Leveraging FMCW-Radar for Autonomous Positioning Systems: Methodology and Application in Downtown Toronto
Bibliographic record
Abstract
The industry of land vehicles entered a new era. In which, driving autonomy is the main goal. It caused a rising demand of more accurate driving systems. Vehicle’s positioning technologies play an important role in such systems. It is one of the main pillars in the autonomous perception task. Global Navigation Satellite System (GNSS) has been always used as the main navigation solution provider. However, the GNSS is subjected for several sources of errors. Signal blockage and multi-path issues take place in urban canyons and downtowns of large cities. Such problems showed the weakness of GNSS solution in critical places. Therefore, Inertial Navigation Systems (INS) were used for long time to provide the navigation information during GNSS outages. A specific INS type with lower number of sensors and high effectiveness for land vehicles named three-dimensional reduced inertial sensor system (3DRISS) has been widely considered and used. The 3D-RISS is integrated with GNSS to acquire accurate information. An integration that is mostly carried out by an Extended Kalman Filter (EKF). Such solution which can show magnificent performances in open skies. However, in GNSS outages the integrated system has to rely only on the solution provided by the 3D-RISS. Despite the fidelity of 3D-RISS measurements in short-term outages, it suffers from a vast drift in inertial sensor errors for long-term. As a result, ramping up the system for higher multi-sensor fusion integration is a necessity. The solution proposed depends on integrating an FMCW Radar used almost in all levels of driving autonomy with the 3D-RISS/GNSS system. The methodology used was experimented during natural outage periods in downtown Toronto. The difficulty of the area and the nature of the GNSS outages show the fidelity of Radar/RISS/GNSS proposed method.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".