ANCHOR: A Port-Hamiltonian Model for Forecasting Team Dynamics in Human-in-the-Loop Systems
Organizations: University of California, Irvine Irvine, CA, USA
Abstract
Cyber-physical-human systems close a loop around people by sensing human behavior, predict it and act on it. Human teams are a natural target, because collaboration breaks down in ways that a timely prompt could prevent. Collaborative mixed reality makes this loop practical, since each headset senses who speaks, where its wearer looks and who stands together, and it can deliver a light prompt. In this loop, the headsets are sensors, the prompts are actuators and the team is the plant. Closing the loop needs a plant model that is small enough to learn from few teams, safe to iterate and readable by a designer. We propose ANCHOR, which models a team as a ball in an energy bowl. The bottom of the bowl is where the team rests, and it is set by the team's recent behavior, its own history and other teams. Formally, ANCHOR is a switched port-Hamiltonian system with 52 parameters, and each part stands for a testable claim from team psychology. Because of this structure, for any fitted parameters, a forecast moves away from rest only when task progress or a prompt pushes it, and prompts of bounded size that are spaced in time move it a bounded distance. On \nGroups{} four-person teams held out from training, a team that drifts from its usual behavior returns most of the way within half a minute. After 32 s, about 24% of the deviation remains, and ANCHOR predicted 30%. Forecasts are clearly better when the resting point blends its three sources than when it uses one. ANCHOR matches the accuracy of a black-box baseline with about 40,000 parameters. It anticipates conversation collapse with an AUROC of 0.85. In simulation under assumed prompt effects, it removes 2.2 times as much breakdown time per prompt as periodic prompting.
Figures & tables
| Block | Size | Each entry |
|---|---|---|
| Speaking | 4 | Member’s speaking time |
| Attention | 6 | Pair’s simultaneous gaze on one image |
| Proximity | 6 | Pair’s time within 0.46 m |
| Team | 4 | Mean of each behavior; speaking balance |
| Question | Part of the model | What it means for a team | Sensor source |
| Where does it rest? | Resting point (P1) | The pattern it returns to, anchored on its past and other teams | Sociogram history |
| State across levels (P3) | Team states emerge from members and pairs but are not reducible to them | Audio, gaze, head pose | |
| How does it return? | Energy , regulation (P2) | Distance from the pattern, and how fast deviations are regulated back | — |
| Link gains in , , | Who interacts with whom constrains coordination | Team structure | |
| What moves it away? | Task input (P5) | Task progress shifts the pattern | Task logs |
| Phase (P4) | Exploration and consolidation regulate differently | Task logs |
| Part | Symbols (values) | Count |
|---|---|---|
| Stiffness | (3), (5), (4), (1) | 13 |
| Regulation | ||
| Exchange | ||
| Port | ||
| Anchors | ||
| Total | 52 |
| Part | Hypothesis | Alternative tested | Member and pair nMSE | Team nMSE | Verdict |
|---|---|---|---|---|---|
| Resting point (P1) | Teams return to a point set by recent behaviour, their own history and other teams | from recent behaviour only | +19.3% (17/17, 2e-5) | +16.5% (14/17, 0.004) | supported |
| from session history only | +3.4% (14/17, 0.035) | +9.7% (14/17, 0.020) | supported | ||
| Regulation (P2) | Deviations fade, so modelling the return helps at 16–48 s | attractor only, no dynamics | +11.3% (17/17, 2e-5) | +8.5% (15/17, 5e-4) | supported |
| Team state (P3) | Team states are not reducible to members and pairs | computed from member forecast | – | +270.3% (16/17, 3e-5) | supported |
| Shared link gains in | Coordinates with the same role can share one value | unconstrained matrices | +14.4% (16/17, 4e-4) | +9.7% (17/17, 2e-5) | supported |
| Phase (P4) | Teams regulate differently in exploration and consolidation | single phase | +0.1% (9/17, 0.782) | -0.4% (7/17, 0.611) | on par |
| Member and pair | Team | |||||
|---|---|---|---|---|---|---|
| Model | Params | 16–48 s | 16–256 s | 16–48 s | 16–256 s | Verdict |
| Attractor only | +11.3 | +1.5 | +8.5 | +0.1 | better | |
| Persistence | +38.8 | +49.2 | +32.1 | +43.5 | better | |
| Recent average | +23.1 | +22.6 | +16.2 | +22.1 | better | |
| Session mean | +28.0 | +13.1 | +46.4 | +36.4 | better | |
| VAR(2) | +15.3 | +10.4 | +16.6 | +11.2 | better | |
| Conversation collapse | Loss of shared focus | Low proximity | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Model | AUC | Det. | Warn | AUC | Det. | Warn | AUC | Det. | Warn |
| ANCHOR (ours) | 0.85 | 74% | 31 | 0.76 | 57% | 35 | 0.66 | 34% | 29 |
| Attractor only | 0.85 | 73% | 31 | 0.76 | 56% | 35 | 0.62 | 28% | 31 |
| Recent average | 0.83 | 68% | 32 | 0.76 | 58% | 37 | 0.63 | 26% | 32 |
| VAR(2) + aug. | 0.80 | 64% | 30 | 0.69 | 43% | 36 | 0.65 | 39% | 28 |
| Ridge + aug. | 0.80 | 60% | 31 | 0.71 | 42% | 35 | 0.68 | 43% | 32 |
Appendix figures & tables22 assets
Supplementary material from the paper’s appendix.
