IP Library › Granted Patent US 12,749,393
Granted Patent B2
US 12,749,393 · App. 18/642,336 · Granted Sep 29, 2026

Detecting safety-relevant road traffic conflicts

Inventors: Johan Engstrom (Los Gatos, CA); Francesca Margherita Favaro (Los Gatos, CA); Azadeh Dinparastdjadid (Sunnyvale, CA); Shuyuan Liu (San Jose, CA); John Michael Scanlon (Burlingame, CA); Trent William Victor (London, GB)
Assignee: Waymo LLC
G08G1/0133G08G1/0112G08G1/166
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 12,749,393
App. No.
18/642,336
Granted
Sep 29, 2026
Kind
B2
Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automatically designating traffic scenarios as safety-relevant traffic conflicts between agents in a driving environment. One of the methods includes receiving data representing a traffic scenario involving two agents; computing a safety-relevant metric for a first plurality of time points of the traffic scenario; computing a surprise metric for a second plurality of time points of the traffic scenario; determining that the surprise metric satisfies a surprise threshold within a threshold time window of the safety-relevant metric satisfying a safety-relevant threshold; and in response, designating the traffic scenario as a safety-relevant traffic conflict.

Claims (48)

1 . A computer-implemented method comprising:

receiving, by an onboard system of an autonomously driven vehicle (ADV), data representing a traffic scenario involving an agent and another entity in a driving environment;

computing a safety-relevant metric for a first plurality of time points of the traffic scenario, wherein the safety-relevant metric represents a level of safety risk between the agent and the other entity;

computing a surprise metric for a second plurality of time points of the traffic scenario, wherein the surprise metric represents a deviation of the agent from a predicted state of the agent in the traffic scenario;

determining that the surprise metric satisfies a surprise threshold within a threshold time window of the safety-relevant metric satisfying a safety-relevant threshold;

in response, designating the traffic scenario as a safety-relevant traffic conflict; and

causing the ADV to perform a driving maneuver in response to designating the traffic scenario as a safety-relevant traffic conflict.

2 . The method of claim 1 , further comprising:

evaluating a collection of traffic scenarios represented in trip log data;

computing safety-relevant metrics and surprise metrics for a plurality of time points in each traffic scenario of the collection of traffic scenarios; and

identifying all safety-relevant traffic conflicts as the traffic scenarios having a safety-relevant metric satisfying the safety-relevant threshold within the threshold time window of the surprise metric for the traffic scenario satisfying the surprise threshold.

3 . The method of claim 1 , wherein the safety-relevant metric represents a spatiotemporal proximity of the agent to the other entity.

4 . The method of claim 3 , wherein the safety-relevant metric is a time-to-collision metric.

5 . The method of claim 3 , wherein the safety-relevant metric is a post-encroachment-time metric.

6 . The method of claim 3 , wherein the safety-relevant metric is a required deceleration metric.

7 . The method of claim 1 , wherein the safety-relevant metric is a potential injury metric that represents a measure of severity of a potential collision between the agent and the other entity in the traffic scenario.

8 . The method of claim 1 , wherein the data representing the traffic scenario comprises data representing a currently occurring traffic scenario for the ADV.

9 . The method of claim 1 , wherein:

causing the ADV to perform a driving maneuver in response to designating the traffic scenario as a safety-relevant traffic conflict comprises causing the ADV to perform a defensive driving maneuver in response to designating the traffic scenario as a safety-relevant traffic conflict.

10 . The method of claim 8 , further comprising:

generating, on a user interface of the ADV, a warning of the traffic scenario as a safety-relevant traffic conflict.

11 . The method of claim 8 , further comprising:

determining that a candidate trajectory may lead to a safety-relevant traffic conflict; and

lowering the probability that the candidate trajectory is selected by the ADV.

12 . The method of claim 1 , wherein the other entity is another agent in the driving environment.

13 . The method of claim 1 , wherein the other entity is an object in the driving environment.

