IP Library › Granted Patent US 12,462,694
Granted Patent B2
US 12,462,694 · App. 17/822,311 · Granted Nov 4, 2025

Route planning device, route planning method, and computer program product

Inventors: Rie Katsuki (Kawasaki, JP); Noriyuki Hirayama (Fuchu, JP); Toshimitsu Kaneko (Kawasaki, JP)
Assignee: KABUSHIKI KAISHA TOSHIBA
G08G5/32G08G5/22G08G5/34G08G5/55G08G5/57G08G5/59G08G5/80
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 12,462,694
App. No.
17/822,311
Granted
Nov 4, 2025
Kind
B2
Abstract

A route planning device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to: calculate a tentative route passing through a plurality of tour points disposed in a virtual space that is acquired by removing an obstacle from a space including the obstacle; and derive a route with one or more via points added around an interference point between the obstacle included in the space and the tentative route with a calculation accuracy corresponding to a precision of via point calculation.

Claims (63)

1 . A route planning device comprising:

a memory; and

one or more processors coupled to the memory and configured to:

calculate a tentative route passing through a plurality of tour points disposed in a virtual space that is acquired by removing an obstacle from a space including the obstacle; and

derive with a calculation accuracy corresponding to a precision of via point calculation, a route with one or more via points added around an interference point between the obstacle included in the space and the tentative route,

wherein

the one or more processors are further configured to:

calculate, based on at least one selected from a collision severity of the obstacle and an obstacle avoidance performance of a mobile body, the precision to be lower as the collision severity is lower and to be lower as the obstacle avoidance performance is higher;

search a search space with a search accuracy corresponding to the precision, and add the one or more via points around the interference point; and

output the tour points and the one or more via points to a display in different display modes,

wherein

the one or more processors are further configured to:

change a density of a group of elements in obstacle information of the obstacle expressed by the group of elements, which are three-dimensional voxels in a three-dimensional space, to a lower density as the precision is lower;

identify the interference point between the obstacle expressed by the changed obstacle information and the tentative route;

search the search space based on the precision and the interference point, and adds the one or more via points around the interference point; and

identify the interference point between the tentative route and an obstacle area with a wider margin area added around the obstacle as the precision is higher.

2 . The device according to claim 1 , wherein the one or more processors are configured to calculate the one or more via points with a lower accuracy as the precision is lower.

3 . The device according to claim 1 , wherein the one or more processors are configured to search the search space for each search point at a longer search interval as the precision is lower, and add the one or more via points to the search point around the interference point.

4 . The device according to claim 1 , wherein the one or more processors are further configured to output the route.

5 . The device according to claim 4 , wherein the one or more processors are configured to change the route based on instruction information, upon receiving the instruction information including at least one selected from an instruction to add an additional via point to the route and an instruction to change a position of the via point.

6 . The device according to claim 1 , wherein the obstacle avoidance performance is defined by at least one selected from an observation accuracy of the mobile body and a positioning accuracy of the mobile body.

7 . The device according to claim 1 , wherein the one or more processors are configured to derive the route by adding the input one or more via points to the tentative route.

8 . The device according to claim 1 , wherein the tentative route comprises the tour points and a straight line connecting the tour points.

9 . The device according to claim 1 , wherein the one or more processors are further configured to, when a total length of the route is less than a length acquired by adding a threshold to a total length of the tentative route used for calculation of the route, identify the route as an output target route.

10 . The device according to claim 1 , wherein the tentative route is a tour route that passes through the tour points at least once.

11 . The device according to claim 1 , wherein

the one or more processors are further configured to:

control, for each of a plurality of the tentative routes with at least part of a via route of the tour points being different from each other, the via point addition processing to repeat, in order from the tentative route of a lowest cost, route derivation processing for deriving a route acquired by adding the one or more via points to the tentative route; and

determine the route of a lowest cost to be a suboptimal route, when the route derivation processing satisfies a termination condition.

12 . The device according to claim 11 , wherein the one or more processors are configured to determine that the termination condition is satisfied, when a number of repetitions of the route derivation processing is equal to or greater than a threshold, and a calculation time of the route derivation processing becomes equal to or longer than a prescribed time or a cost of the derived route is equal to or lower than a cost of another tentative route that is next lowest with respect to the cost of the tentative route used to derive the route.

13 . The device according to claim 11 , wherein the one or more processors are configured to determine the route selected by a user as the suboptimal route, among a plurality of the routes derived by repeating the route derivation processing.

