TacCompress: A Benchmark for Multi-Point Tactile Data Compression in Dexterous Hand

TL;DR

This paper introduces a comprehensive tactile dataset for dexterous hand manipulation and explores both lossless and lossy compression techniques, achieving significant data reduction while maintaining data quality.

Contribution

It provides a new multi-point tactile dataset and evaluates various image codecs for efficient tactile data compression in robotic manipulation.

Findings

Lossless compression achieves up to 200× reduction.

Lossy compression with HM and VTM reaches about 1000× reduction.

Screen-content-targeted codecs outperform general-purpose codecs.

Abstract

Though robotic dexterous manipulation has progressed substantially recently, challenges like in-hand occlusion still necessitate fine-grained tactile perception, leading to the integration of more tactile sensors into robotic hands. Consequently, the increased data volume imposes substantial bandwidth pressure on signal transmission from the hand's controller. However, the acquisition and compression of multi-point tactile signals based on the dexterous hands' physical structures have not been thoroughly explored. In this paper, our contributions are twofold. First, we introduce a Multi-Point Tactile Dataset for Dexterous Hand Grasping (Dex-MPTD). This dataset captures tactile signals from multiple contact sensors across various objects and grasping poses, offering a comprehensive benchmark for advancing dexterous robotic manipulation research. Second, we investigate both lossless and lossy compression on Dex-MPTD by converting tactile data into images and applying six lossless and five lossy image codecs for efficient compression. Experimental results demonstrate that tactile data can be losslessly compressed to as low as 0.0364 bits per sub-sample (bpss), achieving approximately 200$\times$ compression ratio compared to the raw tactile data. Efficient lossy compressors like HM and VTM can achieve about 1000$\times$ data reductions while preserving acceptable data fidelity. The exploration of lossy compression also reveals that screen-content-targeted coding tools outperform general-purpose codecs in compressing tactile data.