IP Library Granted Patent US 12,728,892
Granted Patent B2
US 12,728,892 · App. 18/155,841 · Granted Sep 8, 2026

Driver assistance system and method for performing an at least partially automatic vehicle function depending on a travel route to be assessed

Inventors: Maximilian Templer (Tiddische, DE); Jonas Kaste (Alfeld, DE)
Assignee: VOLKSWAGEN AKTIENGESELLSCHAFT
B60W60/0011B60W40/072B60W40/105B60W40/107B60W50/0097G06F16/285G06N3/092B60W2520/105B60W2552/30B60W2556/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,728,892
App. No.
18/155,841
Granted
Sep 8, 2026
Kind
B2
Abstract

A method for performing an at least partially automatic vehicle function of a vehicle depending on a travel route to be assessed by means of a driver assistance system is disclosed. The method comprises providing a plurality of clusters from route data with respect to at least one known travel route, wherein the clusters group the route data sectionwise according to predefined geometric parameters. The method comprises providing recorded course data that indicate a course of the travel route to be assessed and applying the clusters to the course data in order to divide the travel route to be assessed into route sections corresponding to the clusters. The method comprises determining at least one uncertainty quantity which is characteristic of an uncertainty with respect to the assignment made and determining a control quantity as a function of the uncertainty quantity and providing the control quantity for performing the vehicle function.

Claims (34)

1 . A method for performing an at least partially automatic vehicle function of a vehicle depending on a new travel route to be assessed using a driver assistance system, the method comprising, by the driver assistance system:

obtaining route data of at least one known travel route during at least a training process, wherein the route data has been recorded while traveling on the at least one known travel route;

determining, a plurality of clusters from the route data of the at least one known travel route, wherein the clusters group the route data section-wise according to predefined geometric parameters, wherein regions of the at least one known travel route that have identical or similar geometric properties are associated to a single cluster of the plurality of clusters;

providing recorded course data that indicate a course of the new travel route to be assessed, different from the known travel route, and applying the plurality of clusters, obtained from the at least one known travel route, to the course data of the new travel route to be assessed in order to divide the new travel route to be assessed into route sections, and, as a result, to at least assign a first cluster of the plurality of clusters to a first route section;

determining at least one uncertainty quantity which is characteristic of an uncertainty with respect to the assignment made between the first route section and the first cluster assigned to said first route section, wherein the uncertainty quantity is characteristic of the uncertainty of the chosen cluster assignment and thus describes a degree of similarity of the first route section of the new travel route to be assessed to a region of the known travel route based on the geometric properties;

determining at least one control quantity as a function of the uncertainty quantity;

providing the at least one control quantity to the at least partially automatic vehicle function for performing the at least partially automatic vehicle function; wherein for each route section of the new travel route to be assessed, to which route section a cluster is assigned, a corresponding control quantity is determined depending on the respectively assigned cluster and is provided to the at least partially automatic vehicle function; and

controlling the vehicle at least partially automatically using the at least partially automatic vehicle function.

2 . The method of claim 1 , wherein the predefined geometric parameters comprise one or more of a local curve curvature, a local curvature direction in the direction of travel, a local road width, a local distance of a vehicle trajectory along the travel route to a road edge, a local distance of a vehicle trajectory along the travel route to a lane edge, local spatial route coordinates along the travel route, a local speed of a vehicle along the travel route, and a local acceleration of a vehicle along the travel route.

3 . The method of claim 2 , wherein an extent of interaction of the driver assistance system for performing the vehicle function is changed and/or checked depending on the uncertainty quantity in order to determine the control quantity.

4 . The method of claim 2 , wherein the uncertainty quantity is assessed with respect to a future potential travel route as the new travel route to be assessed.

5 . The method of claim 2 , wherein the driver assistance system uses an agent to determine the control quantity, wherein the agent is configured for exploring an environment of the agent, and wherein the exploration depends on the uncertainty quantity.

