ROCVMay 9, 2025

3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks

arXiv:2505.05800v125 citationsh-index: 40Has Code
Originality Incremental advance
AI Analysis

This work addresses robotic manipulation for unseen tasks, offering incremental improvements through enhanced 3D context integration.

The paper tackles the problem of robotic manipulation in 3D by improving scene context awareness in Vision-Language-Action models, achieving an average success rate of 98.1% on seen tasks and an 8.8% absolute improvement on unseen tasks.

Robotic manipulation in 3D requires learning an $N$ degree-of-freedom joint space trajectory of a robot manipulator. Robots must possess semantic and visual perception abilities to transform real-world mappings of their workspace into the low-level control necessary for object manipulation. Recent work has demonstrated the capabilities of fine-tuning large Vision-Language Models (VLMs) to learn the mapping between RGB images, language instructions, and joint space control. These models typically take as input RGB images of the workspace and language instructions, and are trained on large datasets of teleoperated robot demonstrations. In this work, we explore methods to improve the scene context awareness of a popular recent Vision-Language-Action model by integrating chain-of-thought reasoning, depth perception, and task-oriented region of interest detection. Our experiments in the LIBERO simulation environment show that our proposed model, 3D-CAVLA, improves the success rate across various LIBERO task suites, achieving an average success rate of 98.1$\%$. We also evaluate the zero-shot capabilities of our method, demonstrating that 3D scene awareness leads to robust learning and adaptation for completely unseen tasks. 3D-CAVLA achieves an absolute improvement of 8.8$\%$ on unseen tasks. We will open-source our code and the unseen tasks dataset to promote community-driven research here: https://3d-cavla.github.io

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes