SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912480326844416 |
|---|---|
| author | Fang, Haoquan Grotz, Markus Pumacay, Wilbert Wang, Yi Ru Fox, Dieter Krishna, Ranjay Duan, Jiafei |
| author_facet | Fang, Haoquan Grotz, Markus Pumacay, Wilbert Wang, Yi Ru Fox, Dieter Krishna, Ranjay Duan, Jiafei |
| contents | Robotic manipulation systems operating in diverse, dynamic environments must exhibit three critical abilities: multitask interaction, generalization to unseen scenarios, and spatial memory. While significant progress has been made in robotic manipulation, existing approaches often fall short in generalization to complex environmental variations and addressing memory-dependent tasks. To bridge this gap, we introduce SAM2Act, a multi-view robotic transformer-based policy that leverages multi-resolution upsampling with visual representations from large-scale foundation model. SAM2Act achieves a state-of-the-art average success rate of 86.8% across 18 tasks in the RLBench benchmark, and demonstrates robust generalization on The Colosseum benchmark, with only a 4.3% performance gap under diverse environmental perturbations. Building on this foundation, we propose SAM2Act+, a memory-based architecture inspired by SAM2, which incorporates a memory bank, an encoder, and an attention mechanism to enhance spatial memory. To address the need for evaluating memory-dependent tasks, we introduce MemoryBench, a novel benchmark designed to assess spatial memory and action recall in robotic manipulation. SAM2Act+ achieves an average success rate of 94.3% on memory-based tasks in MemoryBench, significantly outperforming existing approaches and pushing the boundaries of memory-based robotic systems. Project page: sam2act.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18564 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation Fang, Haoquan Grotz, Markus Pumacay, Wilbert Wang, Yi Ru Fox, Dieter Krishna, Ranjay Duan, Jiafei Robotics Robotic manipulation systems operating in diverse, dynamic environments must exhibit three critical abilities: multitask interaction, generalization to unseen scenarios, and spatial memory. While significant progress has been made in robotic manipulation, existing approaches often fall short in generalization to complex environmental variations and addressing memory-dependent tasks. To bridge this gap, we introduce SAM2Act, a multi-view robotic transformer-based policy that leverages multi-resolution upsampling with visual representations from large-scale foundation model. SAM2Act achieves a state-of-the-art average success rate of 86.8% across 18 tasks in the RLBench benchmark, and demonstrates robust generalization on The Colosseum benchmark, with only a 4.3% performance gap under diverse environmental perturbations. Building on this foundation, we propose SAM2Act+, a memory-based architecture inspired by SAM2, which incorporates a memory bank, an encoder, and an attention mechanism to enhance spatial memory. To address the need for evaluating memory-dependent tasks, we introduce MemoryBench, a novel benchmark designed to assess spatial memory and action recall in robotic manipulation. SAM2Act+ achieves an average success rate of 94.3% on memory-based tasks in MemoryBench, significantly outperforming existing approaches and pushing the boundaries of memory-based robotic systems. Project page: sam2act.github.io. |
| title | SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2501.18564 |