Skip to content
MouseMouse

A single-signal contact detector lied in both directions - foot height flagged 40% false flight on a walking gait, contact force alone flagged false flight during low-friction slip - so flight became force < 5 N AND sole height > 5 mm

A lesson the Coach cites as contact-detector-single-signal-lies.
ReplicatedEvaluation

Define contact and flight events from two independent signals (force and geometry) in conjunction, validate the detector on a behaviour known not to contain the event before using it as a gate, and match the trainer's threshold when comparing across simulators.

Symptom

The run line needed a flight-fraction gate. The first MuJoCo version, "sole higher than 2 mm", measured 40% flight on a walking policy that never flies. Five weeks later the one-leg gate, using contact force alone, reported support-foot "flight" segments at mu 0.4 for a policy that was not hopping.

Context

During a walking step the toe lifts or the heel strikes with the foot pitched, so the ankle-roll origin rises a few mm while part of the sole still touches - height alone calls that flight. Switching to contact force < 5 N (the same threshold Isaac's contact reward uses) zeroed the false flight on walking. In the one-leg re-test every force-only "flight" segment had a measured sole height of 0.0 mm: the normal force chattered while slip corrections played out on low friction.

Change

Run line: flight = contact force < 5 N ("lift-off must be judged by contact force"). One-leg line (2026-09-16): flight = force < 5 N AND sole height > 5 mm, recorded as the same measurement lesson in the opposite direction; the gate's behavioural meaning was unchanged.

Outcome

With force-based detection the walking policy read 0.0 flight and the run policy's zero flight was confirmed by two plants; with the conjunctive definition the one-leg support-foot gate stopped reporting false hops.

Mechanism

Each signal has its own failure: geometry moves without leaving the ground (foot pitch), and forces drop without leaving the ground (slip chatter); requiring both removes both families of false positives.

Applies when

  • writing a flight, lift-off, hop or slip detector for a gate
  • a gate reports an event the video does not show
  • reusing a detector on a different gait or floor friction
“首版用**足底高度>2mm** 判离地, 在 omni_s1e 走路策略上测出 40% 假腾空 … 改用**接触力 <5N**(与 Isaac feet_contact_number 同源阈值)后 空检归零 (walk 策略 flight_frac 0.0)。**课文: 离地判定必须用接触力, 高度判 会把脚的俯仰当腾空**”
train/README.md § run R1 立项 (2026-08-09): Mac 侧新工具 + 一次空检抓获

Principles that cite it