Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021037765 - PERFORMANCE TESTING FOR ROBOTIC SYSTEMS

Publication Number WO/2021/037765
Publication Date 04.03.2021
International Application No. PCT/EP2020/073568
International Filing Date 21.08.2020
IPC
G06N 3/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 7/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
7Computer systems based on specific mathematical models
G06K 9/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G05D 1/00 2006.01
GPHYSICS
05CONTROLLING; REGULATING
DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
1Control of position, course, altitude, or attitude of land, water, air, or space vehicles, e.g. automatic pilot
CPC
B60W 2420/42
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
2420Indexing codes relating to the type of sensors based on the principle of their operation
42Image sensing, e.g. optical camera
B60W 2420/52
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
2420Indexing codes relating to the type of sensors based on the principle of their operation
52Radar, Lidar
B60W 2554/40
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
2554Input parameters relating to objects
40Dynamic objects, e.g. animals, windblown objects
B60W 2554/404
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
2554Input parameters relating to objects
40Dynamic objects, e.g. animals, windblown objects
404Characteristics
B60W 2555/20
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
2555Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
20Ambient conditions, e.g. wind or rain
B60W 60/0011
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
60Drive control systems specially adapted for autonomous road vehicles
001Planning or execution of driving tasks
0011involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
Applicants
  • FIVE AI LIMITED
Inventors
  • REDFORD, John
  • KALTWANG, Sebastian
  • SAMANGOOEI, Sina
  • ROGERS, Blain
Agents
  • WOODHOUSE, Tom
Priority Data
1912145.823.08.2019GB
20168311.706.04.2020EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) PERFORMANCE TESTING FOR ROBOTIC SYSTEMS
(FR) TEST DE PERFORMANCES POUR SYSTÈMES ROBOTIQUES
Abstract
(EN)
Herein, a "perception statistical performance model" (PSPM) for modelling a perception slice of a runtime stack for an autonomous vehicle or other robotic system may be used e.g. for safety/performance testing. A first PSPM is configured to: receive a computed perception ground truth; determine from the perception ground truth, based on a set of learned parameters, a probabilistic perception uncertainty distribution, the parameters learned from a set of actual perception outputs generated using the perception slice to be modelled, in order to compute a first time series of perception outputs. A second time series of perception outputs is computed using a second PSPM for modelling a second perception slice of the runtime stack, the first PSPM learned from data of a first sensor modality of the perception slice and the time series, and the second PSPM learned independently thereof from data of a second sensor modality of the second perception slice and the second time series.
(FR)
Dans la présente invention, un « modèle de performance statistique de perception » (PSPM) pour modéliser une tranche de perception d'une pile d'exécution pour un véhicule autonome ou un autre système robotique peut être utilisé, par exemple, pour un test de sécurité/performances. Un premier PSPM est configuré pour : recevoir une vérité de base de perception calculée ; déterminer à partir de la réalité virtuelle de perception, sur la base d'un ensemble de paramètres appris, une distribution probabiliste d'incertitude de perception, les paramètres appris à partir d'un ensemble de sorties de perception réelles générées à l'aide de la tranche de perception à modéliser, afin de calculer une première série chronologique de sorties de perception. Une seconde série chronologique de sorties de perception est calculée à l'aide d'un second PSPM pour modéliser une seconde tranche de perception de la pile d'exécution, le premier PSPM appris à partir de données d'une première modalité de capteur de la tranche de perception et de la série chronologique, et le second PSPM appris indépendamment de celles-ci à partir de données d'une seconde modalité de capteur de la seconde tranche de perception et de la seconde série chronologique.
Latest bibliographic data on file with the International Bureau