AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation

Yijie Zhu, Rui Shao, Ziyang Liu, Jie He, Jizhihui Liu, Jiuru Wang, Zitong Yu

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GOS (goal-conditioned observation synthesis) (ablation)H-GAR baseline · PushTsuccess rate: 0.90 -> 0.92Improved
add GOS (ablation)H-GAR baseline · PushT-Msuccess rate: 0.78 -> 0.82Improved
add GOS (ablation)H-GAR baseline · Libero-10success rate: 0.85 -> 0.89Improved
add IAAR without memory bank (ablation)H-GAR with GOS · Libero-10success rate: 0.89 -> 0.91Improved
add historical action memory bank to IAAR (ablation)H-GAR with GOS+IAAR · PushTsuccess rate: 0.96 -> 0.99Improved
add historical action memory bank to IAAR (ablation)H-GAR with GOS+IAAR · PushT-Msuccess rate: 0.87 -> 0.90Improved
add historical action memory bank to IAAR (ablation)H-GAR with GOS+IAAR · Libero-10success rate: 0.91 -> 0.94Improved
use goal frame only as GOS input instead of uniform multi-frame (ablation)H-GAR · PushT-Msuccess rate: 0.83 -> 0.90Improved
use goal frame only instead of single random frame (ablation)H-GAR · Libero-10success rate: 0.88 -> 0.94Improved
use similarity-based memory update instead of random (ablation)H-GAR · Libero-10success rate: 0.89 -> 0.94Improved
use similarity-based memory update instead of FIFO (ablation)H-GAR · PushTsuccess rate: 0.97 -> 0.99Improved
increase memory bank size from 32 to 64 (ablation)H-GAR · Libero-10success rate: 0.94 -> 0.92Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy