IP Library › Granted Patent US 12,243,436
Granted Patent B2
US 12,243,436 · App. 17/516,239 · Granted Mar 4, 2025

Probability-based obstacle avoidance

Inventors: Grzegorz Marian Kawiecki (El Escorial, ES); Wojciech Dabrowski (Gdynia, PL); Szymon Jan Trabala (Sopot, PL)
Assignee: THE BOEING COMPANY
G08G5/045G06N7/01G06N20/00G08G5/003G08G5/006G08G5/0069B64U10/14B64U2201/10
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 12,243,436
App. No.
17/516,239
Granted
Mar 4, 2025
Kind
B2
Abstract

A system includes an interface configured to receive sensor data corresponding to a potential hazard associated with a travel path of a vehicle. The system also includes an obstacle database including probability distributions of potential obstacles. The system further includes one or more processors coupled to the interface and configured to generate a probability index associated with the potential hazard and to determine whether to modify the travel path based on the probability index and the probability distributions.

Claims (42)

1. A system, comprising:

an interface configured to receive sensor data corresponding to a potential hazard associated with a travel path of a vehicle;

an obstacle database including probability distributions of potential obstacles, wherein each probability distribution of the probability distributions identifies an estimated spatial probability of the vehicle encountering a corresponding potential obstacle; and

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

compare the sensor data to potential obstacles of the obstacle database;

generate a probability index associated with the potential hazard; and

determine whether to modify the travel path based on the probability index and the probability distributions.

2. The system of claim 1 , wherein the probability index corresponds to a likelihood of the vehicle encountering the potential hazard along the travel path.

3. The system of claim 2 , wherein the probability index is determined based on a spatial and temporal probability distribution associated with the potential hazard.

4. The system of claim 1 , wherein the one or more processors are configured to apply machine learning to determine a corresponding probability distribution associated with the potential hazard.

5. The system of claim 1 , wherein the one or more processors are configured to apply machine learning to determine whether to modify the travel path.

6. The system of claim 1 , wherein the one or more processors are configured to, responsive to determining that the potential hazard does not match any of the potential obstacles of the obstacle database:

compute a first cumulative probability index associated with the travel path;

compute a second cumulative probability index associated with an alternate travel path; and

determine whether to transition to the alternate travel path at least partially based on a comparison between the first cumulative probability index and the second cumulative probability index.

7. The system of claim 6 , wherein the one or more processors are configured to determine whether to transition to the alternate travel path further based on a trip efficiency metric, a magnitude of at least one of the first cumulative probability index or the second cumulative probability index, an instruction from a human operator, or any combination thereof.

8. The system of claim 1 , further comprising the vehicle and one or more sensors, the one or more sensors configured to generate the sensor data, and wherein the interface, the obstacle database, the one or more sensors, and the one or more processors are integrated into the vehicle.

9. The system of claim 8 , wherein the vehicle comprises an air-based vehicle.

10. The system of claim 1 , wherein the one or more processors are further configured to:

compare a signature of the potential hazard to signatures of the potential obstacles; and

in response to determining that the signature of the potential hazard does not match any of the signatures of the potential obstacles, generate the probability index associated with the potential hazard.

11. The system of claim 10 , wherein the potential obstacles correspond to at least one of: a stationary natural object, a stationary manmade object, a mobile natural object, a mobile manmade object, hazardous weather, a geofenced region, or a prohibited travel region.

12. A method, comprising:

receiving, by one or more processors, sensor data corresponding to a potential hazard associated with a travel path of a vehicle;

comparing the sensor data to potential obstacles of an obstacle database that includes probability distributions of potential obstacles, wherein each probability distribution of the probability distributions identifies an estimated spatial probability of the vehicle encountering a corresponding potential obstacle;

generating, by the one or more processors, a probability index associated with the potential hazard; and

determining, by the one or more processors, whether to modify the travel path based on the probability index.

13. The method of claim 12 , wherein the probability index corresponds to a likelihood of the vehicle encountering the potential hazard along the travel path.

14. The method of claim 13 , wherein the probability index is determined based on a spatial and temporal probability distribution associated with the potential hazard.