6 . The method of claim 1 , wherein an extent of interaction of the driver assistance system for performing the vehicle function is changed and/or checked depending on the uncertainty quantity in order to determine the control quantity.

7 . The method of claim 6 , wherein the uncertainty quantity is assessed with respect to a future potential travel route as the new travel route to be assessed.

8 . The method of claim 6 , wherein the driver assistance system uses an agent to determine the control quantity, wherein the agent is configured for exploring an environment of the agent, and wherein the exploration depends on the uncertainty quantity.

9 . The method of claim 1 , wherein the uncertainty quantity is assessed with respect to a future potential travel route as the new travel route to be assessed.

10 . The method of claim 1 , wherein the driver assistance system uses an agent, to determine the control quantity, wherein the agent is configured for exploring an environment of the agent, and wherein the exploration depends on the uncertainty quantity.

11 . The method of claim 1 , wherein it is determined based on the uncertainty quantity when exploration is required.

12 . The method of claim 1 , wherein a correlation of at least a portion of the course data with respect to the route section and the assigned cluster is determined in order to determine the uncertainty quantity of a particular route section of the new travel route to be assessed.

13 . The method of claim 1 , the method further comprising determining a cluster center point for each cluster wherein at least the cluster center point of the cluster assigned to the course data to be assessed is taken into account during the determination of the uncertainty quantity.

14 . The method of claim 1 , wherein the uncertainty quantity is determined based on a relative distance metric on the basis of an arrangement of at least a portion of the course data in relation to an arrangement of at least one cluster center point of a cluster in a property space spanned by the predefined geometric parameters.

15 . The method of claim 1 , wherein a driving situation of the vehicle is assessed with respect to a vehicle stability and/or driving safety and the control quantity is determined depending hereon and as a function of the uncertainty quantity.

16 . The method of claim 1 , wherein the control quantity is a characteristic of a manipulated quantity in an adaptive control method for performing the vehicle function.

17 . The method of claim 1 , wherein the driver assistance system uses a teachable model and an additional training process is initiated depending on the uncertainty quantity.

18 . The method of claim 17 , wherein route data and/or course data are identified which cannot be clearly assigned to a cluster and/or the correlation of which with an assigned cluster is merely low, and an additional training process of the teachable model is carried out based on the identified track data and/or course data.

19 . A driver assistance system for a vehicle for performing an at least partially automatic vehicle function of a vehicle depending on a new travel route to be assessed, the system configured for:

obtaining route data of at least one known travel route during at least a training process, wherein the route data has been recorded while traveling on the at least one known travel route;

determining a plurality of clusters from the route data of the at least one known travel route, wherein the clusters group the route data section-wise according to predefined geometric parameters, wherein regions of the at least one known travel route that have identical or similar geometric properties are associated to a single cluster of the plurality of clusters;

providing recorded course data that indicate a course of the new travel route to be assessed, different from the known travel route, and applying the plurality of clusters, obtained from the at least one known travel route, to the course data to be assessed in order to divide the new travel route to be assessed into route sections, and, as a result, to at least assign a first cluster to a first route section;

determining at least one uncertainty quantity which is characteristic of an uncertainty with respect to the assignment made between the first route section and the first cluster assigned to said first route section, wherein the uncertainty quantity is characteristic of the uncertainty of the chosen cluster assignment and thus describes a degree of similarity of the first route section of the new travel route to be assessed to a region of the known travel route based on the geometric properties;

determining at least one control quantity as a function of the uncertainty quantity;

providing the at least one control quantity to the at least partially automatic vehicle function for performing the at least partially automatic vehicle function; wherein for each route section of the new travel route to be assessed, to which route section a cluster is assigned, a corresponding control quantity is determined depending on the respectively assigned cluster and is provided to the at least partially automatic vehicle function; and

controlling the vehicle at least partially automatically using the at least partially automatic vehicle function.

