Systems and methods for detecting impaired decision-making pedestrians

Patent metadata

Field	Value
Publication number	US-12475781-B2
Application number	US-202318533750-A
Country	US
Kind code	B2
Filing date	Dec 8, 2023
Priority date	Dec 8, 2023
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

Systems, methods, and other embodiments described herein relate to identifying and assisting pedestrians identified as experiencing impaired decision-making capabilities. In one embodiment, a method includes determining, from interaction data collected by a user device of a pedestrian, an interaction characteristic of the pedestrian. The method also includes classifying the pedestrian as in an impaired decision-making state based on the interaction characteristic of the pedestrian deviating from baseline interaction data. The method further includes producing a pedestrian assistance countermeasure responsive to a determined impaired decision-making state for the pedestrian.

First claim

What is claimed is:

1 . A system, comprising:
a processor; and a memory storing machine-readable instructions that, when executed by the processor, cause the processor to:
determine, from interaction data collected by a user device of a pedestrian, an interaction characteristic of the pedestrian;
classify the pedestrian as in an impaired decision-making state based on the interaction characteristic of the pedestrian deviating from baseline interaction data; and
produce a pedestrian assistance countermeasure responsive to a determined impaired decision-making state for the pedestrian.

2 . The system of claim 1 , wherein:
the machine-readable instruction that, when executed by the processor, causes the processor to determine the interaction characteristic of the pedestrian comprises a machine-readable instruction that, when executed by the processor, causes the processor to determine at least one of a verbal communication characteristic or a written communication characteristic of the pedestrian; and the machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state comprises a machine-readable instruction that, when executed by the processor, causes the processor to identify that the pedestrian is having difficulty composing at least one of a verbal communication or a written communication.

3 . The system of claim 2 , wherein the machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state comprises a machine-readable instruction that, when executed by the processor causes the processor to classify the pedestrian as in the impaired decision-making state further based on a context of the verbal communication or the written communication.

4 . The system of claim 1 , wherein the machine-readable instruction that, when executed by the processor, causes the processor to determine the interaction characteristic of the pedestrian comprises a machine-readable instruction that, when executed by the processor, causes the processor to determine a characteristic of an interaction of the pedestrian with an application of the user device.

5 . The system of claim 1 , wherein:
the machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state comprises a machine-learning instruction that, when executed by the processor, causes the processor to compare the interaction characteristic of the pedestrian to the baseline interaction data; and the baseline interaction data comprises at least one of:
an interaction pattern of the pedestrian; or
an interaction pattern of an additional individual.

6 . The system of claim 5 , wherein the machine-learning instruction that, when executed by the processor, causes the processor to compare the interaction characteristic of the pedestrian to the baseline interaction data comprises a machine-learning instruction that, when executed by the processor, causes the processor to:
weight the interaction pattern of the pedestrian more heavily than the interaction pattern of the additional individual; and update a machine-learning instruction set to compare the interaction characteristic of the pedestrian to the baseline interaction data based on continuously collected interaction data for the pedestrian.

7 . The system of claim 1 , wherein the machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state comprises a machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state based on at least one of:
a degree of deviation between the interaction characteristic and the baseline interaction data; or a quantity of deviations between interaction characteristics and the baseline interaction data within a period of time.

8 . The system of claim 1 , wherein the machine-readable instruction that, when executed by the processor, causes the processor to produce the pedestrian assistance countermeasure comprises a machine-readable instruction that, when executed by the processor, causes the processor to produce a notification to at least one of:
a human vehicle operator; an autonomous vehicle system; or an infrastructure element.

9 . The system of claim 8 , wherein the machine-readable instruction that, when executed by the processor, causes the processor to produce the pedestrian assistance countermeasure comprises a machine-readable instruction that, when executed by the processor, causes the processor to produce a command signal for at least one of:
a vehicle; or the infrastructure element.

10 . The system of claim 1 , wherein:
the machine-readable instructions further comprise a machine-readable instruction that, when executed by the processor, causes the processor to identify an overt feature of confusion based on at least one of a geographical or temporal similarity between pedestrians classified as in the impaired decision-making state; and the machine-readable instruction that, when executed by the processor, causes the processor to produce the pedestrian assistance countermeasure comprises a machine-readable instruction that, when executed by the processor, causes the processor to produce a report of the overt feature of confusion.

11 . The system of claim 1 , wherein the machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state comprises a machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state based on at least one of a physical movement of the pedestrian or a physical trait of the pedestrian.

12 . The system of claim 1 , wherein the machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state comprises a machine-readable instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state based on context data associated with the pedestrian.

13 . A non-transitory machine-readable medium comprising instructions that, when executed by a processor, cause the processor to:
determine, from interaction data collected by a user device of a pedestrian, an interaction characteristic of the pedestrian; classify the pedestrian as in an impaired decision-making state based on the interaction characteristic of the pedestrian deviating from baseline interaction data; and produce a pedestrian assistance countermeasure responsive to a determined impaired decision-making state for the pedestrian.

14 . The non-transitory machine-readable medium of claim 13 , wherein:
the instruction that, when executed by the processor, causes the processor to classify the pedestrian as in the impaired decision-making state comprises an instruction that, when executed by the processor, causes the processor to compare the interaction characteristic of the pedestrian to the baseline interaction data; and the baseline interaction data comprises at least one of:
an interaction pattern of the pedestrian; or
an interaction pattern of an additional individual.

15 . The non-transitory machine-readable medium of claim 13 , wherein the instruction that, when execute

Assignees

• Toyota Eng & Mfg North America
• Toyota Motor Co Ltd

Inventors

• Austin Benjamin Piya
• Gupta Rohit
• Babian Philip J
• Eren Ali C
• Garrett William Patrick
• Kirschweng Rebecca L
• Tykoski Dianne O

Classifications

• G08G1/0112

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G08G1/0116

  from roadside infrastructure, e.g. beacons · CPC title

• G08G1/005 Primary

  including pedestrian guidance indicator · CPC title