DE-102025145394-A1 - SYSTEM AND METHOD OF CAUSAL COMPOSITION DIFFUSION FOR TRAFFIC GENERATION IN A CLOSED REGULATOR

Abstract

A procedure comprises: receiving initial conditions for a traffic scenario encompassing a multitude of interacting agents, where the initial conditions define the states of the multitude of agents; identifying a causal structure among the multitude of agents based on their states; and ranking the multitude of agents based on the identified causal structure to determine a subset of key agents that have the greatest influence with respect to a controllability goal. For each agent in the multitude, the procedure comprises: generating a future trajectory using a reverse-sampling procedure of a diffusion model; and performing the reverse-sampling procedure by selectively applying a gradient of the controllability goal only to the identified subset of key agents.

Inventors

• Haohong Lin
• Hongge Chen
• Eric Wolff

Assignees

• GM CRUISE HOLDINGS LLC

Dates

Publication Date

20260513

Application Date

20251105

Priority Date

20250916

Claims (10)

1. A computer-implemented procedure that, when executed on data processing hardware, causes the data processing hardware to perform operations, comprising: Receiving initial conditions for a traffic scenario comprising a plurality of interacting agents, where the initial conditions define the states of the plurality of agents; Identifying a causal structure among the plurality of agents based on the states of the plurality of agents, where the causal structure defines causal influences between agents of the plurality of agents; Ranking the plurality of agents based on the identified causal structure to determine a subset of key agents that have the greatest influence with respect to a controllability goal; For each agent of a plurality of agents: Generating a future trajectory using a reverse-sampling procedure of a diffusion model; and conducting the reverse sampling procedure by selectively applying a gradient of the controllability target only to the identified subset of key agents, while conducting for the remaining agents of the multitude of agents is determined based on the identified causal structure, thereby generating a final traffic scenario that satisfies the controllability target while remaining realistic.
2. Procedure according to Claim 1 , where identifying the causal structure includes: creating a decision causal graph (DCG), where the nodes of the DCG represent the agents and the lines represent the causal dependencies for future actions.
3. Procedure according to Claim 2 , wherein the DCG is generated using a scene encoder with a factorized attention mechanism, and wherein causal links are identified between the multitude of agents based on attention weights and/or kinematic factors
4. Procedure according to Claim 3 , where the kinematic factors include a value for the time to collision (TTC) between pairs of agents from the plurality of agents.
5. Procedure according to Claim 1 , where classifying the multitude of agents includes: performing a graph-based analysis of the identified causal structure to determine the degree of interactivity for each agent of the multitude of agents.
6. Procedure according to Claim 1 , wherein conducting the reverse sampling procedure further comprises: applying a classifier-free guiding component, wherein the classifier-free guiding component comprises: a weighted combination of an unconditional distribution based on an agent's own history and an intervened distribution based on the agent's causal parents, as defined by the causal structure.
7. Procedure according to Claim 1 , where the controllability objective is linked to the generation of a safety-critical event.
8. Procedure according to Claim 7 , where the safety-critical event includes: a collision between at least two agents, an off-road condition for at least one agent, or a near-collision.
9. Procedure according to Claim 1 , where the procedure is formulated as a constrained optimization problem within the framework of a constrained factorized Markov decision process (CFMDP), where the controllability goal is maximized under the condition of realism.
10. Procedure according to Claim 1 , where the diffusion model is a probabilistic denoising diffusion model (DDPM) and the reverse sampling procedure iteratively denoises a noise vector to generate each of the future trajectories.

Description

CROSS-REFERENCE TO RELATED REGISTRATION This application claims priority pursuant to 35 USC §119(e) over the US provisional application filed on November 13, 2024, with serial number 63/720,114 The disclosure of this earlier application shall form part of the disclosure of this application and is hereby incorporated in its entirety by reference. INTRODUCTION The information in this section serves to present the general context of the disclosure. Works of the inventors mentioned herein, insofar as they are described in this section, as well as aspects of the description that may not have been prior art at the time of filing, are neither expressly nor implicitly admitted as prior art against the present disclosure. This disclosure relates generally to computer-implemented simulations and, in particular, to systems and methods for generating realistic and controllable traffic scenarios for testing and validating autonomous vehicles (AVs). The development and validation of safe and reliable AVs depends heavily on rigorous testing in a wide variety of driving scenarios. While real-world testing is essential, relying on it to cover the large number of potential interactions, especially rare but safety-critical long-tail events, is impractical and often dangerous. Consequently, realistic simulation has become an indispensable tool for evaluating AV performance. An effective traffic simulator must generate scenarios that are both realistic and controllable. Realism ensures that the simulated behaviors of actors or agents (e.g., other cars, pedestrians) in the environment accurately reflect the complex, nuanced, and often unpredictable nature of interactions in the real world. Controllability allows developers and testers to deliberately create and analyze challenging situations, such as forcing a near miss or collision, to systematically explore the limits of an AV's capabilities. However, existing approaches to traffic simulation struggle to strike an appropriate balance between these two often competing objectives. Data-driven methods that learn from large datasets of real-world driving behavior can produce realistic general behaviors but are often unable to generate new, safety-critical scenarios that are rare in the training data. Furthermore, if these models are used in a closed control loop where the simulation evolves over time, they can suffer from cumulative errors that cause the simulation to drift into unrealistic states. Conversely, while rule-based approaches offer precise control, they often result in behaviors that feel scripted, rigid, and unrealistic because they fail to capture the adaptive decision-making of human drivers. Newer deep generative models, including diffusion models, have shown promise but still face a fundamental challenge: a conflict between the goals of realism and controllability. To steer a simulation toward a specific, user-defined outcome (e.g., a collision), it is often necessary to generate agent behaviors that are improbable and deviate significantly from realistic, data-learned patterns. This “gradient conflict” means that increasing controllability often comes directly at the expense of realism, and vice versa. Therefore, there is a need for a traffic scenario generation system that resolves this conflict and enables the creation of scenarios that are both highly realistic and precisely controllable, particularly for generating safety-critical events. SUMMARY One aspect of the disclosure provides a computer-implemented random composition diffusion method for closed-loop traffic generation, which, when executed on data processing hardware, causes the data processing hardware to perform operations that These operations include: receiving initial conditions for a traffic scenario encompassing a multitude of interacting agents, where the initial conditions define the states of the multitude of agents; and identifying a causal structure among the multitude of agents based on their states, where the causal structure defines causal influences between agents within the multitude. The operations also include: ranking the multitude of agents based on the identified causal structure to determine a subset of key agents that have the greatest influence with respect to a controllability goal. For each agent of the multitude of agents, the operations further include: generating a future trajectory using a reverse-sampling procedure of a diffusion model, and conducting the reverse-sampling procedure by selectively applying a gradient of the controllability target only to the identified subset of key agents, while the conduct for the remaining agents of the multitude of agents is determined based on the identified causal structure, thereby generating a final traffic scenario that satisfies the controllability target while remaining realistic. Implementations of the revelation may include one or more of the following optional features. In some implementations, identifying the causal struct