Product mode: not part of the pre-registered experiment. Simulated in MuJoCo and untested on hardware. A recommendation is a simulation ranking under the stated conditions, not a hardware guarantee.
Build certificate: Hotel delivery mock-up
Press the wall-mounted elevator call button, open the hinged room door with a pull handle, then pick the parcel from the bench and place it into the delivery tray behind the door.
tool change Tool change: Drawer-pull > Force-controlled > Suction · the Studio's recommendation
Result
| Full-task completion | Runs | Weakest step | Median cycle (with changes) | Fidelity |
|---|---|---|---|---|
| 100% | 8 | open_door (100%) | 63.8 s | approximation |
Why: The only setup that completed the task: 100% of the runs, 63.8 s cycle.
Setup
| Tool | Effector | Family | Fidelity | Steps |
|---|---|---|---|---|
| 0 | Drawer-pull hook tool | catalog gripper | rigid | press_button |
| 1 | Force-controlled parallel gripper, 48 mm stroke | catalog gripper | rigid | open_door |
| 2 | Suction cup, 25 mm bellows | suction | approximation | place_parcel |
| Tools | Actuators | Carried (heaviest segment) | Built in total | Changes per run |
|---|---|---|---|---|
| 3 | 2 | 0.764 kg | 1.035 kg | 2 |
changer_plate_tool0.stl: changer tool-side plate for tool 0: 63 mm x 26 mm, 20 mm pass-through bore; 85 g printed; watertight single solid: True.
changer_plate_tool1.stl: changer tool-side plate for tool 1: 63 mm x 26 mm, 20 mm pass-through bore; 85 g printed; watertight single solid: True.
changer_plate_tool2.stl: changer tool-side plate for tool 2: 63 mm x 26 mm, 20 mm pass-through bore; 85 g printed; watertight single solid: True.
Per step
| Step | Primitive | Object | Tool | Success | Failures | Fidelity | Caveats |
|---|---|---|---|---|---|---|---|
| press_button | push | call_button | 0: Drawer-pull hook tool | 100% | none | rigid | |
| open_door | hook_pull | room_door | 1: Force-controlled parallel gripper, 48 mm stroke | 100% | none | rigid | |
| place_parcel | grasp (as suction) | parcel | 2: Suction cup, 25 mm bellows | 100% | none | approximation | Suction cup (approximation): a compliant lip of rigid segments on a bellows spring with a limited tilt; the seal is a geometric test (every lip segment touching the face, part material under 13 rays inside the lip) gating a MuJoCo adhesion actuator capped at vacuum x lip area (at most 60 kPa). The lip must touch the face: no pull across a gap. Not modelled: air flow, leak rate, porosity, vacuum build-up time (the vacuum follows the shared close ramp and is cut the control tick the seal is lost), lip material hysteresis, peel dynamics beyond the contact distribution. The lip's friction is the part's. Treat suction results as a screen, then verify on hardware. |
Conditions
Every compared setup ran the same conditions and seeds in the same order. A seed draws the friction jitter (+-10%) and a +-0.5 mm aim jitter; the placement errors below are hidden from the controllers.
| Condition | Seed | Placement error x/y (mm) | Run | Cycle | Trajectory |
|---|---|---|---|---|---|
| nominal | 0 | none | completed | 63.8 s | 84c8e608c583c606 |
| place01 | 1 | call_button +0.31/-0.19; parcel +1.73/+0.13; room_door +0.54/+1.44; tray -0.98/-0.17 | completed | 63.8 s | 5496c86ce5ba9d52 |
| place02 | 2 | call_button +0.09/+0.24; parcel +1.04/-0.23; room_door +0.41/-0.25; tray +0.77/-1.92 | completed | 63.8 s | ae1b73b91fd0c360 |
| place03 | 3 | call_button -1.50/-1.83; parcel +1.81/-0.55; room_door +0.90/+1.98; tray +0.48/-1.97 | completed | 63.8 s | 79e70dc285f9a5a3 |
| place04 | 4 | call_button -0.00/+1.47; parcel +0.18/+0.81; room_door -0.79/-1.13; tray +1.77/-1.51 | completed | 63.8 s | 9a756b82cde4405e |
| place05 | 5 | call_button -1.63/-1.20; parcel -1.07/+0.45; room_door +1.41/-1.59; tray -0.75/+1.15 | completed | 63.8 s | d7e1e9673f649fee |
| place06 | 6 | call_button -0.23/+0.27; parcel -0.53/+0.32; room_door +0.66/-0.03; tray -1.48/-1.31 | completed | 63.8 s | 5f965ca08f972069 |
| place07 | 7 | call_button -1.50/+1.48; parcel -0.89/+1.97; room_door -0.58/+1.72; tray +0.24/+1.08 | completed | 63.8 s | 52e2b8c6b106903c |
Compared setups
| Setup | Kind | Completion | Weakest step | Cycle | Tools | Eligible |
|---|---|---|---|---|---|---|
| Tool change: Drawer-pull > Force-controlled > Suction | tool change | 100% | open_door 100% | 63.8 s | 3 | yes |
| Two-tool head: Force-controlled parallel + Suction cup | multi head | 0% | open_door 0% | 12.8 s | 2 | never completed the task (stops at open_door in 8/8 runs: out_of_reach 8x) |
| Two-tool head: Force-controlled parallel + Suction cup | multi head | 0% | open_door 0% | 12.8 s | 2 | never completed the task (stops at open_door in 8/8 runs: out_of_reach 8x) |
| Angular-jaw gripper of an open hobby arm (best single off-the-shelf) | single | 0% | open_door 0% | 10.6 s | 1 | never completed the task (stops at press_button in 8/8 runs: criterion_not_met 8x) |
Against the best single off-the-shelf effector: completion +100 points, cycle +53.2 s, +2 tools.
