1. [Publications](/index.php/publications)
2. SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation
 
 # SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation

  ![](/sites/default/files/styles/wide/public/publications/fooaa_0.png?itok=sLdxjeJg)

 We introduce SPOT, an object-centric imitation learning framework. The key idea is to capture each task by an object-centric representation, specifically the SE(3) object pose trajectory relative to the target. This approach decouples embodiment actions from sensory inputs, facilitating learning from various demonstration types, including both action-based and action-less human hand demonstrations, as well as cross-embodiment generalization. Additionally, object pose trajectories inherently capture planning constraints from demonstrations without the need for manually-crafted rules. To guide the robot in executing the task, the object trajectory is used to condition a diffusion policy. We systematically evaluate our method on simulation and real-world tasks. In real-world evaluation, using only eight demonstrations shot on an iPhone, our approach completed all tasks while fully complying with task constraints.



 ## Authors



Cheng-Chun Hsu (UT Austin)

[Bowen Wen](/index.php/person/bowen-wen)

[Jie Xu](/index.php/person/jie-xu)

[Yashraj Narang](/index.php/person/yashraj-narang)

 (UCSD)

[Yuke Zhu](/index.php/person/yuke-zhu)

Joydeep Biswas (UT Austin)

[Stan Birchfield](/index.php/person/stan-birchfield)

 

 

 ## Publication Date



Thursday, May 15, 2025

 

 ## Published in



[ICRA 2025](https://2025.ieee-icra.org/)

 

 ## Research Area



[Computer Vision](/index.php/research-area/computer-vision)

[Robotics](/index.php/research-area/robotics)

 

 

 ## External Links



[paper](https://arxiv.org/abs/2411.00965)

[webpage](https://nvlabs.github.io/object_centric_diffusion/)