14 . A system comprising: one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

receiving, by an onboard system of an autonomously driven vehicle (ADV), data representing a traffic scenario involving an agent and another entity in a driving environment;

computing a safety-relevant metric for a first plurality of time points of the traffic scenario, wherein the safety-relevant metric represents a level of safety risk between the agent and the other entity;

computing a surprise metric for a second plurality of time points of the traffic scenario, wherein the surprise metric represents a deviation of the agent from a predicted state of the agent in the traffic scenario;

determining that the surprise metric satisfies a surprise threshold within a threshold time window of the safety-relevant metric satisfying a safety-relevant threshold;

in response, designating the traffic scenario as a safety-relevant traffic conflict; and

causing the ADV to perform a driving maneuver in response to designating the traffic scenario as a safety-relevant traffic conflict.

15 . The system of claim 14 , wherein the operations further comprise:

evaluating a collection of traffic scenarios represented in trip log data;

computing safety-relevant metrics and surprise metrics for a plurality of time points in each traffic scenario of the collection of traffic scenarios; and

identifying all safety-relevant traffic conflicts as the traffic scenarios having a safety-relevant metric satisfying the safety-relevant threshold within the threshold time window of the surprise metric for the traffic scenario satisfying the surprise threshold.

16 . The system of claim 14 , wherein the safety-relevant metric represents a spatiotemporal proximity of the agent to the other entity.

17 . The system of claim 16 , wherein the safety-relevant metric is a time-to-collision metric.

18 . The system of claim 16 , wherein the safety-relevant metric is a post-encroachment-time metric.

19 . The system of claim 16 , wherein the safety-relevant metric is a required deceleration metric.

20 . A computer storage medium encoded with a computer program, the program comprising instructions that are operable, when executed by data processing apparatus, to cause the data processing apparatus to perform operations comprising:

receiving, by an onboard system of an autonomously driven vehicle (ADV), data representing a traffic scenario involving an agent and another entity in a driving environment;

computing a safety-relevant metric for a first plurality of time points of the traffic scenario, wherein the safety-relevant metric represents a level of safety risk between the agent and the other entity;

computing a surprise metric for a second plurality of time points of the traffic scenario, wherein the surprise metric represents a deviation of the agent from a predicted state of the agent in the traffic scenario;

determining that the surprise metric satisfies a surprise threshold within a threshold time window of the safety-relevant metric satisfying a safety-relevant threshold;

in response, designating the traffic scenario as a safety-relevant traffic conflict; and

