Efficient Robotic Policy Learning via Latent Space Backward Planning

Dongxiu Liu, Haoyi Niu, Zhihao Wang, Jinliang Zheng, Yinan Zheng, Zhonghong Ou, Jianming HU, Jianxiong Li, Xianyuan Zhan

Track: full paper

Keywords: Efficient Visuomotor Planning, Robotics, Subgoal-Conditioned Policy

TL;DR: A lightweight and efficient long-horizon visuomotor planning framework by generating subgoals in coarse-to-fine horizons backward from the final goal.

Abstract: Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introduces two significant challenges for downstream policy learning: substantial computational costs that hinder real-time deployment, and accumulated inaccuracies that can mislead action extraction. Planning with coarse-grained subgoals partially alleviates efficiency issues. However, their forward planning schemes can still result in off-task predictions due to accumulation errors, leading to misalignment with long-term goals. This raises a critical question: Can robotic planning be both efficient and accurate enough for real-time control in long-horizon, multi-stage tasks? To address this, we propose a **B**ackward **P**lanning scheme in **L**atent space (**LBP**), which begins by grounding the task into final latent goals, followed by recursively predicting intermediate subgoals closer to the current state. The grounded final goal enables backward subgoal planning to always remain aware of task completion, facilitating on-task prediction along the entire planning horizon. The subgoal-conditioned policy incorporates a learnable token to summarize the subgoal sequences and determines how each subgoal guides action extraction. Through extensive simulation and real-robot long-horizon experiments, we show that LBP outperforms existing fine-grained and forward planning methods, achieving SOTA performance. Project Page: [https://lbp-authors.github.io](https://lbp-authors.github.io).

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Presenter: ~Haoyi_Niu1

Format: Yes, the presenting author will attend in person if this work is accepted to the workshop.

Funding: Yes, the presenting author of this submission falls under ICLR’s funding aims, and funding availability would significantly influence their ability to attend the workshop in person.

Submission Number: 5