Appendix
| Symbol | Meaning |
|---|---|
| , | window at which a forecast starts; steps ahead (16 s each) |
| , | team state (20 numbers); its forecast |
| resting point (equilibrium, or attractor) | |
| recent, session and population anchors | |
| learned anchor weights | |
| deviation from the resting point |
| Term | Circuit | Team |
|---|---|---|
| Energy | Charge stored in capacitors | Distance from the usual pattern |
| Regulation | Resistors, which dissipate | Self-regulation back to the pattern |
| Exchange | Lossless coupling | Talk turning into shared focus |
| Port | Voltage source | Task progress shifting the pattern |
| Kick | Current pulse | A prompt to the team |
| Phase | Switch position | Exploration or consolidation |
| Recent anchor , decay | 5 windows, 0.7 |
| Training horizon / evaluation horizon | 8 / 16 windows |
| Phase threshold on | 0.5 |
| Stability window for | 4 windows (64 s) |
| Optimizer | L-BFGS-B, 300 it., exact gradients |
| Regularization | ( unconstrained) |
| VAR(2) ridge / direct ridge | 1 / 10 |
| Shift | Matched | |||||||
|---|---|---|---|---|---|---|---|---|
| Corruption | +obs | ANCHOR | VAR | MLP | +obs | ANCHOR | VAR | MLP |
| Noise | 1.14 | 1.13 | 1.13 | 1.21 | 1.05 | 1.05 | 1.31 | 1.18 |
| Noise | 1.47 | 1.47 | 1.17 | 1.29 | 1.11 | 1.11 | 1.38 | 1.20 |
| Noise | 2.99 | 2.97 | 1.29 | 1.46 | 1.14 | 1.14 | 1.38 | 1.23 |
| Dropout | 1.01 | 1.01 | 1.12 | 1.16 | 1.01 | 1.01 | 1.12 | 1.16 |
| Dropout | 1.03 | 1.03 | 1.13 | 1.17 | 1.04 | 1.03 | 1.13 | 1.17 |
| Member and pair | Team | |||
|---|---|---|---|---|
| Variant | Params | 16–48 s | 16–256 s | 16–256 s |
| Selected model | 52 | 0.758 | 1.082 | 1.002 |
| 1st-order, diag | 45 | 0.762 | 1.088 | 1.011 |
| 1st-order, diag, switched | 54 | 0.760 | 1.083 | 1.002 |
| 1st-order, equiv | 69 | 0.769 | 1.093 | 1.013 |
| 1st-order, equiv, switched | 95 | 0.771 | 1.086 | 0.998 |
| Model | Speaking | Attention | Proximity | Speaking |
|---|---|---|---|---|
| level | density | density | balance | |
| ANCHOR (ours) | 0.86 | 1.19 | 1.13 | 0.82 |
| Attractor only | 0.88 | 1.20 | 1.14 | 0.82 |
| Persistence | 1.22 | 1.61 | 1.58 | 1.25 |
| Recent average | 1.07 | 1.38 | 1.35 | 1.02 |
| VAR(2) + aug. | 0.97 | 1.61 | 1.25 | 0.86 |
| Member and pair | Team | |||
|---|---|---|---|---|
| Model | 16–48 s | 16–256 s | 16–48 s | 16–256 s |
| Attractor only | +11.3% (17/17, 2e-5) | +1.5% (12/17, 0.057) | +8.5% (15/17, 5e-4) | +0.1% (9/17, 0.747) |
| Persistence | +38.8% (17/17, 2e-5) | +49.2% (17/17, 2e-5) | +32.1% (16/17, 3e-5) | +43.5% (17/17, 2e-5) |
| Recent average | +23.1% (17/17, 2e-5) | +22.6% (16/17, 3e-5) | +16.2% (16/17, 3e-4) | +22.1% (14/17, 0.001) |
| Session mean | +28.0% (17/17, 2e-5) | +13.1% (12/17, 0.006) | +46.4% (16/17, 5e-5) | +36.4% (14/17, 0.002) |
| VAR(2) | +15.3% (16/17, 3e-5) | +10.4% (12/17, 0.080) | +16.6% (14/17, 5e-4) | +11.2% (11/17, 0.071) |
| Member and pair | Team | Top | ||||
| Model | Params | 16–48 s | 16–256 s | 16–48 s | 16–256 s | pair |
| ANCHOR (ours) | 0.758 | 1.082 | 0.705 | 1.002 | 30% | |
| ANCHOR + observer | 0.759 | 1.082 | 0.707 | 1.004 | 30% | |