14 . The device according to claim 1 , wherein the precision is calculated by using following equations

p 1= k obs 1/ m obs +ε

p 2= p 1+ k col m col

where p 1 represents a first precision, p 2 represents the final calculated precision, k obs and k col represent gains, ε is a number greater than zero, m col represents the collision severity, and m obs represents the obstacle avoidance performance m obs .

15 . A route planning method comprising:

calculating a tentative route passing through a plurality of tour points disposed in a virtual space that is acquired by removing an obstacle from a space including the obstacle; and

deriving, with a calculation accuracy corresponding to a precision of via point calculation, a route with one or more via points added around an interference point between the obstacle included in the space and the tentative route,

wherein

the method further includes:

calculating, based on at least one selected from a collision severity of the obstacle and an obstacle avoidance performance of a mobile body, the precision to be lower as the collision severity is lower and to be lower as the obstacle avoidance performance is higher;

searching a search space with a search accuracy corresponding to the precision, and add the one or more via points around the interference point; and

outputting the tour points and the one or more via points to a display in different display modes,

wherein

the method further includes:

changing a density of a group of elements in obstacle information of the obstacle expressed by the group of elements, which are three-dimensional voxels in a three-dimensional space, to a lower density as the precision is lower;

identifying the interference point between the obstacle expressed by the changed obstacle information and the tentative route;

searching the search space based on the precision and the interference point, and adds the one or more via points around the interference point; and

identifying the interference point between the tentative route and an obstacle area with a wider margin area added around the obstacle as the precision is higher.

16 . A computer program product comprising a non-transitory computer-readable medium including programmed instructions, the instructions causing a computer to execute a method comprising:

calculating a tentative route passing through a plurality of tour points disposed in a virtual space that is acquired by removing an obstacle from a space including the obstacle; and

deriving, with a calculation accuracy corresponding to a precision of via point calculation, a route with one or more via points added around an interference point between the obstacle included in the space and the tentative route,

wherein

the method further includes:

calculating, based on at least one selected from a collision severity of the obstacle and an obstacle avoidance performance of a mobile body, the precision to be lower as the collision severity is lower and to be lower as the obstacle avoidance performance is higher;

searching a search space with a search accuracy corresponding to the precision, and add the one or more via points around the interference point; and

outputting the tour points and the one or more via points to a display in different display modes,

wherein

the method further includes:

changing a density of a group of elements in obstacle information of the obstacle expressed by the group of elements, which are three-dimensional voxels in a three-dimensional space, to a lower density as the precision is lower;

identifying the interference point between the obstacle expressed by the changed obstacle information and the tentative route;

searching the search space based on the precision and the interference point, and adds the one or more via points around the interference point; and

identifying the interference point between the tentative route and an obstacle area with a wider margin area added around the obstacle as the precision is higher.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 25, 2022
From: KATSUKI, RIE; HIRAYAMA, NORIYUKI; KANEKO, TOSHIMITSU
To: KABUSHIKI KAISHA TOSHIBA
Reel/Frame 060901/0895 →
Priority Claims (1)
JP 2021-170495 · Oct 18, 2021 · national
Continuity (1)
Related Publication 20230122583A1 · Apr 20, 2023
References Cited (14)
US 9821801B2 · Di Cairano · 2017 [cited by examiner]
US 10810688B1 · Lemons · 2020 [cited by examiner]
US 20130024107A1 · Xie et al. · 2013 [cited by applicant]
US 20140379179A1 · Goossen · 2014 [cited by examiner]
US 20180364060A1 · Katsuki · 2018 [cited by examiner]
US 20190170519A1 · Anwar · 2019 [cited by examiner]
US 20230244235A1 · Okada · 2023 [cited by examiner]
JP 2011113488A · 2011 [cited by applicant]
JP 2012190405A · 2012 [cited by applicant]
JP 2019006143A · 2019 [cited by applicant]
JP 2020161091A · 2020 [cited by applicant]
Fetanat, Masoud, et al. “Optimization of dynamic mobile robot path planning based on evolutionary methods”, IEEE, Sep. 21, 2015 (Year: 2015). [cited by examiner]
Zhao, Kun, et al., “3D Detection for Occluded Vehicles From Point Clouds”, Apr. 8, 2021, IEEE Intelligent Transportation Systems Magazine (Year: 2021). [cited by examiner]
Japanese Office Action dated Dec. 3, 2024, issued in Japanese Patent Application No. 2021-170495 (with English translation). [cited by applicant]