Research

A follow-up to our L5 result. The L5 controller's clearance term used a true-surface distance no real sensor produces; under a realistic sensor model the suite was L3. We report the honest path back: an on-device controller proven byte-identical to sim, geometry repair with a sensing-noise budget (99.5% collision-free over 800 randomized noisy runs), a taxonomy of nine avoidance approaches that failed and why, and 16/16 collision-free validation of both vehicle classes through ArduPilot SITL. We do not claim IRL L5 — hardware is the remaining gate.

A systematic methodology for achieving zero-intervention autonomy in a heterogeneous quadcopter-and-rover fleet on a 16-scenario adversarial benchmark. Starting from L3 (20 total interventions), five collision patterns attributable to scenario geometry — not the control policy — are identified and resolved, reaching L5 (0 interventions, 100% success, 0 collisions) without modifying the reactive controller.

Introduces Yonder, a multi-million-frame drone-perspective indoor dataset with rich sensing, and shows why offline detection gains can fail to translate to closed-loop navigation when training and evaluation simulators disagree geometrically.

Nine-cell factorial study comparing tower vs. self-organized coordination, continuous vs. terminal-only communications, and four observation modalities (ADS-B, camera, both, none) across 405 simulated vertiport trials. Self-org with ADS-B matches tower throughput below ~20 ops/hour then degrades; silent-cruise drones exceed safe LoS thresholds at 12 ops/hour. Characterizes the throughput–safety Pareto frontier and broadcast necessity threshold for UAM droneport designs.

11,340 seeded trials across four attack classes (GNSS spoofing, RF jamming, kinetic interception, control takeover) and six matched defenses in a four-drone warehouse swarm. Central finding: mission success rate is the wrong primary metric for C-UAS — physical effects (79.5% PN capture rate, 5–8 m position error) are clearly measurable even when aggregate task completion is unaffected. A kinematic plausibility detector achieves 39.8% TP at 0% false-positive rate. Includes an explicit fidelity boundary analysis delineating what kinematic simulation can and cannot faithfully reproduce.

Controlled swarm simulations up to 1,000 agents comparing sensing stacks and coordination architectures, with a focus on when ultra-wideband ranging becomes necessary as fleet scale and environment difficulty increase.

Adds Gemma 4 to the same Isaac Sim closed-loop benchmark and compares end-to-end goal prediction against modular deployment of the same weights as a semantic target selector, illustrating the leverage of the separation principle.

Large-scale closed-loop benchmark across many VLMs, decomposing failures into semantic understanding versus metric spatial grounding, and a modular architecture that closes the gap on operational commands while prioritizing collision-free flight.

An eighteen-iteration engineering log: improving a modular autonomy stack in aggregate, scaling detector fine-tuning with large synthetic data, diagnosing a cross-simulator localization gap, and characterizing exploration and planning as the next bottlenecks.