paper-with-me

홈 › Papers

TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning

2026-03-02 · Zhenan Wang, Yanzhe Wang, Meixuan Ren, Peng Li, Yang Liu, Yifei Nie, Limin Long, Yun Ye, Xiaofeng Wang, Zhen Zhu, Huixu Dong arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.01700

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression

2023-01-01 · ICCV 2023 1 · Sheng Shen, Huanjing Yue, Jingyu Yang

Natural image compression has been greatly improved in the deep learning era. However, the compression performance will be heavily degraded if the pretrained encoder is directly applied on screen content image compre…

DecoderImage CompressionTransfer Learning

TaF-VLA: Tactile-Force Alignment in Vision-Language-Action Models for Force-aware Manipulation

2026-01-28 · Yuzhe Huang, Pei Lin, Wanlin Li, Daohan Li 외 arxiv

Vision-Language-Action (VLA) models have recently emerged as powerful generalists for robotic manipulation. However, due to their predominant reliance on visual modalities, they fundamentally lack the physical intuition …

Physical Intuition

Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities

2025-11-14 · Yiyun Zhou, Mingjing Xu, Jingwei Shi, Quanjiang Li 외 arxiv

Tactile sensing offers rich and complementary information to vision and language, enabling robots to perceive fine-grained object properties. However, existing tactile sensors lack standardization, leading to redundant f…

Representation Learning

TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data

2026-02-10 · Zhengxue Cheng, Yan Zhao, Keyu Wang, Hengdi Zhang 외 arxiv

Tactile sensing is crucial for embodied intelligence, providing fine-grained perception and control in complex environments. However, efficient tactile data compression, which is essential for real-time robotic applicati…

Robotic Grasping

DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter

2026-02-05 · Xukun Li, Yu Sun, Lei Zhang, Bosheng Huang 외 arxiv

Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal di…