Related Experiment Videos
A Sensor-Centric Survey of Autonomous Driving: Integrating Measurement Physics, Uncertainty Modeling, and
Umar Iqbal1, Ali Massoud2,3, Aboelmagd Noureldin2,3
1Department of Electrical Engineering, College of Engineering, Illinois State University, Campus Box 6000, Normal, IL 61790, USA.
Sensors (Basel, Switzerland)
|June 26, 2026
Summary
Autonomous driving systems require integrated safety-critical measurement systems. This survey presents a sensor-centric framework linking measurement physics, uncertainty, fusion, and risk-aware planning for robust autonomous vehicle safety.
Area of Science:
- Robotics and Control Systems
- Sensor Fusion and Perception
- Functional Safety Engineering
Background:
- Autonomous driving systems (ADSs) integrate diverse sensors (cameras, LiDAR, radar, GNSS/IMU) but face challenges like modality-specific failures, calibration drift, and out-of-distribution conditions.
- Current ADAS architectures often treat components as loosely coupled modules, leading to overconfidence and decision errors when sensor certainty is overestimated.
- Existing safety frameworks lack a unified approach to connect sensor measurement physics with robust uncertainty representation and fusion integrity.
Purpose of the Study:
- To introduce a sensor-centric framework that unifies measurement physics, uncertainty quantification, fusion architectures, and safety assurance for ADSs.
- To formalize the physical measurements of each sensor modality and unify probabilistic, evidential, and conformal uncertainty representations.
- To generalize aviation-style integrity concepts (RAIM/ARAIM) to multi-modal autonomous systems and map safety mechanisms to industry standards.
Main Methods:
- Formalizing sensor measurement physics and unifying diverse uncertainty representations (probabilistic, evidential, conformal).
- Analyzing various fusion architectures (filtering, factor-graph, BEV, transformer, state-space) for robustness and graceful degradation.
- Generalizing RAIM/ARAIM integrity concepts for multi-modal sensor fusion and mapping safety mechanisms to ISO 26262, SOTIF, and other standards.
Main Results:
- A coherent sensor-to-assurance framework linking measurement physics to uncertainty, fusion integrity, and safety assurance.
- Evaluation of fusion architectures based on explicit integrity monitoring requirements.
- Mapping of safety mechanisms to concrete architectural solutions and relevant automotive safety standards.
Conclusions:
- A unified sensor-centric framework is crucial for building reliable and safe autonomous driving systems.
- Integrating measurement physics, robust uncertainty representation, and fusion integrity monitoring enhances system safety and addresses limitations of current ADAS.
- The proposed framework provides a throughline from sensor data to deployable safety arguments, aligning with international safety standards.
Related Concept Videos
00:59Uncertainty: Overview
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
01:30Vector Functions and Motion: Problem Solving
Accurate position tracking is fundamental to the safe and effective operation of unmanned aerial vehicles (UAVs), particularly during precision maneuvers near complex structures. In this scenario, a drone is programmed to perform a high-precision inspection of a vertical structure, starting at position ((x, y, z) = (3, 0, 0)), with an initial velocity oriented in the positive z-direction. The trajectory of the drone is governed by a time-dependent acceleration function a(t), which is predefined...
01:24One-Degree-of-Freedom System
In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
03:37Uncertainty in Measurement: Accuracy and Precision
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
01:30Three-Dimensional Force System
In mechanical engineering, a three-dimensional force system is a system of forces acting in three dimensions, with forces applied along the x, y, and z coordinate axes. The three-dimensional force system is an important concept in mechanical engineering, as it allows engineers to understand and analyze the behavior of objects and structures in three dimensions. By understanding the forces acting on a system, engineers can design more efficient and effective mechanical systems that can withstand...
02:46Uncertainty in Measurement: Reading Instruments
Counting is the type of measurement that is free from uncertainty, provided the number of objects being counted does not change during the process. Such measurements result in exact numbers. By counting the eggs in a carton, for instance, one can determine exactly how many eggs are there in the carton. Similarly, the numbers of defined quantities are also exact. For example, 1 foot is exactly 12 inches, 1 inch is exactly 2.54 centimeters, and 1 gram is exactly 0.001 kilograms. Quantities...