Related Experiment Videos
Enhancing semantic and risk controllability in safety-critical scenario generation: An LLM-guided conditional
Hanchu Zhou1, Yaqi Li1, Chengcheng Wang2
1School of Traffic and Transportation Engineering, Central South University, Changsha, China.
Accident; Analysis and Prevention
|July 11, 2026
Summary
This study introduces a Large Language Model (LLM)-guided framework for generating realistic and controllable safety-critical scenarios for autonomous vehicle testing. The method balances scenario criticality, realism, and controllability effectively.
Area of Science:
- Artificial Intelligence
- Robotics
- Computer Science
Background:
- Autonomous vehicle validation requires robust safety-critical scenario generation.
- Existing methods face challenges in achieving semantic control, risk-level control, and trajectory realism simultaneously.
Purpose of the Study:
- To propose a novel framework for controllable safety-critical scenario generation for autonomous vehicles.
- To address limitations in current methods regarding semantic controllability, risk-level controllability, and trajectory realism.
Main Methods:
- Utilized a Large Language Model (LLM) to translate natural language into structured generation conditions.
- Employed a conditional latent diffusion model guided by LLM-derived conditions for scenario generation.
- Incorporated semantic and risk features for controllable generation and filtered scenarios for semantic consistency.
Main Results:
- The proposed LLM-guided diffusion framework successfully generates realistic and risk-controllable safety-critical scenarios.
- Achieved a superior balance among criticality, realism, and controllability compared to baseline methods.
- LLM-based semantic conditioning enhanced accuracy in both scenario type and risk level.
Conclusions:
- The developed method offers a flexible and controllable approach for generating safety-critical scenarios.
- Provides a valuable tool for autonomous vehicle testing and safety evaluation.
- Demonstrates the efficacy of LLM integration in enhancing controllable scenario generation.
Related Concept Videos
01:10Propagation of Uncertainty from Systematic Error
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this particular...
00:59Propagation of Uncertainty from Random Error
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
01:26Constraints and Statical Determinacy
In structural engineering, the equilibrium of a system is not only determined by its equations of equilibrium but also with the help of constraints. Constraints refer to restrictions on the motion of a system. The proper combinations of constraints can minimize the total number of constraints needed to maintain a system in mechanical equilibrium. When this happens, the system is said to be statically determinate. For such systems, the unknown reaction supports can be estimated using equilibrium...
01:30Hazard Analysis and Critical Control Points (HACCP)
Hazard Analysis and Critical Control Points (HACCP) is a science-based, preventive system used globally to ensure food safety by identifying, evaluating, and controlling biological, chemical, and physical hazards throughout food production. Originally developed by NASA and the Pillsbury Company for astronaut food, HACCP is now a core component of the Codex Alimentarius.HACCP operates on prerequisite programs—such as Good Manufacturing Practices (GMPs), sanitation procedures, and supplier...
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...