FLA · The sole, close up · 16 Nov 2026 · all reports · summary

The sole, close up

What the simulated sole actually reports while the K1 walks: which sensing points fire, what the shear looks like, and where the sole's reading departs from the true ground force. Seven short segments from the two experiments.

Simulation only. The sole is a model of a pressure-and-shear sole, not a recording of one.

In short

  1. The sole model was the same in both experiments. Both replay the step-1 episodes exactly, so pressure and shear come from one sensor model.
  2. Totals are right. Standing force equals body weight to within 0.89 % in the six-class data and 0.10 % in the two-class data, measured on the simulator's noise-free force.
  3. The readout carries deliberate noise. Two robots standing with the same true force read −5.7 % and +1.2 % on the sole.
  4. One gap is known and not fixed. A load that runs parallel to the sole is not seen. In one heel-to-toe step the ground pushes with 222 N and the sole reads about zero.
  5. Shear is four vectors per foot, and in this rigid-body simulation they carry about three independent numbers.
1

The clip

Left: the feet. Right: both soles, with each of the 152 points per foot drawn as a dot that lights up above 1.5 N. The four white boxes are the pressure blocks, the bold arrows are the four shear vectors, the blue dot is the centre of pressure. Bottom: the sole's total force (orange) against the simulator's true ground force (white), with the contact label as a blue band.

Seven segments, slowed to between 0.1× and 0.5× speed.
SegmentWhat it shows
1Flat-foot gait on hard floor, with one touchdown and one lift-off replayed at 0.2× so the order of points lighting up can be read.
2Soft floor, then slippery floor, on the same scales.
3Heel-to-toe gait on step edges: the known gap, slowed to 0.1× and frozen.
4Two robots standing still: equal true force, different sole readings.
5The nominal and the shifted sensor model reading the same steps.
6Hard floor above, soft floor below, same commanded speed of 0.25 m/s.
7Crossing from hard to soft: the step before, the boundary step and the step after.
2

Hard against soft

Feet on hard floor above and soft floor below, with the sole point grids, shear arrows and force traces for each
Same command and same scales. On hard floor the touchdown has a sharp impact peak in the true force; on soft floor the force rises smoothly.

Reading the frame. Differences this coarse are what the teachers use, and why both score about 0.99 on hard against soft. Over a whole step the contact area is 26 % on soft floor against 20 % on hard, though single frames go both ways. The sole's total also undershoots the impact peak on hard floor.

3

The known gap

Heel-to-toe gait on a step edge: the true ground force trace rises far above the sole's total, and no sole points are lit
The white trace is the true force on the foot; the orange trace is what the sole reports.
4

Why four shear vectors

5

What this does not show

Related: six-class dataset, two-class dataset, teachers, sensor-layout check.