# TGrasp6D reports 94% success in task-oriented robot grasping

> The arXiv paper describes a system that uses a task and one RGB-D image to plan a six-degree-of-freedom grasp, with a real-robot demonstration.

Oossa · 2026-10-16 · https://oossa.com/en/tgrasp6d-reports-94-success-in-task-oriented-robot-grasping

Researchers introduce TGrasp6D, a system that uses a task description and a single RGB-D image—a color image paired with depth data—to choose how a robot should grasp an object. For example, it can favor a knife’s handle for slicing or leave the handle clear for a handoff.

The paper reports a 94% success rate on the TaskGrasp dataset, compared with 74% for the best baseline. The team also demonstrated the approach on a Franka Research 3 robot with real-world objects; the abstract does not provide details on the number of trials or independent testing.

## The facts

- The paper reports 94% success on TaskGrasp; its best baseline scored 74%.
- The paper was published on arXiv on October 16, 2026.

## Why it matters

For robotics researchers, the reported results suggest task descriptions and a single depth image could help robots choose grasps without relying on a hand-labeled dataset for every task-object pair; performance beyond the reported tests is not established here.

## Sources & references

1. [TGrasp6D: Task-Informed Vision-Language Priors and Pose Refinement enable Zero-Shot Task-Oriented 6DoF Grasping](https://arxiv.org/abs/2610.20901) – arXiv cs.RO, 2026-10-16

Last updated: 2026-10-16