A Detection and Filtering Framework for Collaborative Localization

TL;DR

This research explores the means to improve localization on vehicles belonging to the ADAS category in a platooning context, where an ADAS vehicle follows a lead"Smart"AV equipped with a highly accurate sensor suite.

Abstract

Increasingly, autonomous vehicles (AVs) are becoming a reality, such as the Advanced Driver Assistance Systems (ADAS) in vehicles that assist drivers in driving and parking functions with vehicles today. The localization problem for AVs relies primarily on multiple sensors, including cameras, LiDARs, and radars. Manufacturing, installing, calibrating, and maintaining these sensors can be very expensive, thereby increasing the overall cost of AVs. This research explores the means to improve localization on vehicles belonging to the ADAS category in a platooning context, where an ADAS vehicle follows a lead "Smart" AV equipped with a highly accurate sensor suite. We propose and produce results by using a filtering framework to combine pose information derived from vision and odometry to improve the localization of the ADAS vehicle that follows the smart vehicle.

Figures (6)

• Figure 1: Improving localization of an 'ADAS' vehicle by fusing pose from inertial odometry($^{ADAS}H_{world}$) and pose information derived by perceiving the smart vehicle($^{ADAS}H_{world}$). Fusion is done through an EKF that gives the improved pose estimate $^{ADAS}\hat{P}_{world}$. $^AH_B$ is the pose of A in frame B.
• Figure 2: The proposed Framework: Perception module inputs a pose information to the filter, odometry information is also input to the network to obtain an improved pose estimate
• Figure 3: Trajectory of ADAS Vehicle, $\sigma$=5, $\gamma$=5, no added noise on raw pose
• Figure 4: Position error ADAS Vehicle, $\sigma$=5, $\gamma$=5, no added noise on raw pose
• Figure 5: Orientation error of ADAS Vehicle,, $\sigma$=5, $\gamma$=5, no added noise on raw pose