Evolutionary computation researcher at Connecticut College: hexapod gait evolution and niched game-agent co-evolution
2
papers here
2
reviewed by Evolve
0
first-author
2
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Output volume is not yet scored: publication counts, venue types, and yearly production are not available in the current snapshot. This axis would measure total research output and how it is distributed over time.
Impact—
Impact is not yet scored: citation counts, h-index, and venue influence are absent from the current data. This axis would measure how widely the work is cited and taken up by other researchers.
Focus0/100
The focus score is 0 on the 0–100 scale, and the field distribution explains it: output splits evenly — 0.5 evolutionary robotics and 0.5 evolutionary computation (game AI / multi-agent systems). Current work thus straddles two subfields rather than concentrating in one, spanning embodied robot evolution and competitive agent co-evolution in parallel.
Collaboration22/100
The collaboration score is 22 out of 100, derived from only 2 distinct co-authors in the record: Gary B. Parker and Jim O'Connor. Research here is a small, stable-team effort rather than a broad network; current work stays inside this tight circle and has not yet extended to wider institutional or international collaboration.
Activity—
Activity is not yet scored: yearly publication cadence and recent-output trends are missing from the current record. This axis would measure publishing pace and sustained research engagement across recent years.
Reproducibility38/100
Reproducibility scores 38, the mean across the 2 papers reviewed. Readiness is rated medium for the hexapod gait preprint and low for the Core agents work; both reviews flag the same gaps — no statistical significance testing, missing baselines (centralized GA; external rivals), and figure-only results.
Research summary
John Asaro, affiliated with Connecticut College, works in evolutionary computation, with a current field distribution split evenly (0.5 / 0.5) between evolutionary robotics and evolutionary computation for game AI and multi-agent systems. The Evolve catalog holds two 2026 arXiv preprints, both listing Asaro as corresponding author. The first, 'Decentralized Evolution of Hexapod Gaits with Independent Leg Controllers,' evolves each hexapod leg's controller independently in Webots, departing from cooperative coevolution; the second, 'Niching Agents in The Core,' applies quadrant-based niching with cyclic genetic algorithms to competitive co-evolution of Xpilot agents. Work is concentrated in a tight circle of 2 distinct co-authors, Gary B. Parker and Jim O'Connor, yielding a low collaboration score of 22. Evolve's reproducibility reviews average 38 across the 2 papers — medium readiness for the hexapod work, low for the Core agents paper — with both reviews flagging missing statistical tests, absent baselines, and figure-only results. Output, impact, and activity metrics are not yet available, making this an early-stage profile.
Collaboration pattern
Collaboration is tightly concentrated: the record shows only 2 distinct co-authors — Gary B. Parker and Jim O'Connor — behind the 2026 preprints. The pattern suggests a small, stable team rather than an open network; no cross-institution or international links appear in the current data.
Research keywords
Highlights
Independent per-leg controller evolution for hexapod gaits
Quadrant-niched agents for competitive co-evolution in Xpilot
Corresponding author on both 2026 catalog preprints
Both entries in the Evolve catalog list Asaro as corresponding author — middle author on the hexapod gait paper and last author on the Core agents paper — indicating a leading role across the two-project output.
Timeline
- 2026arXiv preprint 'Decentralized Evolution of Hexapod Gaits with Independent Leg Controllers' appears, evolving each hexapod leg's controller independently in Webots with Asaro as corresponding author.
- 2026arXiv preprint 'Niching Agents in The Core' follows, applying quadrant-based niching and cyclic genetic algorithms to competitive co-evolution of Xpilot-AI agents.
- 2026Both preprints enter the Evolve review catalog, receiving reproducibility readiness ratings of medium and low, with a mean reproducibility score of 38.
- 2026The year's output is produced within a two-co-author circle: Gary B. Parker and Jim O'Connor.
Papers in the Evolve catalog
- corresponding
Decentralized Evolution of Hexapod Gaits with Independent Leg Controllers
- corresponding
Niching Agents in The Core
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric dimensions are computed from a limited public bibliographic snapshot (OpenAlex-derived); only the 2 catalog papers are in scope.
- Both catalog entries are 2026 arXiv preprints; no peer-reviewed venue record appears in this snapshot.
- Output, impact, and activity dimensions lack underlying data and are intentionally left unscored rather than estimated.
- The profile is name-resolved from public bibliographic records via ORCID 0009-0001-0723-4921; identity confidence depends on those records.