Transportation control researcher (h-index 58) extending into ML-driven air traffic management and robot learning
3
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
58
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-17) 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—
No output score has been computed for this profile yet. This axis would measure publication volume, venue quality, and authorship roles across the record; the radar lacks the underlying assessment, so no estimate is offered here.
Impact—
No impact score is available yet. Although raw citation indicators exist (h-index 58, i10-index 221), the composite impact axis — citation accrual per paper and field-normalized influence — has not been computed, so no score is reported here.
Focus0/100
The focus axis scores 0/100, consistent with a broadly spread record: OpenAlex topic assignments split 231/146/135 across traffic control, transportation planning, and traffic prediction, plus 39 works on differential-equation stability and controllability, while the current field mix is an even 50/50 split between air-traffic ML and robot learning. Recent catalog papers span aviation forecasting, embodied AI, and voice-trajectory data.
Collaboration53/100
The collaboration axis scores 53/100. The recent three-year window records 57 works with 13 distinct coauthors, and the 2026 catalog papers are multi-author efforts with Bayen as last author on FlowATC and V2TATC and a middle author on CFAMs. Recurring collaborators span both active fields: Jeff Schneider, Giuseppe Loianno, and Zackory Erickson on the robotics side; Louis Brusset, Mathurin Petit, Jordan Kam, and Emir Torun on the air-traffic side.
Activity100/100
The activity axis scores 100/100, the maximum in this profile. OpenAlex counts 57 works in the last three years, and yearly output remains substantial through 2026 (23 works), against a record that peaked at 43 works in 2014 and 40 in 2011 and 2020. Three 2026 arXiv preprints in the Evolve catalog confirm ongoing output.
Reproducibility20/100
The reproducibility axis scores 20/100, computed from two reviewed papers (reproMean 20 over reproPapers 2). Both are rated low reproducibility readiness: FlowATC releases no code and trains on narrow data, while CFAMs reports +13.9pp growth and −0.5pp forgetting but leaves key controls, statistics, and data unverifiable. Releasing code and data would most directly raise this score.
Research summary
Alexandre M. Bayen is a US-based researcher at Google whose bibliometric record, resolved through OpenAlex, centers on transportation control and management. Across a publishing record spanning 2001–2026, OpenAlex topic assignments place 231 works in traffic control and management, 146 in transportation planning and optimization, and 135 in traffic prediction and management techniques, with a control-theory base of 39 works on stability and controllability of differential equations and 38 on advanced control systems optimization. The record carries an h-index of 58 and an i10-index of 221, with yearly output peaking at 43 works in 2014 and 40 works in 2011 and again in 2020. Activity remains high: 57 works in the last three years. The current focus has shifted toward learning-based methods, split evenly (50/50) between machine learning for air traffic management and robotics. Three 2026 arXiv papers in the Evolve catalog illustrate this: FlowATC applies flow matching to aircraft trajectory prediction; CFAMs targets gradient-free post-deployment robot learning; and V2TATC contributes a joint voice-trajectory embedding dataset for air traffic controller situational awareness. Evolve's reviews rate both assessed papers low on reproducibility readiness, citing narrow or unverifiable data and missing code.
Collaboration pattern
Recent bibliometrics show 13 distinct coauthors in the last three years and a mid-range collaboration score (53/100). The 2026 catalog papers are team efforts, with Bayen as last author on FlowATC and V2TATC and a middle author on CFAMs — consistent with a senior group-lead role rather than corresponding-author oversight. Recurring partners span both current fields: air-traffic collaborators (Louis Brusset, Mathurin Petit, Jordan Kam, Emir Torun) and robotics collaborators (Jeff Schneider, Giuseppe Loianno, Zackory Erickson, Amarjot Singh).
Research keywords
Highlights
Flow matching reframes aircraft trajectory prediction
Gradient-free post-deployment learning for physical AI
Voice-trajectory dataset for controller situational awareness
The 2026 arXiv paper V2TATC introduces joint voice-trajectory embedding and a dataset for air traffic controller situational awareness, extending the aviation line of work; Evolve has not yet published a review for it.
Timeline
- 2026FlowATC — flow-matching-based aircraft trajectory prediction released on arXiv, with Bayen in the last-author position.
- 2026CFAMs — gradient-free continual learning for post-deployment physical AI, with Bayen in a middle-author position.
- 2026V2TATC — joint voice-trajectory embedding and dataset for air traffic controller situational awareness, with Bayen in the last-author position.
Papers in the Evolve catalog
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 metrics (h-index, i10-index, topic counts, yearly counts) come from an OpenAlex-resolved profile; identity is name-resolved from public bibliographic data, matched to ORCID 0000-0002-6697-222X.
- Radar scores for output and impact are missing and are not estimated anywhere in this profile.
- Only two of the three catalog papers carry Evolve reviews; V2TATC has no verdict, keywords, or reproducibility rating yet.
- The affiliation ('Google, United States') and coauthor lists come from the provided snapshot and were not independently verified; both assessed papers are arXiv preprints, not peer-reviewed publications.