causing the ADV to perform a driving maneuver in response to designating the traffic scenario as a safety-relevant traffic conflict.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 18, 2024
From: ENGSTROM, JOHAN; FAVARO, FRANCESCA MARGHERITA; DINPARASTDJADID, AZADEH; SCANLON, JOHN MICHAEL; LIU, SHUYUAN; VICTOR, TRENT WILLIAM
To: WAYMO LLC
Reel/Frame 068020/0550 →
Continuity (2)
Provisional Application 63460815 · Apr 20, 2023
Related Publication 20240355199A1 · Oct 24, 2024
References Cited (80)
US 11447142B1 · Engstrom et al. · 2022 [cited by applicant]
US 11926332B1 · Engstrom · 2024 [cited by examiner]
US 20170291602A1 · Newman et al. · 2017 [cited by applicant]
US 20220388505A1 · Sharma et al. · 2022 [cited by applicant]
US 20230078779A1 · Eng et al. · 2023 [cited by applicant]
US 20230359202A1 · Urtasun · 2023 [cited by examiner]
US 20240199084A1 · Supeene · 2024 [cited by examiner]
Avila et al., “An active inference approach to on-line agent monitoring in safety-critical systems,” Advanced Engineering Informatics, Aug. 13, 2015, 29(4):1083-1095. [cited by applicant]
Extended Search Report in European Appln. No. 24171568.9, dated Oct. 1, 2024, 10 pages. [cited by applicant]
Antony et al., “Behavioral, physiological, and neural signatures of surprise during naturalistic sports viewing,” Neuron, Jan. 2021, 109(2):377-90. [cited by applicant]
Bagdadi et al., “Jerky driving-an indicator of accident proneness?” Accident Analysis & Prevention, Jul. 1, 2021, 43(4), 1359-1363. [cited by applicant]
Berseth et al., “Smirl: Surprise minimizing reinforcement learning in unstable environments,” CoRR, submitted on Dec. 11, 2019, arXiv:1912.05510v4, 16 pages. [cited by applicant]
Bruineberg et al., “Free-energy minimization in joint agent-environment systems: A niche construction perspective,” Journal of theoretical biology, Oct. 14, 2018, 455:161-78. [cited by applicant]
Chai et al., “Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction,” CoRR, submitted on Oct. 12, 2019, arXiv:1910.05449v1, 14 pages. [cited by applicant]
Cheung et al., “Uncertainty and surprise jointly predict musical pleasure and amygdala, hippocampus, and auditory cortex activity,” Current Biology, Dec. 2, 2019, 29(23):4084-92. [cited by applicant]
De Freitas et al., “From driverless dilemmas to more practical commonsense tests for automated vehicles,” Proceedings of the national academy of sciences, Mar. 16, 2021, 118(11): e2010202118. [cited by applicant]
de Saint-Cyr et al., “Jokes and belief revision,” In 17th International Conference on Principles of Knowledge Representation and Reasoning (KR 2020), IJCAI: International Joint Conferences on Artificial Intelligence Org… [cited by applicant]
Engstrom et al., “Great expectations: a predictive processing account of automobile driving,” Theoretical issues in ergonomics science, Mar. 4, 2018, 19(2):156-94. [cited by applicant]
Engstrom et al., “Modeling road user response timing in naturalistic settings: a surprise-based framework,” CoRR, submitted on Aug. 18, 2022, arXiv:2208.08651v2, 19 pages. [cited by applicant]
Faraji et al., “Balancing new against old information: the role of puzzlement surprise in learning,” Neural Computation, Jan. 1, 2018, 30(1):34-83. [cited by applicant]
Findling et al., “Imprecise neural computations as a source of adaptive behaviour in volatile environments,” Nature Human Behaviour, Jan. 2021, 5(1):99-112. [cited by applicant]
Fiser et al., “Statistically optimal perception and learning: from behavior to neural representations,” Trends in cognitive sciences, Mar. 1, 2010, 14(3):119-30. [cited by applicant]
Franklin et al., “Structured event memory: A neuro-symbolic model of event cognition,” Psychological Review, Apr. 2020, 127(3):327. [cited by applicant]
Friston et al., “Active inference: a process theory,” Neural computation, Jan. 2017, 29(1):1-49. [cited by applicant]
Friston et al., “Dynamic representations and generative models of brain function,” Brain research bulletin, Feb. 1, 2001, 54(3):275-85. [cited by applicant]
Friston, “The free-energy principle: a unified brain theory?” Nature reviews neuroscience, Feb. 2010, 11(2):127-38. [cited by applicant]
Gershman et al., “The computational nature of memory modification,” Elife, Mar. 15, 2017, 6: e23763. [cited by applicant]
Gershman, “What does the free energy principle tell US about the brain?” CoRR, submitted on Jan. 23, 2019, arXiv:1901.07945v5, 10 pages. [cited by applicant]
Glascher et al., “States versus rewards: dissociable neural prediction error signals underlying model-based and model-free reinforcement learning,” Neuron, May 27, 2010, 66(4):585-95. [cited by applicant]
