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

2026-02-10

AI Summary

Efficient compression of tactile data remains underexplored in bandwidth-constrained real-time robotic applications, primarily due to its heterogeneity and spatiotemporal complexity. This work proposes TaCo, the first comprehensive benchmark for tactile compression, systematically evaluating 30 compression methods across five sensor modalities on four downstream tasks: lossless storage, human visualization, material and object classification, and dexterous grasping. We introduce TaCo-LL and TaCo-L—novel data-driven codecs specifically designed for lossless and lossy tactile compression, respectively—and integrate off-the-shelf compression algorithms with neural encoding techniques to uncover the trade-offs between compression efficiency and task performance. Experiments demonstrate that our approaches significantly outperform existing baselines across multiple tasks, establishing a foundation for efficient tactile data compression and its practical deployment in robotic perception systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Data Mining & Knowledge Management: Data Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

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 applications under strict bandwidth constraints, remains underexplored. The inherent heterogeneity and spatiotemporal complexity of tactile data further complicate this challenge. To bridge this gap, we introduce TaCo, the first comprehensive benchmark for Tactile data Codecs. TaCo evaluates 30 compression methods, including off-the-shelf compression algorithms and neural codecs, across five diverse datasets from various sensor types. We systematically assess both lossless and lossy compression schemes on four key tasks: lossless storage, human visualization, material and object classification, and dexterous robotic grasping. Notably, we pioneer the development of data-driven codecs explicitly trained on tactile data, TaCo-LL (lossless) and TaCo-L (lossy). Results have validated the superior performance of our TaCo-LL and TaCo-L. This benchmark provides a foundational framework for understanding the critical trade-offs between compression efficiency and task performance, paving the way for future advances in tactile perception.

Problem

• tactile data compression
• heterogeneous data
• lossless compression
• lossy compression
• bandwidth constraints

Innovation

• tactile compression
• neural codecs
• heterogeneous tactile data
• lossless compression
• lossy compression