INVESTIGATING THE COMPLEMENTARY USE OF RADAR AND LIDAR FOR POSITIONING APPLICATIONS
Bibliographic record
Abstract
Abstract. In the realm of Autonomous Vehicles (AVs), accurate, reliable and uninterrupted positioning capabilities are vital to ensure successful operations. Light Detection And Ranging (LiDAR) technology, capable of providing a high-fidelity 3D representation of the surrounding environment, has enabled numerous odometry-based positioning algorithms. These algorithms utilize a registration process to estimate relative motion from two successive 3D scans. However, the accuracy of the registration process can be compromised by the presence of dynamic objects, leading to significant translational and rotational deviations. On the other hand, Radar technology provides spatial and speed information. However, it is limited by spatial sparsity and susceptibility to noise. In this paper, we propose combining the complementary LiDAR and Electronic Scanning Radar (ESR) measurements, along with onboard motion sensors for improved navigation performance in complex and dynamic environments. This is achieved by employing a radar-based filtering mechanism that refines the LiDAR’s point cloud mitigating the impact of dynamic objects. This results in a more robust registration process, which in turn enhances the LiDAR Inertial Odometry (LIO) solution. The proposed method was verified using real data collected from onboard motion sensors, a 3D LiDAR, and four ESRs from road tests conducted in downtown Calgary, Alberta, Canada. Our approach achieved an improved average horizontal positioning and heading RMSE of 0.43 meters and 0.25 degrees, respectively, compared to the 0.66 meters and 0.39 degrees observed with the standalone LIO solution. Moreover, submeter-level and lane-level accuracies were enhanced to 95% and 100% of the time, respectively, up from 85.7% and 94.9%.
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 | 0.001 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".