PaXini PX-6AX GEN3: A Data-Native Tactile Sensing Platform

The PaXini PX-6AX GEN3 series is a family of multidimensional tactile sensing modules designed for high-resolution force perception, contact understanding, and data-driven robotic manipulation. Rather than treating touch as a binary event, PX-6AX GEN3 captures spatially distributed, triaxial force fields at the contact surface.

Design Philosophy

Traditional robotic force sensing focuses on global force or torque. PaXini is designed around modern learning systems, where local contact geometry, force distribution, and temporal evolution are critical signals. The system provides: spatially distributed sensing (not single-point), triaxial force (Fx, Fy, Fz) at each cell, high repeatability for dataset consistency, and direct digital access for real-time learning pipelines.

Sensing Principle

PX-6AX GEN3 adopts a semi-flexible, Hall-effect-based architecture. A compliant elastomer layer deforms under contact; deformation induces controlled displacement of magnetic elements; a rigid sensing layer measures magnetic field changes; embedded algorithms reconstruct triaxial force vectors. Anti-stray magnetic field algorithms isolate force-induced signals and suppress environmental interference.

Data Output and Semantics

At each time step, the sensor provides per-cell triaxial force vectors and aggregated resultant forces. This representation enables learning systems to reason about contact location, pressure distribution, slip and shear forces, and transitions between sticking and sliding. Partial contacts, misalignment, and incipient slip are essential signals for robust policy learning.

Learning Workflows Enabled

Dense tactile signals augment visual and proprioceptive observations for imitation learning. Distributed force feedback provides rich reward signals for RL. Tactile data can be fused with vision, joint states, and audio to train multimodal perception and control models.