Field robotics researcher at TUM working on learned navigation — traversability, video planning, and underwater systems
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
10
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—
The output axis measures total publication volume and how it is distributed across the career. This snapshot does not include the underlying full-output data needed to compute it, so no score or estimate is given here.
Impact—
The impact axis measures citation-based influence, such as citation counts and how they accumulate across a body of work. The underlying citation distribution is not available in this snapshot, so it is left unscored rather than estimated.
Focus0/100
The focus axis measures topical concentration and scores 0, reflecting a spread portfolio. OpenAlex splits his field distribution evenly (0.5 robotics / robot learning and vision-language navigation, 0.5 field robotics / robot learning) and assigns works to five topics, led by underwater vehicles and communication systems (26) ahead of sensor-based localization (10), mobile-robot control and dynamics (8), reinforcement learning in robotics (6), and maritime navigation and safety (6).
Collaboration46/100
Collaboration scores 46. His OpenAlex record lists 9 distinct coauthors in the recent window, and the co-author network surfaces frequent partners including Hojin Lee, Sizhe Lester Li, Maximilian Hilger, Susie Lu, Achim J. Lilienthal, Vincent Sitzmann, Yunho Lee, and Cheolhyeon Kwon. On the two reviewed 2026 papers he is a middle author on the continual-learning study and last author on CueNav, neither in the corresponding slot.
Activity72/100
Activity scores 72. The counts-by-year series shows continuous output from 2017 (2 works) through 2026, peaking at 7 works in 2020 and dipping to 1 in 2022, then recovering to 4 in 2024, 5 in 2025 and 2 already in 2026. The last three years total 11 works, a sustained cadence for an experimental robotics profile.
Reproducibility55/100
Reproducibility scores 55, computed as the mean over the 2 Evolve-assessed papers, both rated medium reproducibility readiness. The continual-learning review notes navigation trials with n=3 and unreported λ/τ hyperparameters; the CueNav review flags thin statistics and a privileged bird's-eye-view input despite promising 93% real-robot results. Findings look plausible but need fuller experimental reporting to reproduce independently.
Research summary
Daniel A. Duecker is a robotics researcher at the Technical University of Munich whose profile is resolved from OpenAlex bibliographic data linked to ORCID 0000-0001-7256-6984. His topic-assigned works cluster around underwater vehicles and communication systems (26 works), sensor-based localization (10), control and dynamics of mobile robots (8), reinforcement learning in robotics (6), and maritime navigation and safety (6). Across 2017–2026 the counts-by-year series totals 37 works, with 11 works in the last three years (2024: 4, 2025: 5, 2026: 2), an h-index of 10 and an i10-index of 11. Evolve has reviewed two of his 2026 arXiv papers: a continual-learning approach to traversability prediction with uncertainty-aware adaptation that curbs forgetting without storing raw data, and CueNav, a visual-cue-guided video-planning framework for generalizable robot navigation that pairs diffusion-model video planning with a per-robot optical-flow inverse dynamics model and reports a 93% real-robot success rate. Both reviews flag medium reproducibility readiness, noting thin trial statistics (n=3 navigation trials) and unreported hyperparameters. He appears as a middle author on the first paper and last author on the second, suggesting active work within multi-author robotics teams.
Collaboration pattern
Co-authorship is active but mid-sized: the OpenAlex snapshot lists 9 distinct coauthors and scores collaboration at 46. Recurring partners include Hojin Lee, Sizhe Lester Li, Maximilian Hilger, Susie Lu, Achim J. Lilienthal, Vincent Sitzmann, Yunho Lee, and Cheolhyeon Kwon. On the two reviewed 2026 papers he sits as a middle author on the continual-learning study and as last author on CueNav, in neither case corresponding — consistent with collaborative team science rather than solo work.
Research keywords
Highlights
Continual learning keeps off-road traversability models from forgetting
CueNav: visual-cue video planning reaches 93% real-robot navigation success
OpenAlex record anchored in underwater vehicles and communication systems
With 26 topic-assigned works, underwater vehicles and communication systems is the largest cluster on his OpenAlex profile, ahead of robotics and sensor-based localization (10), control and dynamics of mobile robots (8), reinforcement learning in robotics (6), and maritime navigation and safety (6).
Timeline
- 20172 works recorded in OpenAlex — the start of the tracked publication window.
- 2020Peak year in the counts-by-year series, with 7 works recorded.
- 2022Lowest output year in the series, with 1 recorded work.
- 2025Output rebounds to 5 works, part of the 11 works across the last three years.
- 20262 works recorded so far, including two Evolve-reviewed arXiv papers: the continual-learning traversability study and CueNav video planning.
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.
- All bibliometrics come from an OpenAlex-linked snapshot (identity: openalex, ORCID 0000-0001-7256-6984); the output and impact radar axes are not scored in this snapshot even though h-index and i10-index are reported.
- The reproducibility score is a mean over only 2 Evolve-assessed papers, both sourced from arXiv, so it is a small and preprint-heavy sample.
- Topic and field labels are OpenAlex auto-classifications and may not fully capture the actual research scope.
- No career facts beyond the provided affiliation are verified; roles such as PI status or lab leadership are not asserted in this profile.