| Attractor only | 0.848 | 1.099 | 0.775 | 1.009 | 30% | |
| Persistence | 1.049 | 1.627 | 0.913 | 1.416 | 31% | |
| Recent average | 0.927 | 1.330 | 0.807 | 1.206 | 31% | |
| Coordinate | Shift | Cons. | Expl. | |||
|---|---|---|---|---|---|---|
| Speaking (member) | 0.44 | 0.19 | 0.37 | -0.058 | 26 | 37 |
| Attention (pair) | 0.18 | 0.81 | 0.01 | -0.073 | 17 | 28 |
| Proximity (pair) | 0.10 | 0.41 | 0.50 | -0.066 | 28 | 55 |
| Team speaking level | 0.34 | 0.13 | 0.53 | -0.042 | 38 | 32 |
| Team attention density | 0.35 | 0.58 | 0.07 | -0.060 | 22 | 43 |
| Team proximity density | 0.19 | 0.46 | 0.35 | -0.111 | 15 | 78 |
| Irreversibility | Rotational share | Min. autocorrelation | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Signal | Bin (s) | Team | Surr. | Team | Surr. | Team | Surr. | ||
| Speaking | 1 | 0.279 | 0.293 | 0.715 | 0.010 | 0.014 | 0.782 | -0.063 | -0.081 |
| Speaking | 2 | 0.287 | 0.309 | 0.767 | 0.034 | 0.034 | 0.326 | -0.066 | -0.092 |
| Speaking | 4 | 0.270 | 0.288 | 0.727 | 0.093 | 0.087 | 0.220 | -0.069 | -0.101 |
| Speaking | 8 | 0.298 | 0.295 | 0.624 | 0.185 | 0.185 | 0.473 | -0.052 | -0.084 |
| Proximity | 1 | 0.127 | 0.135 | 0.480 | 0.021 | 0.016 | 0.063 | +0.030 | -0.038 |
| 32 s | 64 s | 96 s | ||||
|---|---|---|---|---|---|---|
| Model | all | onset | all | onset | all | onset |
| Conversation collapse | ||||||
| ANCHOR (ours) | 0.80 | 0.83 | 0.78 | 0.80 | 0.76 | 0.78 |
| Attractor only | 0.81 | 0.83 | 0.78 | 0.79 | 0.76 | 0.78 |
| Persistence | 0.76 | 0.73 | 0.75 | 0.72 | 0.72 | 0.69 |
| Recent average | 0.80 | 0.82 | 0.78 | 0.78 | 0.76 | 0.78 |
| Threshold | Collapse | Focus | Low prox. | Predictive best | vs. periodic |
|---|---|---|---|---|---|
| 15th | 0.75 / 0.76 | 0.77 / 0.77 | 0.65 / 0.69 | 5/12 | 3.9 |
| 25th (main) | 0.85 / 0.85 | 0.76 / 0.76 | 0.66 / 0.68 | 8/12 | 2.2 |
| 35th | 0.75 / 0.77 | 0.77 / 0.79 | 0.66 / 0.69 | 8/12 | 1.4 |
| Cue | Plant | None | Periodic | Reactive | Forecast | ANCHOR-predictive |
|---|---|---|---|---|---|---|
| Balance | ANCHOR | 13.3 | 11.4 (4.7) | 11.4 (3.8) | 10.8 (5.1) | 12.1 (1.8) |
| Attention | ANCHOR | 11.5 | 5.7 (4.7) | 5.6 (2.3) | 5.3 (1.9) | 5.6 (1.7) |
| Balance | VAR | 12.6 | 11.0 (4.7) | 10.4 (3.4) | 10.0 (4.8) | 11.5 (1.7) |
| Attention | VAR | 12.5 | 7.6 (4.7) | 7.0 (2.8) | 9.0 (1.9) | 9.7 (1.5) |
| Cue | Plant | None | Periodic | Reactive | Forecast | ANCHOR-predictive | |
|---|---|---|---|---|---|---|---|
| Balance | ANCHOR | 0.25 | 13.3 | 12.4 / 0.18 | 12.3 / 0.24 | 12.0 / 0.23 | 12.8 / 0.34 |
| Balance | ANCHOR | 0.50 | 13.3 | 11.4 / 0.38 | 11.4 / 0.47 | 10.8 / 0.47 | 12.1 / 0.62 |
| Balance | ANCHOR | 1.00 | 13.3 | 9.9 / 0.68 | 9.8 / 0.94 | 8.9 / 0.93 | 9.8 / 1.06 |
| Attention | ANCHOR | 0.25 | 11.5 | 8.2 / 0.65 | 7.5 / 1.37 | 7.2 / 1.62 | 7.2 / 1.64 |
| Attention | ANCHOR | 0.50 | 11.5 | 5.7 / 1.15 | 5.6 / 2.41 | 5.3 / 2.98 | 5.6 / 3.22 |
| Attention | ANCHOR | 1.00 | 11.5 | 3.1 / 1.68 | 4.0 / 3.81 | 3.9 / 5.08 | 4.2 / 5.28 |
Human-in-the-Loop AI
Human-in-the-loop AI combines human feedback, oversight, and decision-making with machine learning and autonomous systems.
See all 312 papers