Sensitivity to change times
Re-ranked with tool changes of 3, 6 and 12 s and head switches of 0.75, 1.5 and 3 s: the recommendation is the same for every pair; the order changes in 0 of 15 pairs.
Assumed constants
Equal for every candidate; none is sourced from a target arm or changer.
| Constant | Value | Note |
|---|---|---|
| roll_torque_nm | 15 N m | wrist roll torque limit |
| roll_speed_max_deg_s | 180 deg/s | wrist roll speed cap |
| pitch_range_deg | 90 deg | wrist pitch limit, +- from straight down |
| pitch_speed_dps | 180 deg/s | wrist pitch speed cap |
| pitch_torque_nm | 15 N m | wrist pitch torque limit |
| tool_change_s | 7.5 s | automatic tool change time (a fixed clock advance) |
| present_s | 1.5 s | multi-tool head switch time (a fixed tilt, not simulated) |
| changer_master_kg | 0.25 kg | tool changer master plate (stays on the wrist) |
| changer_tool_plate_kg | 0.1 kg | tool changer plate on every tool |
| changer_stack_mm | 52 mm | tool changer stack height |
| arm_payload_kg | 3 kg | largest tool stack the arm may carry; heavier setups are refused |
| bracket_density_kg_m3 | 1300 kg/m^3 | printed carbon-filled polymer bracket |
| placement_error_mm | 2 mm | per-object placement error of the condition grid (uniform) |
| simplicity_per_extra_effector | 0.05 rate | integrator rule R01: completion a setup must add per added effector or changer |
| simplicity_step_floor | 0.5 rate | integrator rule R01: a weakest step under this fails outright |
| tie_margin | 0.05 rate | completion-rate tie among setups of the same complexity |
| cycle_margin | 0.1 fraction | among setups of the same complexity, a simpler one may be this much slower |
| soft_arm_max_part_kg | 2.5 kg | integrator rule R09: the heaviest part a soft arm may carry |
| hook_min_mm | 5 mm | a rigid tool hooks if its tip reaches this far sideways past the tool and flange |
| hook_throat_mm | 6 mm | room a lip needs between a hook and the flange, else the flange blocks it |
| process_torque_nm | 4 N m | integrator rule R05: tightening a threaded member to this torque or more needs a nut runner (1 N m above hand-tight) |
| socket_fit_mm | 0.5 mm | a nut runner's socket drives a hex at most this much under its own size |
| sweep_clearance_mm | 5 mm | multi-tool head swept-volume clearance |
Caveats
- Suction cup (approximation): a compliant lip of rigid segments on a bellows spring with a limited tilt; the seal is a geometric test (every lip segment touching the face, part material under 13 rays inside the lip) gating a MuJoCo adhesion actuator capped at vacuum x lip area (at most 60 kPa). The lip must touch the face: no pull across a gap. Not modelled: air flow, leak rate, porosity, vacuum build-up time (the vacuum follows the shared close ramp and is cut the control tick the seal is lost), lip material hysteresis, peel dynamics beyond the contact distribution. The lip's friction is the part's. Treat suction results as a screen, then verify on hardware.
- The floating wrist abstracts the arm: there is no arm reach or arm collision model.
- Presenting a multi-tool head is a fixed tilt per segment plus a fixed time, not a simulated motion.
- A tool change is a fixed time, not a simulated docking.
- Controllers are scripted and open-loop on the placement error.
- A recommendation is a simulation ranking under the stated conditions, not a hardware guarantee.
Provenance
| Item | Value |
|---|---|
| Contract | rtt-effectors/2 |
| Task id | dc0ae4f82a5123cc7039f7ac2e35fe3b54399c63dd4443c5cc50cb24c33e3243 |
| Setup id | e38465aad8735559314fe4beca2de13556c1bc614e0c13a4274a9bf2f046b6fc |
| Fairness hash | 82b5bcdac3b461e77bc17444036a535a9acb32f29bafd804947228e68090636d |
| Controllers | default |
| Screen | 183 runs on 3 conditions |
Product mode: not part of the pre-registered experiment. Simulated in MuJoCo and untested on hardware. A recommendation is a simulation ranking under the stated conditions, not a hardware guarantee.