Simulation of Automotive Radar Point Clouds in Standardized Frameworks
Material type: TextDescription: 1 online resource (127 pages)Content type:- text
- computer
- online resource
- 3736965362
- 9783736965362
- TL158 .S568 2021
- COPYRIGHT NOT covered - Click this link to request copyright permission: https://lib.ciu.edu/copyright-request-form
Item type | Current library | Collection | Call number | URL | Status | Date due | Barcode | |
---|---|---|---|---|---|---|---|---|
Online Book (LOGIN USING YOUR MY CIU LOGIN AND PASSWORD) | G. Allen Fleece Library ONLINE | Non-fiction | TL158 (Browse shelf(Opens below)) | Link to resource | Available | on1287131951 |
Description based upon print version of record.
Includes bibliographies and index.
Intro -- Chapter 1 Autonomous driving andsimulational challenges -- 1.1 Safety validation and simulative test drives -- 1.2 Principles of automotive radar sensors -- 1.3 Modeling and standardized simulationframeworks -- Chapter 2 State of research in automotiveradar modeling -- 2.1 Differentiation of various modeling levels -- 2.2 Ray-tracing in environments of high-fidelity -- 2.3 Models executable in standardized environments -- 2.4 Validation and verification of sensor models -- Chapter 3 Derivation of research questions,hypotheses and objectives
3.2 Stochastic radar models based on deepgenerative networks -- 3.3 Hybrid multipurpose approaches for radar sensormodels -- 3.4 Deficiencies of current validation criteria -- Chapter 4 Modeling challenges related to raycone tracing -- 4.1 The caustic distance and the angular beamexpansion -- 4.2 Estimating current errors in case of multiplereflections -- 4.3 Consequences and lower bounds for the numberof rays -- Chapter 5 Approaches to statistical radar pointcloud simulation -- 5.1 Statistical formulation of radar sensor modeling -- 5.2 Kernel density estimation and radar point clouds
5.3 Deep generative networks as sensor models -- 5.4 Comparison of learning capacities and itsconsequences -- Chapter 6 A hybrid modeling approach forradar point clouds -- 6.1 Tracing and catching rays as the baseline -- 6.2 Improvements to the ray casting approach -- 6.3 Capabilities for data-based optimization -- 6.4 Bottom line on the hybrid modeling approach -- Chapter 7 Validation based on statisticalhypothesis testing -- 7.1 Consistency of validation criterion -- 7.2 On the Kolmogorov-Smirnov test -- 7.3 Applications to radar sensor models
7.4 Retrospective and future validation challenges -- Chapter 8 Conclusion and prospectivechallenges -- 8.1 Recap of the radar point cloud simulation -- 8.2 Lessons learned and future recommendations -- Nomenclatur -- References -- Index
COPYRIGHT NOT covered - Click this link to request copyright permission:
There are no comments on this title.