Glauz, “Application of traffic conflict analysis at intersections,” National Cooperative Highway Research Program Report, Feb. 1980, 118 pages. [cited by applicant]
Gold et al., “Predictability and uncertainty in the pleasure of music: a reward for learning?” Journal of Neuroscience, Nov. 20, 2019, 39(47):9397-409. [cited by applicant]
Gutenberg.org [online], “The poetics of aristotle,” available on before Dec. 26, 2008, via Internet Archive: Wayback Machine URL <https://web.archive.org/web/20240000000000*/https://www.gutenberg.org/files/1974/1974-h/1… [cited by applicant]
Hayden et al., “Surprise signals in anterior cingulate cortex: neuronal encoding of unsigned reward prediction errors driving adjustment in behavior,” Journal of Neuroscience, Mar. 16, 2011, 31(11), 4178-4187. [cited by applicant]
Hyden, “The development of a method for traffic safety evaluation: The swedish traffic conflicts technique,” Bulletin Lund Institute of Technology, Department, 1987(70). [cited by applicant]
ISO/TR 21974-1, Naturalistic driving studies—Vocabulary—Part 1: safety critical events, International Organization for Standardization, Nov. 2018, 15 pages. [cited by applicant]
Itti, “Bayesian surprise attracts human attention,” Vision Research, Jun. 2, 2009, 49(10):1295-306. [cited by applicant]
Kaelbling et al., “Planning and acting in partially observable stochastic domains,” Artificial Intelligence, May 1, 1998, 101(1-2):99-134. [cited by applicant]
Kolossa et al., “A computational analysis of the neural bases of bayesian inference,” Neuroimage, Feb. 1, 2015, 106: 222-237. [cited by applicant]
Kusano et al., “Methodology for determining maximum injury potential for automated driving system evaluation,” Traffic Injury Prevention, Oct. 10, 2022, 23(supl): S224-7. [cited by applicant]
Kusano et al., “Collision avoidance testing of the waymo automated driving system,” CoRR, submitted on Dec. 15, 2022, arXiv:2212.08148, 25 pages. [cited by applicant]
Lee et al., “Trust in automation: Designing for appropriate reliance,” Human factors, Mar. 2004, 46(1):50-80. [cited by applicant]
Liakoni et al., “Learning in volatile environments with the bayes factor surprise,” Neural Computation, Feb. 1, 2021, 33(2):269-340. [cited by applicant]
Macedo et al., “Modeling forms of surprise in artificial agents: empirical and theoretical study of surprise functions,” In Proceedings of the Annual Meeting of the Cognitive Science Society, 2004, 7 pages. [cited by applicant]
Marsh, “Introduction to continuous entropy,” Department of Computer Science, Princeton University, Dec. 13, 2013, 1034, 17 pages. [cited by applicant]
Martens et al., “The failure to act upon important information: where do things go wrong,” Vrije Universiteit, Amsterdam, The Netherlands, Jan. 2007, 307 pages. [cited by applicant]
Mellers et al., “Decision affect theory: Emotional reactions to the outcomes of risky options,” Psychological Science, Nov. 1997, 8(6):423-9 (abstract only). [cited by applicant]
Modirshanechi et al., “A taxonomy of surprise definitions,” Journal of Mathematical Psychology, Sep. 1, 2022, 110:102712. [cited by applicant]
Nayakanti et al., “Wayformer: Motion forecasting via simple & efficient attention networks,” CoRR, submitted on Jul. 12, 2022, arXiv:2207.05844v1, 20 pages. [cited by applicant]
Ozbay et al., “Derivation and validation of new simulation-based surrogate safety measure,” Transportation Research Record, Jan. 2008, 2083(1):105-113. [cited by applicant]
P'erez et al., “On jon snow's death: Plot twist and global fandom in game of thrones,” Culture & Psychology, Sep. 2020, 26(3): 384-400 (abstract only). [cited by applicant]
Pearce et al., “A model for pavlovian learning: variations in the effectiveness of conditioned but not of unconditioned stimuli,” Psychological Review, Nov. 1980, 87(6):532. [cited by applicant]
Piccinini et al., “How do drivers respond to silent automation failures? driving simulator study and comparison of computational driver braking models,” Human factors, Nov. 2020, 62(7):1212-29. [cited by applicant]
Plato.stanford.edu [online], “Philosophy of humor,” Nov. 20, 2012, retrieved on Jun. 27, 2024, retrieved from <https://plato.stanford.edu/entries/humor/?utm_campaign=observational%20comedy.&utm_medium-email&utm source=R… [cited by applicant]
Prat-Carrabin et al., “Human inference in changing environments with temporal structure,” Psychological Review, Oct. 2021, 128(5):879. [cited by applicant]
