# Adaptive Zonotope Safety Shield

- ID: 2753
- Canonical URL: https://synthcore.org/idea/2753/adaptive-zonotope-safety-shield
- API JSON: https://synthcore.org/api/idea/2753.json
- API Markdown: https://synthcore.org/api/idea/2753.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.26852](https://arxiv.org/abs/2608.26852)
- Category: dynamics
- Solves: stability, accuracy, sample-efficiency
- ML areas: rl, optimizer, training-dynamics
- Math tags: control-theory, dynamical-systems, linear-algebra, geometry
- Ratings: usefulness 7/10; difficulty 6/10; novelty 7/10

## Idea description

Wrap a neural policy with an online disturbance estimator and a zonotopic reachability shield. Instead of rejecting actions using a permanently worst-case disturbance set, update the disturbance zonotope from observed transition residuals and accept an action only when the resulting reachable set remains inside the safe region.

## Mathematical statement

For a discrete-time plant x_(t+1) = f(x_t, u_t, w_t), use a local affine model x_(t+1) approximately equals A_t x_t + B_t u_t + d_t + w_t, where x_t is the state, u_t is the neural-policy action, A_t and B_t are local Jacobians or fitted linear dynamics, d_t is a nominal offset, and w_t is bounded disturbance. Represent the current state and disturbance as zonotopes X_t = c_x,t + G_x,t [-1,1]^p and W_t = c_w,t + G_w,t [-1,1]^q. The one-step reachable set is X_(t+1) = A_t X_t plus B_t u_t plus d_t plus W_t, with center c_x,(t+1) = A_t c_x,t + B_t u_t + d_t + c_w,t and generator matrix G_x,(t+1) = [A_t G_x,t, G_w,t]. Given a safety set S, accept the action only if an over-approximation of X_(t+1) is contained in S. For observed residuals r_i = x_(i+1) - f_nom(x_i,u_i), update the disturbance center and axis-aligned radii using c_w,j <- (1-alpha)c_w,j + alpha median_i(r_i,j) and q_j <- max((1-beta)q_j, max_i |r_i,j - c_w,j| + epsilon), where q_j defines W_t = c_w + diag(q) zeta with ||zeta||_infinity <= 1, alpha and beta are adaptation rates, and epsilon is a robustness margin.

## Key formulas

- x_(t+1) = f(x_t, u_t, w_t),   X_(t+1) = A_t X_t plus B_t u_t plus d_t plus W_t
- X_t = c_x,t + G_x,t [-1,1]^p,   W_t = c_w,t + G_w,t [-1,1]^q
- c_x,(t+1) = A_t c_x,t + B_t u_t + d_t + c_w,t,   G_x,(t+1) = [A_t G_x,t, G_w,t]
- u_t is accepted if and only if X_(t+1)(u_t) is a subset of S;   q_j <- max((1-beta)q_j, max_(i in batch) |r_i,j - c_w,j| + epsilon)

## Implementation notes

1. Integration point: place the shield between a policy network pi_theta and the environment, and optionally use the same reachable-set violation as a policy-training penalty. For a proposed action, linearize a differentiable simulator around the current state, or estimate A_t and B_t with finite differences or a small local dynamics model. 2. Pseudocode: propose u = policy(x); after the next state is observed, compute residual r = x_next - f_nom(x,u); update c_w and q using the robust batch rule above; construct X_next from the current state zonotope and W; if X_next is outside S, project u toward a backup action u_safe or replace it with the action minimizing zonotope constraint violation. During training, add lambda times normalized reachable-set violation to the policy loss. 3. Computed from the paper mechanism: zonotope propagation, set containment, and online disturbance refinement. Estimated empirically: local Jacobians, residual statistics, epsilon, and the probability that the estimated disturbance set covers future residuals. Maintain a held-out residual-coverage monitor and never shrink q below a calibrated quantile plus epsilon. 4. First cheap experiment: train PPO on a two-dimensional point mass with unknown bounded acceleration disturbances, comparing PPO, a fixed worst-case box shield, and the adaptive shield. Sweep disturbance magnitude and adaptation rate. The quantitative prediction is that the adaptive shield's reachable-set generator norm and action-rejection rate decrease after residual burn-in while empirical disturbance coverage remains above 1 minus delta. If the true disturbance scale jumps beyond the learned set, coverage should fail within one batch and q should expand. Measure the largest disturbance magnitude with zero constraint violations over 1000 episodes; the adaptive method should approach the fixed-shield safety boundary within 20 percent while rejecting fewer actions.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: no_effect
- Verdict: Built and numerically verified an adaptive axis-aligned disturbance zonotope shield with affine reachability and online median/max-radius updates. The mechanism manifested: zonotope box containment had 0 disagreements over 3000 cases, learned q tracked disturbance amplitude plus epsilon within 0.00292, and a disturbance jump expanded q in the first batch with 100% coverage. However, the tiny shield comparison showed no efficiency or safety win: adaptive rejection was 70.08% versus fixed 66.86%, with violation rates 67.49% versus 66.86%.

### Mechanism check

- Verdict: Built and numerically verified an adaptive axis-aligned disturbance zonotope shield with affine reachability and online median/max-radius updates. The mechanism manifested: zonotope box containment had 0 disagreements over 3000 cases, learned q tracked disturbance amplitude plus epsilon within 0.00292, and a disturbance jump expanded q in the first batch with 100% coverage. However, the tiny shield comparison showed no efficiency or safety win: adaptive rejection was 70.08% versus fixed 66.86%, with violation rates 67.49% versus 66.86%.
- Confidence: 8/10
- Limitations: This is a deterministic toy affine point-mass experiment, not PPO or a learned nonlinear dynamics model. It uses axis-aligned disturbance generators, a zero-action backup, short finite episodes, and does not test multi-step reachability, calibration under distribution shift beyond one jump, computational overhead, or statistically repeated seeds.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.58435
- Paired wins: 4/8
- Benchmark verdict: no significant win

## Artifacts

- [adaptive_shield_experiment.py](https://synthcore.org/code/1087/adaptive_shield_experiment.py)
- [bench_report.json](https://synthcore.org/code/1087/bench_report.json)
- [report.md](https://synthcore.org/code/1087/report.md)
- [report_bench_2026-09-02T001641.md](https://synthcore.org/code/1087/report_bench_2026-09-02T001641.md)
- [results.json](https://synthcore.org/code/1087/results.json)
- [stage2_bench.py](https://synthcore.org/code/1087/stage2_bench.py)
- [Download all files as ZIP](https://synthcore.org/download/1087)

## Disclaimer

AI-generated research hypothesis, automatically tested. Not peer-reviewed.