Object-Centric Instruction Augmentation for Robotic Manipulation
This addresses the challenge of enabling robots to better understand object locations for tasks like pick-and-place, though it is incremental as it builds on existing language model approaches.
The paper tackles the problem of robotic manipulation by augmenting language instructions with object position cues, using a Multi-modal Large Language Model to improve policy performance, and shows that policies trained with this method outperform traditional ones in simulated and real-world tasks.
Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understanding both what the objects are and where they are located is crucial. While the former has been extensively discussed in the literature that uses the large language model to enrich the text descriptions, the latter remains underexplored. In this work, we introduce the \textit{Object-Centric Instruction Augmentation (OCI)} framework to augment highly semantic and information-dense language instruction with position cues. We utilize a Multi-modal Large Language Model (MLLM) to weave knowledge of object locations into natural language instruction, thus aiding the policy network in mastering actions for versatile manipulation. Additionally, we present a feature reuse mechanism to integrate the vision-language features from off-the-shelf pre-trained MLLM into policy networks. Through a series of simulated and real-world robotic tasks, we demonstrate that robotic manipulator imitation policies trained with our enhanced instructions outperform those relying solely on traditional language instructions.