TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918366104518656 |
|---|---|
| author | Wang, Zhenan Wang, Yanzhe Ren, Meixuan Li, Peng Liu, Yang Nie, Yifei Long, Limin Ye, Yun Wang, Xiaofeng Zhu, Zhen Dong, Huixu |
| author_facet | Wang, Zhenan Wang, Yanzhe Ren, Meixuan Li, Peng Liu, Yang Nie, Yifei Long, Limin Ye, Yun Wang, Xiaofeng Zhu, Zhen Dong, Huixu |
| contents | In visually ambiguous manipulation such as detecting button click tactile feedback is often the sole source of ground truth. However, fusing tactile data poses a significant challenge due to a spatiotemporal mismatch: tactile perception requires high-frequency processing with long-horizon memory (System 1), whereas visual policies operate at low control frequencies (System 2). Existing architectures struggle to bridge this gap: Transformers are computationally prohibitive for high-frequency loops (>100Hz), while LSTMs suffer from forgetting over extended interaction histories. In this paper, we introduce TacMamba, a hierarchical architecture that aligns high-bandwidth tactile reflexes with low-frequency visual planning. Our approach comprises three core contributions: (1) a custom high-frequency tactile interface designed for flexible integration; (2) a Mamba-based Tactile History Compressor that encodes continuous force history into a compact state with O(1) inference latency (0.45 ms), enabling plug-and-play fusion with VLA models without joint pre-training and (3) a Tactile-Guided Dual-Stage Training strategy that leverages temporal discrimination for self-supervised representation learning and phase-uniform sampling to mitigate data sparsity. Experiments on discrete counting and implicit state switching demonstrate that TacMamba achieves 100% success rates, significantly outperforming the visual-only pi_0.5 baseline, while strictly satisfying hard real-time constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01700 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning Wang, Zhenan Wang, Yanzhe Ren, Meixuan Li, Peng Liu, Yang Nie, Yifei Long, Limin Ye, Yun Wang, Xiaofeng Zhu, Zhen Dong, Huixu Robotics In visually ambiguous manipulation such as detecting button click tactile feedback is often the sole source of ground truth. However, fusing tactile data poses a significant challenge due to a spatiotemporal mismatch: tactile perception requires high-frequency processing with long-horizon memory (System 1), whereas visual policies operate at low control frequencies (System 2). Existing architectures struggle to bridge this gap: Transformers are computationally prohibitive for high-frequency loops (>100Hz), while LSTMs suffer from forgetting over extended interaction histories. In this paper, we introduce TacMamba, a hierarchical architecture that aligns high-bandwidth tactile reflexes with low-frequency visual planning. Our approach comprises three core contributions: (1) a custom high-frequency tactile interface designed for flexible integration; (2) a Mamba-based Tactile History Compressor that encodes continuous force history into a compact state with O(1) inference latency (0.45 ms), enabling plug-and-play fusion with VLA models without joint pre-training and (3) a Tactile-Guided Dual-Stage Training strategy that leverages temporal discrimination for self-supervised representation learning and phase-uniform sampling to mitigate data sparsity. Experiments on discrete counting and implicit state switching demonstrate that TacMamba achieves 100% success rates, significantly outperforming the visual-only pi_0.5 baseline, while strictly satisfying hard real-time constraints. |
| title | TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.01700 |