Does the stylised feeding-arm lip-force result survive real contact physics? osrobot-assist re-run in MuJoCo

What it found

The osrobot-assist spoon-feeding trial rebuilt in MuJoCo (a sphere on two slide joints, two box lips that follow the mouth's sway, MuJoCo soft contact), with the same controller and 200 paired seeds per row. With the arm blocked, the steady contact force equals the controller identity KP×LEAD×speed (2.00 N at 0.10 m/s) but the impact peak is 1.84× higher at every speed (3.68 N), and falls with more contact damping. With a swaying mouth the share fed at most 2 N drops from the stylised 1.00 to 0.45 at 0.10 m/s (30 mm sway, camera arm), with peaks of 11 to 23 N because the kinematic lips sweep into the tip, a contact the stylised model leaves out. Feeding time agrees within 4 % in all but one row. Stylised and preliminary: rigid lips that cannot yield, assumed contact damping, no human model.

A figure from its own output

Paper, code and results

• README and method
• Experiments and results
• Code
• Tests

More in Open-source purpose-built robots

• Is the peak force of a feeding arm on the lips set by the lips' stiffness, the arm's force loop, or its approach lead?Is the peak force of a feeding arm on the lips set by lip stiffness, the force loop or the approach lead? Lip stiffness moves the mean peak from 0.32 to 2.02 N at 0.20 m/s (stylised; extends osrobot-assist).
• If the person being fed judges the spoon better as it nears the mouth, how much of a camera's value does a blind feeding arm get back?If the person being fed judges the spoon better as it nears the mouth, how much of a camera's value does a blind arm get back? A misjudgement shrinking to zero at the lips lifts the blind arm's safe share at 40 mm from 0.47 to 0.84 and restores every feed; stylised, extends osrobot-leannoise.
• If the person being fed misjudges the spoon, or sees it late, can a blind feeding arm still do without a camera?If the person being fed misjudges the spoon or sees it late, can a blind feeding arm still do without a camera? A 20 mm misjudgement drops the blind arm's safe share from 1.00 to 0.60 (camera arm 0.78); stylised, extends osrobot-lean.
• If the person being fed leans toward the spoon, can a blind feeding arm do without a camera?If the person being fed leans toward the spoon, can a blind feeding arm do without a camera? At 30 mm sway and 0.20 m/s the blind arm's safe share rises from 0.21 to 1.00 as the lean reaches 100 mm/s (stylised; extends osrobot-assist).
• When a pest window sets a deadline, is a scout-and-treater fleet or a fleet of inline weeding robots cheaper?When a pest window sets a deadline, is a scout-and-treater fleet or inline weeding robots cheaper? One scout cannot finish 16 fields faster than 5.3 to 32.5 h; pipeline/inline cost is 1.06 to 1.12 at 0.72 ha, 1.49 at 0.18 ha, and 0.87 to 0.93 at 1.62 ha where it can meet the deadline.
• If one scout drone feeds ground treaters in a pipeline, can a held fleet beat inline weeding robots?If one scout drone feeds ground treaters in a pipeline, can a held fleet beat inline weeding robots? One scout keeps only 1.0 to 1.3 treaters busy; overlapping the stages cuts the held-pair penalty to 1.04 at 0.72 ha fields and 0.86 at 1.62 ha, still losing on small fields. Assumed prices; scheduling over osrobot-pairprice's fits.

All 44 Open-source purpose-built robots projects →

Other research topics

Proper scoring & elicitation28Effort & peer prediction9Verification games & slashing19Detection & tolerances14Markets as routers13Prediction-market design9Paying contributors8Decentralised training systems23Digital twins & sim-to-real164LLM chip design loops40Robot manufacturing loops53Ambient AI assistant46Self-replicating manufacturing34Simulation-first design64Engineered clothing45Task-specific AI accelerators40Algorithmic chip-design loops42Open-source purpose-built robots44The software-engineering loop43Adversarial human imitation41Open-source residential construction41Autonomous multi-angle capture34Sensing, imaging and 3D31Energy supply and dense energy storage39Robot societies among people31Agentic co-design of low-cost robots27Laundry-hanging robots25Machine learning on qualitative data23Robots on the building site27Civilizations & group psychology1History & human sciences1

Produced with AI assistance (Claude). Results are from the code in this repository and are simulated or stylised unless the abstract says otherwise; nothing here implies affiliation with or endorsement by any lab, researcher or company cited. MIT licensed.