Saved in:
Bibliographic Details
Main Authors: Cao, Yunhao, Bhaumik, Zubin, Jia, Jessie, He, Xingyi, Fang, Kuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.05953
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914182770720768
author Cao, Yunhao
Bhaumik, Zubin
Jia, Jessie
He, Xingyi
Fang, Kuan
author_facet Cao, Yunhao
Bhaumik, Zubin
Jia, Jessie
He, Xingyi
Fang, Kuan
contents We introduce Correspondence-Oriented Imitation Learning (COIL), a conditional policy learning framework for visuomotor control with a flexible task representation in 3D. At the core of our approach, each task is defined by the intended motion of keypoints selected on objects in the scene. Instead of assuming a fixed number of keypoints or uniformly spaced time intervals, COIL supports task specifications with variable spatial and temporal granularity, adapting to different user intents and task requirements. To robustly ground this correspondence-oriented task representation into actions, we design a conditional policy with a spatio-temporal attention mechanism that effectively fuses information across multiple input modalities. The policy is trained via a scalable self-supervised pipeline using demonstrations collected in simulation, with correspondence labels automatically generated in hindsight. COIL generalizes across tasks, objects, and motion patterns, achieving superior performance compared to prior methods on real-world manipulation tasks under both sparse and dense specifications.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05953
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Correspondence-Oriented Imitation Learning: Flexible Visuomotor Control with 3D Conditioning
Cao, Yunhao
Bhaumik, Zubin
Jia, Jessie
He, Xingyi
Fang, Kuan
Robotics
We introduce Correspondence-Oriented Imitation Learning (COIL), a conditional policy learning framework for visuomotor control with a flexible task representation in 3D. At the core of our approach, each task is defined by the intended motion of keypoints selected on objects in the scene. Instead of assuming a fixed number of keypoints or uniformly spaced time intervals, COIL supports task specifications with variable spatial and temporal granularity, adapting to different user intents and task requirements. To robustly ground this correspondence-oriented task representation into actions, we design a conditional policy with a spatio-temporal attention mechanism that effectively fuses information across multiple input modalities. The policy is trained via a scalable self-supervised pipeline using demonstrations collected in simulation, with correspondence labels automatically generated in hindsight. COIL generalizes across tasks, objects, and motion patterns, achieving superior performance compared to prior methods on real-world manipulation tasks under both sparse and dense specifications.
title Correspondence-Oriented Imitation Learning: Flexible Visuomotor Control with 3D Conditioning
topic Robotics
url https://arxiv.org/abs/2512.05953