Preuschoff et al., “Pupil dilation signals surprise: Evidence for noradrenaline's role in decision making,” Frontiers in Neuroscience, Sep. 30, 2011, 5:115. [cited by applicant]
Raccah, “Humour et m'etaphore: quelques 'el'ements d'une analogie pour la construction d'un sens inattendu: Illustration sur un corpus de citations de George Bernard Shaw,” Revue de S'emantique et Pragmatique, Oct. 16, … [cited by applicant]
Rasanen et al., “Attention and expectation problems in bicycle-car collisions: an in-depth study,” Accident Analysis & Prevention, Sep. 1, 1998, 30(5):657-66 (abstract only). [cited by applicant]
Reisenzein et al., “The cognitive-evolutionary model of surprise: A review of the evidence,” Topics in cognitive science, Jan. 2019, 11(1):50-74. [cited by applicant]
Reisenzein, “ Exploring the strength of association between the components of emotion syndromes: The case of surprise,” Cognition & Emotion, Jan. 1, 2000, 14(1):1-38. [cited by applicant]
Rouhani et al., “Signed and unsigned reward prediction errors dynamically enhance learning and memory,” Elife, Mar. 4, 2021, e61077. [cited by applicant]
Scanlon et al., “Collision avoidance effectiveness of an automated driving system using a human driver behavior reference model in reconstructed fatal collisions,” Waymo, LLC. 2022, 27 pages. [cited by applicant]
Schwartenbeck et al., “Exploration, novelty, surprise, and free energy minimization,” Frontiers in psychology, Oct. 7, 2013, 4:710. [cited by applicant]
Seop.illc.uva.nl [online] “Aristotle's Rhetoric,” available on before May 11, 2015, via Internet Archive: Wayback Machine URL <https://web.archive.org/web/20230000000000*/https://seop.illc.uva.nl/entries/aristotle-rheto… [cited by applicant]
Seth et al., “Active interoceptive inference and the emotional brain,” Philosophical Transactions of the Royal Society B: Biological Sciences, Nov. 19, 2016, 371(1708):20160007. [cited by applicant]
Shannon, “A mathematical theory of communication,” The Bell system technical journal, Jul. 1948, p. 379-423. [cited by applicant]
Shany et al., “Surprise related activation in the nucleus accumbens interacts with music-induced pleasantness,” Social Cognitive and Affective Neuroscience, Apr. 2019, 14(4):459-70. [cited by applicant]
Sinclair et al., “Surprise and destabilize: Prediction error influences episodic memory reconsolidation,” Learning & memory, Aug. 1, 2018, 25(8):369-81. [cited by applicant]
Soltani et al., “Adaptive learning under expected and unexpected uncertainty,” Nature Reviews Neuroscience, Oct. 2019, 20(10): 635-644. [cited by applicant]
Sutton et al., “Reinforcement learning,” Journal of Cognitive Neuroscience, Jan. 28, 1999, 11(1): 126-134. [cited by applicant]
Tageldin et al., “Developing evasive action-based indicators for identifying pedestrian conflicts in less organized traffic environments,” Journal of Advanced Transportation, Oct. 2016, 50(6): 1193-1208. [cited by applicant]
Talmi et al., “The feedback-related negativity signals salience prediction errors, not reward prediction errors,” Journal of Neuroscience, May 8, 2013, 33(19): 8264-8269. [cited by applicant]
Theeuwes et al., “Self-explaining roads,” Safety Science, Jun. 1, 1995, 19(2-3): 217-225. [cited by applicant]
Theeuwes, “Visual search at intersections: An eye-movement analysis,” Vision in vehicles, 1996, 5: 125-134 (abstract only). [cited by applicant]
Tschantz et al., “Scaling active inference,” CoRR, submitted on Nov. 24, 2019, arXiv:1911.10601v1, 13 pages. [cited by applicant]
Victor et al., “Automation expectation mismatch: Incorrect prediction despite eyes on threat and hands on wheel,” Human factors, Dec. 2018, 60(8):1095-116. [cited by applicant]
Wei et al., “An active inference model of car following: Advantages and applications,” CoRR, submitted on Mar. 27, 2023, arXiv:2303.15201v1, 29 pages. [cited by applicant]
Wei et al., “Modeling driver responses to automation failures with active inference,” IEEE Transactions on Intelligent Transportation Systems, Mar. 11, 2022, 23(10):18064-18075 (abstract only). [cited by applicant]
Wei et al., “World model learning from demonstrations with active inference: application to driving behavior,” In International Workshop on Active Inference, Sep. 19, 2022, p. 130-142. [cited by applicant]
Yu et al., “Uncertainty, neuromodulation, and attention,” Neuron, May 19, 2005, 46(4):681-92. [cited by applicant]
Zheng et al., “Modeling traffic conflicts for use in road safety analysis: A review of analytic methods and future directions,” Analytic methods in accident research, Mar. 1, 2021, 29:100142 (abstract only). [cited by applicant]