IP Library › Granted Patent US 12,722,645
Granted Patent B2
US 12,722,645 · App. 18/889,884 · Granted Sep 1, 2026

Behavior estimation device and behavior estimation method for saddle-type vehicle

Inventors: Yuki Uto (Hyogo, JP); Taichi Inaba (Hyogo, JP); Hisato Tokunaga (Hyogo, JP); Takayuki Higashi (Hyogo, JP)
Assignee: KAWASAKI MOTORS, LTD.
B60W40/12G01S19/14B60W2300/36B60W2510/0638
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 12,722,645
App. No.
18/889,884
Granted
Sep 1, 2026
Kind
B2
Abstract

There is provided a behavior estimation device and a behavior estimation method for analyzing a behavior of a saddle-type vehicle including a vehicle body, a drive source, and a grounded traveling body. The behavior estimation device includes: a receiving device that receives an output instruction value of the drive source by a driver and a rotational speed of the drive source, the output instruction value and the rotational speed being detected by a sensor provided in the saddle-type vehicle during traveling of the saddle-type vehicle; and a processing device that estimates whether the grounded traveling body is in a grounded state in which the grounded traveling body is in contact with a road surface or in a jump state in which the grounded traveling body is separated from the road surface based on the output instruction value and the rotational speed received.

Claims (48)

1 . A behavior estimation device configured to analyze a behavior of a saddle-type vehicle including a vehicle body, a drive source, an operating element configured to receive an operation of a driver, and a grounded traveling body configured to travel using a driving force generated by the drive source, the behavior estimation device comprising:

a receiving device configured to receive an output instruction value of the drive source which changes in accordance with an operation amount of the operating element and a rotational speed of the drive source, the output instruction value and the rotational speed being detected by a sensor provided in the saddle-type vehicle during traveling of the saddle-type vehicle; and

a processing device configured to estimate whether the grounded traveling body is in a grounded state in which the grounded traveling body is in contact with a road surface or in a jump state in which the grounded traveling body is separated from the road surface based on the output instruction value and the rotational speed received by the receiving device, wherein

the processing device is configured to:

calculate a temporal change of the output instruction value; and

estimate whether the grounded traveling body is in the grounded state or in the jump state based on determination that the temporal change is a characteristic temporal change occurring before and after a jump of the saddle-type vehicle.

2 . The behavior estimation device according to claim 1 , wherein

the processing device receives time-series data of the output instruction value and the rotational speed from the receiving device, and outputs time-series data of an estimation result indicating whether the saddle-type vehicle is in the grounded state or the jump state.

3 . The behavior estimation device according to claim 1 , wherein

the grounded state includes:

a pre-jump grounded state indicating a state in which the grounded traveling body is in contact with the ground and is in a middle of transitioning to the jump state;

a landing state indicating a state in which the grounded traveling body is in contact with the ground and lands from the jump state; and

a normal grounded state indicating a state in which the grounded traveling body is in contact with the ground and that is other than the pre-jump grounded state and the landing state, and

the processing device estimates which of the pre-jump grounded state, the landing state, the normal grounded state, and the jump state corresponds to.

4 . The behavior estimation device according to claim 1 , wherein

the processing device further estimates whether the saddle-type vehicle is in the grounded state or the jump state based on a vehicle speed and a front-rear acceleration, which are detected by the sensor provided in the saddle-type vehicle during the traveling of the saddle-type vehicle.

5 . The behavior estimation device according to claim 4 , wherein

the processing device calculates a vehicle speed and a front-rear acceleration of the saddle-type vehicle based on time-series data of position information of the saddle-type vehicle.

6 . The behavior estimation device according to claim 5 , wherein

the receiving device receives the time-series data of the position information of the saddle-type vehicle from a GNSS sensor serving as the sensor.

7 . The behavior estimation device according to claim 1 , wherein

the processing device causes a display device to display information in which an estimation result as to whether the saddle-type vehicle is in the grounded state or the jump state is superimposed on a map based on position information of the saddle-type vehicle and the estimation result.

