and an approximate 1.5x improvement in high-level planning accuracy compared to LLM-based baselines. Demo videos and an overview of LMM-3DP are available at https://lmm-3dp-release.github.io.