CLIPPER: Replayable Shortlisted Optimization for Repeated Spatial Coverage Planning

Julian Teusch; Jörg Philipp Müller; Monika Sester

cs.ROAug 27, 2026

CLIPPER: Replayable Shortlisted Optimization for Repeated Spatial Coverage Planning

Authors: Julian Teusch, Jörg Philipp Müller, Monika Sester

Organizations: Institute of Computer Science, Clausthal University of Technology, Germany · Institute of Cartography and Geoinformatics, Leibniz University Hannover, Germany

Abstract

Operational requirements developed with the City of Braunschweig frame municipal micromobility planning under geofenced exclusions, mandatory retained sites, spacing rules, and area-level caps. Each policy edit requires a new feasible plan; full-set greedy takes tens of seconds per alternative at city scale. We present CLIPPER (Constraint-exact Low-latency Iterative Planning with Pooled Evaluation and Replay). It forms bounded candidate pools but recomputes exact current gains and checks every active constraint before selection. Coverage from each candidate alone sets the initial order. Offline full-set scans measure gains omitted by the pool; online, a conservative bound triggers expansion or audit. CLIPPER-F gives each proposal group the same number of candidate slots. Across Braunschweig, Munich, and Berlin, its mean coverage over complete chains stays within 0.245 percentage points of full-set greedy under the same policy, with 13.6--28.9 times lower mean rollout time. CLIPPER-A instead distributes one shared candidate budget across the groups. Under its coverage-prioritized policy, it uses 9--15% of full-set greedy's rollout time under the same policy, with mean gaps of 1.82 percentage points in Braunschweig, 0.12 in Munich, and 0.27 in Berlin. Together, CLIPPER enables rapid, replayable comparison of recorded city-scale planning states while enforcing every encoded model constraint.

Figures & tables

Figure 1: CLIPPER execution contract.

\Omega

is the recorded scenario;

P_{t}

is the pool at round

t

;

\hat{\delta}_{t}

bounds the exact omitted gain

\delta_{t}

. Solid arrows show timed execution; screening and full-set audits are excluded from rollout time.

Panel of Figure 2 — Figure 2: Braunschweig CLIPPER-F diagnostic replay using a $25\text{\,}\mathrm{m}$ candidate-grid resolution. At $E_{5}$ , $162$ candidates fall inside exclusions, $90$ sites are mandatory, and $25\text{\,}\mathrm{m}$ spacing applies; the plan retains $443$ baseline sites and selects $157$ replacements. Panel (d) shows retained, removed, and added sites. The benchmark edits are constructed rather than recorded municipal actions.

Mode	Policy	City	Coverage: CLIPPER/control (%)	Gap	Rollout: CLIPPER/control (s)	Speedup
CLIPPER-F ( $K=1024$ )	balanced	BS	90.1/90.4	0.245	1.762/24.029	$13.6\times$
		MUC	69.7/69.7	0.003	1.493/22.943	$15.4\times$
		BER	59.5/59.5	0.001	1.825/52.685	$28.9\times$
CLIPPER-A ( $8192$ slots)	relaxed	BS	95.0/96.8	1.82	3.219/28.343	$8.8\times$
		MUC	81.1/81.2	0.12	3.360/22.931	$6.8\times$
		BER	69.3/69.5	0.27	4.415/48.826	$11.1\times$

Table 1: Full-data means over

E_{0},\ldots,E_{10}

. Paired cells give CLIPPER/control; gap is control minus CLIPPER coverage in percentage points, and speedup is control/CLIPPER rollout time. BS/MUC/BER denote Braunschweig/Munich/Berlin. Coverage is rounded to one decimal; gaps use unrounded means. CLIPPER-F and CLIPPER-A use different cap policies.

