Aptiv Technologies Ag

Aptiv Technologies Limited

Bin Jia

David Aaron Schwartz

Kumar Vishwajeet

Sana Sarfraz

Xiaohui Wang

This document describes road modeling with ensemble Gaussian processes. A road is modeled at a first time using at least one Gaussian process regression (GPR). A kernel function is determined based on a sample set of detections received from one or more vehicle systems. Based on the kernel function, a respective mean lateral position associated with a particular longitudinal position is determined for each GPR of the at least one GPR. The respective mean lateral position for each of the at least one GPR is aggregated to determine a combined lateral position associated with the particular longitudinal position. A road model is then output including the combined lateral position associated with the particular longitudinal position. In this way, a robust and computationally efficient road model may be determined to aid in vehicle safety and performance.

Road modeling with ensemble gaussian processes

This document describes techniques and systems for generating a fused object bounding box based on uncertainty. At least two bounding boxes, each associated with a different sensor, is generated. A fused center point and yaw angle as well as length, width, and velocity can be found by mixing the distributions of the parameters from each bounding box. A discrepancy between the center points of each bounding box can be used to determine whether to refine the fused bounding box (e.g., find an intersection between at least two bounding boxes) or consolidate the fused bounding box (e.g., find a union between at least two bounding boxes). This results in the fused bounding box having a confidence level of the uncertainty associated with the fused bounding box. In this manner, better estimations of the uncertainty of the fused bounding box may be achieved to improve tracking performance of a sensor fusion system.

Generating a fused object bounding box based on uncertainty

The techniques and systems herein enable pose correction based on landmarks and barriers. A vehicle pose, one or more radar-occupancy grid (ROG) landmark locations relative to the vehicle, and one or more map landmark locations are received. Based on determined association probabilities of candidate pairs (e.g., treating the map landmark locations as observations), one of the ROG landmark locations and one of the map landmark locations are selected as corresponding to each other. An ROG barrier location and a map barrier location are identified, and ripple point locations are identified that are along the barriers at a radial distance from the landmarks. Based on the ripple point locations and a cost function, a pose correction for the pose is determined. By using the described techniques, reliable vehicle localization can be performed using radar data and a map in a wide array of environments without necessitating other sensors.

Pose correction based on landmarks and barriers

This document describes techniques, systems, and methods for multi-scan sensor fusion for object tracking. A sensor-fusion system can obtain radar tracks and vision tracks generated for an environment of a vehicle. The sensor-fusion system maintains sets of hypotheses for associations between the vision tracks and the radar tracks based on multiple scans of radar data and vision data. The set of hypotheses include mass values for the associations. The sensor-fusion system determines a probability value for each hypothesis. Based on the probability value, matches between radar tracks and vision tracks are determined. The sensor-fusion system then outputs the matches to a semi-autonomous or autonomous driving system to control operation of the vehicle. In this way, the described techniques, systems, and methods can provide high-precision object tracking with quantifiable uncertainty.

Multi-scan sensor fusion for object tracking

This document describes techniques, apparatuses, and systems for a grid-based road model with multiple layers. An example road-perception system generates a roadway grid representation that includes multiple cells. The road-perception system uses data from multiple information sources to generate a road model that includes multiple layers. Each layer represents a roadway attribute of each cell in the grid and includes one or more layer hypotheses. In this way, the described techniques and systems can provide an accurate and reliable road model and quantify uncertainty therein.

Grid-based road model with multiple layers

This document describes techniques and systems to make determinations of lane-type and roadway hypotheses in a road model. The road-perception system can fuse various forms of evidence to determine lane-type hypotheses and respective belief masses associated with the lane-type hypotheses. The road-perception system the computes, using the belief masses, a belief parameter and a plausibility parameter associated with the lane-type hypotheses. One or more roadway hypotheses are then determined using the lane-type hypotheses. The road-perception system then uses the respective belief parameter and plausibility parameter associated with the lane-type hypotheses to compute a belief parameter and a plausibility parameter associated with the roadway hypotheses. In this way, the described techniques and systems can provide an accurate and reliable road model with quantified uncertainty.

Growing community of inventors

Columbia, MD, United States of America

Bin Jia