paper-with-me

홈 › Papers

KITE: Keypoint-Conditioned Policies for Semantic Manipulation

2023-06-29 · Priya Sundaresan, Suneel Belkhale, Dorsa Sadigh, Jeannette Bohg

While natural language offers a convenient shared interface for humans and robots, enabling robots to interpret and follow language commands remains a longstanding challenge in manipulation. A crucial step to realizing a performant instruction-following robot is achieving semantic manipulation, where a robot interprets language at different specificities, from high-level instructions like "Pick up the stuffed animal" to more detailed inputs like "Grab the left ear of the elephant." To tackle this, we propose Keypoints + Instructions to Execution (KITE), a two-step framework for semantic manipulation which attends to both scene semantics (distinguishing between different objects in a visual scene) and object semantics (precisely localizing different parts within an object instance). KITE first grounds an input instruction in a visual scene through 2D image keypoints, providing a highly accurate object-centric bias for downstream action inference. Provided an RGB-D scene observation, KITE then executes a learned keypoint-conditioned skill to carry out the instruction. The combined precision of keypoints and parameterized skills enables fine-grained manipulation with generalization to scene and object variations. Empirically, we demonstrate KITE in 3 real-world environments: long-horizon 6-DoF tabletop manipulation, semantic grasping, and a high-precision coffee-making task. In these settings, KITE achieves a 75%, 70%, and 71% overall success rate for instruction-following, respectively. KITE outperforms frameworks that opt for pre-trained visual language models over keypoint-based grounding, or omit skills in favor of end-to-end visuomotor control, all while being trained from fewer or comparable amounts of demonstrations. Supplementary material, datasets, code, and videos can be found on our website: http://tinyurl.com/kite-site.

📄 PDF Abstract BibTeX arXiv:2306.16605

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction FollowingObject

Methods 이 논문이 사용한 방법론

OPT OPT is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear…

Similar Papers 제목 키워드 기반

CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints

2025-07-26 · Yuhong Deng, Chao Tang, Cunjun Yu, Linfeng Li 외 arxiv

Clothes manipulation, such as folding or hanging, is a critical capability for home service robots. Despite recent advances, most existing methods remain limited to specific clothes types and tasks, due to the complex, h…

KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation

2026-06-20 · Qianxu Wang, Kuan Fang arxiv

Generalizing manipulation policies across robot embodiments remains difficult because standard policies entangle task reasoning with embodiment-specific motor control. We study zero-shot cross-embodiment manipulation, wh…

General-purpose Clothes Manipulation with Semantic Keypoints

2024-08-15 · Yuhong Deng, David Hsu

Clothes manipulation is a critical capability for household robots; yet, existing methods are often confined to specific tasks, such as folding or flattening, due to the complex high-dimensional geometry of deformable fa…

Action GenerationLanguage ModelingLanguage ModellingLarge Language Model+1

A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards

2025-02-12 · Shivansh Patel, Xinchen Yin, Wenlong Huang, Shubham Garg 외

Task specification for robotic manipulation in open-world environments is challenging, requiring flexible and adaptive objectives that align with human intentions and can evolve through iterative feedback. We introduce I…

Reinforcement Learning (RL)

PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies

2025-09-22 · Jesse Zhang, Marius Memmel, Kevin Kim, Dieter Fox 외 arxiv

Robotic manipulation policies often fail to generalize because they must simultaneously learn where to attend, what actions to take, and how to execute them. We argue that high-level reasoning about where and what can be…

Zero-shot GeneralizationRobot Manipulation