15. The method of claim 12 , wherein determining whether to modify the travel path is based at least partially on machine learning.

16. The method of claim 12 , wherein determining whether to modify the travel path comprises:

computing a first cumulative probability index associated with the travel path;

computing a second cumulative probability index associated with an alternate travel path; and

determining whether to transition to the alternate travel path at least partially based on a comparison between the first cumulative probability index and the second cumulative probability index.

17. The method of claim 16 , wherein determining whether to transition to the alternate travel path is further based on a trip efficiency metric, a magnitude of at least one of the first cumulative probability index and the second cumulative probability index, an instruction from a human operator, or any combination thereof.

18. The method of claim 12 , further comprising comparing a signature of the potential hazard to signatures of the potential obstacles of the obstacle database, and wherein the probability index associated with the potential hazard is generated in response to determining that the signature of the potential hazard does not match any of the signatures of the potential obstacles.

19. A non-transitory, computer-readable medium storing instructions that, when executed by a processor, cause the processor to initiate, perform, or control operations comprising:

receiving sensor data corresponding to a potential hazard associated with a travel path of a vehicle;

comparing the sensor data to potential obstacles of an obstacle database that includes probability distributions of potential obstacles, wherein each probability distribution of the probability distributions identifies an estimated spatial probability of the vehicle encountering a corresponding potential obstacle;

generating a probability index associated with the potential hazard; and

determining whether to modify the travel path based on the probability index.