8 . The behavior estimation device according to claim 1 , wherein

the processing device applies an estimation model in which the output instruction value and the rotational speed are input and an estimation result indicating whether the saddle-type vehicle is in the grounded state or the jump state is output, and

the estimation model is created by learning a feature based on the output instruction value, a feature based on the rotational speed, and correct data indicating whether the saddle-type vehicle is in the grounded state or the jump state in a case of a combination of the features as training data.

9 . The behavior estimation device according to claim 8 , wherein

the processing device receives time-series data of the output instruction value and the rotational speed from the receiving device, and

the processing device performs processing of matching sampling rates of the output instruction value and the rotational speed by down-sampling the time-series data of at least one of the output instruction value and the rotational speed, and then inputs processing result to the estimation model.

10 . The behavior estimation device according to claim 8 , wherein

the training data includes data detected when the saddle-type vehicle travels along a plurality of traveling paths.

11 . The behavior estimation device according to claim 1 , wherein

the saddle-type vehicle is a motorcycle traveling on an unpaved road.

12 . The behavior estimation device according to claim 1 , wherein

the processing device is configured to estimate whether the grounded traveling body is in the grounded state or in the jump state based on determination of a temporal change of the output instruction value in which the output instruction value decreases from a large value to zero and thereafter changes again from zero to a large value during traveling of the saddle-type vehicle.

13 . The behavior estimation device according to claim 1 , wherein

the processing device is configured to estimate whether the grounded traveling body is in the grounded state or in the jump state based on a correlation between the output instruction value and the rotational speed.

14 . The behavior estimation device according to claim 13 , wherein

the processing device is configured to:

calculate a temporal change of the output instruction value; and

estimate whether the grounded traveling body is in the grounded state or in the jump state based on determination that the temporal change is a characteristic temporal change occurring before and after a jump of the saddle-type vehicle, and a correlation between the output instruction value and the rotational speed.

15 . The behavior estimation device according to claim 14 , wherein

the correlation includes a correlation in which a load generated on the drive source in the jump state is smaller than the load generated on the drive source in the grounded state.

16 . The behavior estimation device according to claim 14 , wherein

the correlation includes a correlation in which an increase amount in the rotational speed corresponding to an increase amount of the output instruction value in the jump state is greater than the increase amount in the rotational speed corresponding to the increase amount of the output instruction value in the grounded state.

17 . A behavior estimation method for causing a computer to analyze a behavior of a saddle-type vehicle including a vehicle body, a drive source, a sensor configured to detect an instructed amount of a change in output of the drive source by a driver, and a grounded traveling body that is in contact with a road surface and travels by a driving force generated by the drive source, the behavior estimation method comprising:

receiving the instructed amount of the change in output of the drive source detected by the sensor during the traveling of the saddle-type vehicle;

calculating a temporal change of the instructed amount of the change in output of the drive source; and

estimating whether the grounded traveling body is in a grounded state in which the grounded traveling body is in contact with the road surface or in a jump state in which the grounded traveling body is separated from the road surface based on determination that the temporal change is a characteristic temporal change occurring before and after a jump of the saddle-type vehicle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 21, 2024
From: UTO, YUKI; INABA, TAICHI; TOKUNAGA, HISATO; HIGASHI, TAKAYUKI
To: KAWASAKI MOTORS, LTD.
Reel/Frame 068952/0610 →
Priority Claims (1)
JP 2023-150656 · Sep 19, 2023 · national
Continuity (1)
Related Publication 20250091590A1 · Mar 20, 2025
References Cited (12)
US 20130041522A1 · Mori · 2013 [cited by examiner]
US 20160009275A1 · Hieda · 2016 [cited by examiner]
US 20170101008A1 · Hirokami · 2017 [cited by examiner]
US 20180257740A1 · Kikkawa · 2018 [cited by examiner]
US 20200012964A1 · Shimazu · 2020 [cited by examiner]
US 20210019960A1 · Matsuda · 2021 [cited by examiner]
US 20210269016A1 · Hattori · 2021 [cited by examiner]
US 20230083770A1 · Kurotobi · 2023 [cited by examiner]
US 20240335758A1 · Adams · 2024 [cited by examiner]
US 20250171099A1 · Tanaka · 2025 [cited by examiner]
JP 2019064469A · 2019 [cited by applicant]
WO WO2023053270A1 · 2023 [cited by examiner]