The LEADER framework achieves ten‑millisecond "eye‑open" LiDAR relocalization while surpassing the decimeter‑level accuracy of classic retrieval‑registration pipelines, using cylindrical projection, sparse convolution, and a Truncated Relative Reliability loss, as demonstrated on the NCLT benchmark.
This article presents the technical background of SLAM, explains why GNSS‑based navigation fails in complex urban environments, describes the selection and testing of several LiDAR‑IMU SLAM algorithms—including FAST‑LIO2—on Qiji unmanned vehicles, and details the hardware configuration, algorithmic improvements, experimental workflow, and positioning results achieved in a real‑world patrol project.
JD Retail’s Technology and Data Center announced that two of its papers were accepted at ICRA 2021: one presenting a deep balanced learning approach for long‑tailed facial expression recognition, and the other introducing a vanishing‑point‑aided LiDAR‑visual‑inertial estimator for robust state estimation.
The article describes how high‑frequency LiDAR scanners on precision mapping vehicles suffer from Multi‑Time‑Around (MTA) errors—mis‑assigning distant returns to near ranges—and explains both internal laser strategies (continuity assumption and variable‑period emission) and a four‑step neighborhood‑weighting algorithm that reliably corrects these artifacts, restoring accurate point‑clouds for automated map generation.
This article reviews perception technologies used in autonomous heavy‑truck systems—including lane‑line detection, obstacle detection, and LiDAR sensing—detailing traditional and deep‑learning approaches, practical challenges on high‑speed highways, and the cost, performance, and reliability issues faced when moving these solutions to mass production.
This article explains how integrating depth data from LiDAR and stereo cameras with image‑based perception through front‑fusion algorithms reduces semantic errors, enhances static obstacle mapping, and enables semi‑supervised spatial annotation for high‑precision maps used in autonomous driving.
Pony.ai shares its extensive experience on multi‑sensor perception for autonomous trucks, explaining why sensor fusion is needed, the essential motion‑compensation and calibration steps, and practical camera‑lidar and radar‑lidar fusion techniques that improve detection range and robustness.
Microsoft has launched an open‑source tool that lets distribution maintainers and developers create custom Linux packages for the Windows Subsystem for Linux, while also previewing new WSL features such as background tasks and Unix‑domain sockets, and reporting that Uber disabled safety radar on a Volvo autonomous vehicle involved in a fatal pedestrian crash.