20. The non-transitory, computer-readable medium of claim 19 , wherein the probability index is determined based on a spatial and temporal probability distribution associated with the potential hazard.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 1, 2021
From: KAWIECKI, GRZEGORZ MARIAN; DABROWSKI, WOJCIECH; TRABALA, SZYMON JAN
To: THE BOEING COMPANY
Reel/Frame 057985/0178 →
Continuity (2)
Provisional Application 63135227 · Jan 8, 2021
Related Publication 20220223059A1 · Jul 14, 2022
References Cited (34)
US 9361591B2 · Na · 2016 [cited by examiner]
US 9542849B1 · Bertram et al. · 2017 [cited by applicant]
US 9632502B1 · Levinson · 2017 [cited by examiner]
US 11553303B2 · Hasegawa et al. · 2023 [cited by applicant]
US 20140122409A1 · Na et al. · 2014 [cited by applicant]
US 20150206438A1 · Marsden · 2015 [cited by examiner]
US 20170193830A1 · Fragoso · 2017 [cited by examiner]
US 20190196007A1 · Fucke et al. · 2019 [cited by applicant]
US 20210173415A1 · Cajias · 2021 [cited by examiner]
CN 109116867A · 2019 [cited by applicant]
EP 3508869A1 · 2019 [cited by applicant]
“The Drone Analyst Breaks Down Sense and Avoid,” The Drone Analyst Breaks Down Sense and Avoid—Drone Business Center, https://dronebusiness.center/drone-analyst-breaks-sense-avoid-12329/, Sep. 22, 2016, pp. 1-4. [cited by applicant]
Banerjee, Mandrita, et al., A blockchain future for internet of things security: a position paper, Digital Communications and Networks, 2018, vol. 4, pp. 149-160. [cited by applicant]
Choi, Jeong-Min et al., “Self-learning navigation algorithm for vision-based mobile robots using machine learning algorithms,” Journal of Mechanical Science and Technology, 2011, vol. 25, Issue 1, pp. 247-254. [cited by applicant]
Consumer drone shipments worldwide 2015-2021, Statista, https://www.statista.com/statistics/608887/consumer-drone-shipments-worldwide/, pp. 1-2. [cited by applicant]
Dayton, John et al., “Obstacle Avoidance System for UAVs using Computer Vision,” California Polytechnic University, Pomona, CA 91768, Mar. 7, 2014, pp. 1-8. [cited by applicant]
Dima, Cristian et al., “Classifier Fusion for Outdoor Obstacle Detection,” Engineering Computer Science, IEEE International Conference on Robotics and Automation, 2004, pp. 1-7. [cited by applicant]
Dima, Cristian, et al., “Active Learning for Outdoor Obstacle Detection,” The Robotics Institute, Carnegie Mellon University, Jun. 2005, pp. 1-8. [cited by applicant]
Gellerman, Nicholas et al., “A Terrain Avoidance Algorithm Based on the Requirements of Terrain Awareness and Warning Systems,” 2015 IEEE Aerospace Conference, 2015, pp. 1-6, doi: 10.1109/AERO.2015.7119160. [cited by applicant]
Johnsson, Julie et al., “Boeing Is Getting Ready to Sell “Flying Taxis” In the Next Decade,” The Washington Post, Mar. 6, 2018, pp. 1-6. [cited by applicant]
Kulic, Ranka, et al., “Autonomous Vehicle Obstacle Avoiding and Goal Position Reaching by Virtual Obstacle,” Proceedings of the European Control Conference, Jul. 2-5, 2007, pp. 2484-2491. [cited by applicant]
Linn, Allison, “Flying car not as far-fetched a fantasy as you might think,” Honoluluadvertiser.com, Aug. 29, 2004, Obstacle Avoidance System for UAVs using Computer Vision. 1 pg. [cited by applicant]
Michels, Jeff et al. “High Speed Obstackle Avoidance using Monocular Vision and Reinforcement Learning,” Conference: Machine Learning, Proceedings of the Twenty-Second International Conference (ICML 2005), Bonn, Germany… [cited by applicant]
Nelson, Chris, “Airbus flying cars accelerate city transport revolution,” TheNationalNews.com, Apr. 10, 2017, https://www.thenationalnews.com/business/airbus-flying-cars-accelerate-city-transport-revolution-1.56434, pp.… [cited by applicant]
Otto, Robert P., “Small Unmanned Aircraft Systems (SUAS) Flight Plan: 2016-2036,” U.S. Air Force, pp. 1-94. [cited by applicant]
Outchakoucht, Aissam et al. “Dynamic Access Control Policy based on Blockchain and Machine Learning for the Internet of Things,” International Journal of Advanced Computer Science and Applications, vol. 8, No. 7, 2017, … [cited by applicant]
Extended European Search Report for Application No. 21213364.9 dated Jun. 3, 2022, 8 pgs. [cited by applicant]
Aguilar, Wilbert G., et al. “Obstacle avoidance for low-cost UAVs,” 2017 IEEE 11th Inernational Conference on Semantic Computing, pp. 1-6. [cited by applicant]
Branch, Arthur et al., “A Design Study for the Safe Integration of Unmanned Aerial Systems into the National Airspace System,” 2016 IEEE Systems and Information Engineering Design Conference (SIEDS '16), pp. 1-6. [cited by applicant]
Richards, Blin et al., “Obstacle Avoidance System for UAVs Using Computer Vision,” California State Polytechnic University, Pomona, CA, Mar. 7, 2014, http://hdl.handle.net/10211.3/119764; pp. 1-8. [cited by applicant]
Unknown, “The Business of Luxurious Cars: Must-Read Reports and Analysis,” https://web.archive.org/ web/20170720171009/http://www.reportlinker.com/ci02180/Luxury-Automobile.html, retrieved Oct. 4, 2024, pp. 1-7. [cited by applicant]
Anonymous, “$700 Billion Land, Water, Air Autonomous Vehicles Market 2017-2037,” Research and Markets, Oct. 27, 2017, https://www.prnewswire.com/news-releases/700-billion-land-water-air-autonomous-vehicles-market-2017-2… [cited by applicant]
Anonymous, “Disruptive Mobility portfolio unites future aerospace vehicle development,” Boeing News Now, Mar. 16, 2018, http://active.boeing.com/boeing-now/story.cfm? SID=14154&key=E5F795DC98A2421BF72A740EB7104D45096486… [cited by applicant]
Ebel, Thomas, “Obstacle Databases for Instrument Flight: A risk Analysis”, Technical Notes, Journal of Aerospace Information Systems, vol. 1, No. 10, Oct. 2019, pp. 1-4. [cited by applicant]