20 . A vehicle comprising a driver assistance system according to claim 19 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 8, 2023
From: TEMPLER, MAXIMILIAN; KASTE, JONAS
To: VOLKSWAGEN AKTIENGESELLSCHAFT
Reel/Frame 063567/0358 →
Priority Claims (1)
DE 10 2022 200 536.8 · Jan 18, 2022 · national
Continuity (1)
Related Publication 20230227066A1 · Jul 20, 2023
References Cited (38)
US 9205759B2 · Pulliam · 2015 [cited by examiner]
US 9423261B2 · Dorum · 2016 [cited by examiner]
US 10604156B2 · Sorstedt · 2020 [cited by examiner]
US 12139134B2 · Jiang · 2024 [cited by examiner]
US 20080010009A1 · Miyoshi · 2008 [cited by examiner]
US 20130274986A1 · Trepagnier et al. · 2013 [cited by applicant]
US 20140136414A1 · Abhyanker · 2014 [cited by applicant]
US 20140236482A1 · Dorum · 2014 [cited by examiner]
US 20150191178A1 · Roy · 2015 [cited by examiner]
US 20160178381A1 · Lynch · 2016 [cited by examiner]
US 20170102703A1 · Lynch · 2017 [cited by examiner]
US 20170293660A1 · Nachlieli · 2017 [cited by examiner]
US 20180009445A1 · Nishi · 2018 [cited by examiner]
US 20180061226A1 · Thelen · 2018 [cited by examiner]
US 20190047527A1 · Falconer · 2019 [cited by examiner]
US 20190051172A1 · Stenneth · 2019 [cited by examiner]
US 20190202494A1 · Itou · 2019 [cited by examiner]
US 20190255989A1 · Rowell · 2019 [cited by examiner]
US 20200104714A1 · Lee · 2020 [cited by examiner]
US 20200180650A1 · Lee · 2020 [cited by examiner]
US 20200192393A1 · Aragon · 2020 [cited by applicant]
US 20200241545A1 · Anthony · 2020 [cited by examiner]
US 20200307561A1 · Bush · 2020 [cited by examiner]
US 20210165409A1 · Berntorp et al. · 2021 [cited by applicant]
US 20210197825A1 · Choi · 2021 [cited by examiner]
US 20220332345A1 · Heo · 2022 [cited by examiner]
US 20230030104A1 · Puchkarev · 2023 [cited by examiner]
US 20230227066A1 · Templer · 2023 [cited by examiner]
US 20240011792A1 · Wu · 2024 [cited by examiner]
DE 102021200889A1 · 2022 [cited by applicant]
DE 102021201698A1 · 2022 [cited by applicant]
Kiran, B. Ravi, et al. “Deep reinforcement learning for autonomous driving: A survey.” IEEE transactions on intelligent transportation systems 23.6 (2021): 4909-4926. (Year: 2021). [cited by examiner]
Kumar, Vijay, Jitender Kumar Chhabra, and Dinesh Kumar. “Performance evaluation of distance metrics in the clustering algorithms.” INFOCOMP Journal of Computer Science 13.1 (2014): 38-52. (Year: 2014). [cited by examiner]
Kumaraswamy, Raksha, et al. “Context-dependent upper-confidence bounds for directed exploration.” Advances in Neural Information Processing Systems 31 (2018). (Year: 2018). [cited by examiner]
Abramson, Myriam et al., “Tabu Search Exploration for On-Policy Reinforcement Learning,” In IEEEProceedings of the International Joint Conference on Neural Networks, vol. 4, pp. 2910-2915, Jul. 20, 2003. [cited by applicant]
Garcia, Francisco M. et al., “A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning,” arXiv:1902.00843v1, 16 pages, Feb. 3, 2019. [cited by applicant]
German Office Action, Application No. 102022200536.8, 6 pages, Sep. 26, 2022. [cited by applicant]
Extended European Search Report, Application No. 22215459.3, 9 pages, May 12, 2023. [cited by applicant]