Goal State Generation for Robotic Manipulation Based on Linguistically Guided Hybrid Gaussian Diffusion

TL;DR

This paper introduces a novel linguistically guided hybrid Gaussian diffusion network for generating feasible, collision-free target states in robotic manipulation tasks, improving success rates and reducing overlaps in point clouds.

Contribution

The paper presents a new LHGD network and a gravity coverage coefficient method for controlled, language-guided target state generation in robotic manipulation, addressing previous randomness and overlap issues.

Findings

Achieves highest success rates in manipulation tasks

Reduces point cloud overlaps significantly

Produces collision-free target states without extra obstacle avoidance

Abstract

In robotic manipulation tasks, achieving a designated target state for the manipulated object is often essential to facilitate motion planning for robotic arms. Specifically, in tasks such as hanging a mug, the mug must be positioned within a feasible region around the hook. Previous approaches have enabled the generation of multiple feasible target states for mugs; however, these target states are typically generated randomly, lacking control over the specific generation locations. This limitation makes such methods less effective in scenarios where constraints exist, such as hooks already occupied by other mugs or when specific operational objectives must be met. Moreover, due to the frequent physical interactions between the mug and the rack in real-world hanging scenarios, imprecisely generated target states from end-to-end models often result in overlapping point clouds. This overlap adversely impacts subsequent motion planning for the robotic arm. To address these challenges, we propose a Linguistically Guided Hybrid Gaussian Diffusion (LHGD) network for generating manipulation target states, combined with a gravity coverage coefficient-based method for target state refinement. To evaluate our approach under a language-specified distribution setting, we collected multiple feasible target states for 10 types of mugs across 5 different racks with 10 distinct hooks. Additionally, we prepared five unseen mug designs for validation purposes. Experimental results demonstrate that our method achieves the highest success rates across single-mode, multi-mode, and language-specified distribution manipulation tasks. Furthermore, it significantly reduces point cloud overlap, directly producing collision-free target states and eliminating the need for additional obstacle avoidance operations by the robotic arm.