State	Core (%)	Lock (%)	Hot	Space (m)	Gap	Speedup	Gap	Speedup	Gap	Speedup
	Constructed edit schedule				Braunschweig		Munich		Berlin
$E_{0}$	0.0	0.0	0	0	0.377	12.8	-0.010	15.7	0.002	28.7
$E_{1}$	2.5	0.0	0	0	0.377	40.7	-0.010	47.9	0.002	81.4
$E_{2}$	5.0	0.0	0	0	0.377	39.5	0.016	49.1	0.002	84.3
$E_{3}$	5.0	10.0	0	0	0.319	40.7	0.004	46.5	0.002	72.5
$E_{4}$	7.5	10.0	0	0	0.319	38.4	0.004	44.7	0.002	72.7

Table 2: Complete chain and CLIPPER-F performance. Core is the baseline share assigned

75\text{\,}\mathrm{m}

exclusions; Lock is the mandatory share; Hot counts

150\text{\,}\mathrm{m}

exclusion halos; Space is minimum network spacing (zero disables it). Gap is control minus CLIPPER coverage in percentage points; speedup is control/CLIPPER rollout time. Each state is recomputed.

Greedy Optimization

See all 12 papers

CLIPPER Beyond Shortlisting: Auditable Decision Support for Changing Municipal Micromobility Policies
Sep 30, 2026Julian Teusch, Jörg Philipp Müller, Monika SesterCombinatorial Optimization Urban Planning
Institute of Computer Science Clausthal University of Technology Clausthal-Zellerfeld, Germany · Institute of Cartography and Geoinformatics Leibniz University Hannover Hannover, Germany
CityPlanner: A Sandbox Agent for Executable Urban Planning
Sep 9, 2026Wentao Zhang, Jingyuan Wang, Zetong Zhou +2Agentic RL Urban Planning
School of Computer Science and Engineering, Beihang University, Beijing, China · MIIT Key Laboratory of Data and Decision Intelligence, Beihang University, Beijing, China
From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation
Jul 17, 2026Himel Dev, Tanmoy Sen, Madhusudan Basak +1Travel Planning User Preference Modeling
Tech LLC · University of Virginia · University of Massachusetts Amherst

Sep 30, 2026J/K move · Enter open · S save

CLIPPER Beyond Shortlisting: Auditable Decision Support for Changing Municipal Micromobility Policies

Julian Teusch, Jörg Philipp Müller, Monika Sester

Institute of Computer Science Clausthal University of Technology Clausthal-Zellerfeld, Germany · Institute of Cartography and Geoinformatics Leibniz University Hannover Hannover, Germany

Combinatorial Optimization Urban Planning Greedy Optimization

Open paper AskPDF arXiv

In municipal planning workshops, planners and other stakeholders compare shared-micromobility parking policies by varying no-parking zones, retained sites, spacing, or area allocations. Each edit changes feasible sites and how much demand they cover, so the alternative must be reoptimized on the same spatial data. Full-set greedy, the transparent reference for this task, takes tens of seconds per alternative at city scale. We present Constraint-exact Low-latency Iterative Planning with Pooled Evaluation and Replay (CLIPPER), an optimizer with audit functions developed for requirements elicited with the City of Braunschweig. In each greedy round, it forms a deterministic candidate pool of bounded size, computes how much still-uncovered demand each candidate would add, and rejects candidates that violate an active constraint. An optional offline audit scans every remaining feasible candidate and records what the restricted pool omitted. We evaluate these functions on complete eleven-state edit chains (

E_0,\ldots,E_{10}

) in Braunschweig, Munich, and Berlin. With

K=1024

candidates per group, the fixed-width mode CLIPPER-F has mean coverage gaps to full-set greedy under the same policy of 0.245, 0.003, and 0.001 percentage points in Braunschweig, Munich, and Berlin, respectively, while mean rollout time falls by factors of 13.6--28.9; no audited run terminates while a candidate outside the pool could still increase coverage. Plans computed from two checksummed versions of Braunschweig's official no-parking-zone data differ in 30 of about 540 selected sites although coverage moves by only about 0.1 percentage points. These changes still require municipal assessment and implementation. The findings inform a proposed municipal process that versions policy inputs, reports site changes beside coverage, and scans the full candidate set before a final decision.

Abstract

Greedy Optimization

Explore similar work

CLIPPER Beyond Shortlisting: Auditable Decision Support for Changing Municipal Micromobility Policies

CityPlanner: A Sandbox Agent for Executable Urban Planning

From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation