Browse Topic: Sensors and actuators
Achieving full vehicle autonomy is not just about adding sensors or compute - it requires a fundamental shift in how vehicles are architected. Autonomous systems rely on higher-resolution sensors, massive processing power, and the ability to fuse data from multiple sources in real time. Centralized in-vehicle architectures, which consolidate computing and enable sensor fusion, place unprecedented demands on connectivity. Precise time synchronization across systems becomes critical, as does advanced control to ensure safe and reliable operation. Any delay or data loss can impact decision-making, making robust, resilient communication links essential. High-performance connectivity is the backbone of this evolution. It must deliver the highest bandwidth to handle massive streams of sensor data, support long-reach connections across the vehicle, and maintain error-free performance even in the most challenging electromagnetic environments. This combination of speed, reach, and reliability
Autonomous platforms such as self-driving vehicles, advanced driver-assistance systems (ADAS), and intelligent aerial drones demand real-time video perception systems capable of delivering actionable visual information at ultra-low latency. High-resolution vision pipelines are often hindered by delays introduced at multiple stages—sensor acquisition, video encoding, data transmission, decoding, and display—undermining the responsiveness required for safety-critical decision making. This study introduces a holistic system-level optimization framework that systematically reduces end-to-end video latency while maintaining image fidelity and perception accuracy. The proposed approach integrates hardware-accelerated encoding, zero-copy direct memory access (DMA), lightweight UDP-based RTP transport, and GPU-accelerated decoding into a unified pipeline. By minimizing redundant memory copies and software bottlenecks, the system achieves seamless data flow across hardware and software
Autonomous vehicle navigation requires accurate prediction of driving path curvature to ensure smooth and safe trajectory planning. This paper presents a novel approach to curvature prediction using deep neural networks trained on GPS-derived ground truth data, rather than model predictions, providing a more accurate training signal that reflects actual vehicle motion. We develop a multi-modal neural network architecture with temporal GRU encoders that processes vision features, driver intent signals, historical curvature, and vehicle state parameters to predict curvature. A key innovation is the use of GPS-based actual curvature measurements computed from vehicle motion data (κ = ωz/v) as training supervision, enabling the model to learn from real-world driving patterns. The model is trained on 5,322 samples from real-world driving data collected on The University of Oklahoma’s Norman Campus using a Comma 3X device and a 2025 Nissan Leaf electric vehicle. Experimental results
Monitoring power device temperature in an electric vehicle propulsion drive converter is extremely important to achieve full power delivery within the maximum power capability envelope. Usually, on-die temperature sensors are installed on Si-IGBT power devices in electric vehicle propulsion drive converters to enable monitoring device temperature and achieve over-temperature protection. Currently, SiC MOSFET is a promising power device in power converters of electric drives because of its lower loss, higher switching speed, higher voltage capability, and higher junction temperature limit in comparison with the widely used Si-IGBT. However, SiC MOSFET is a more expensive device, installation of an on-die temperature sensor on SiC MOSFET will significantly increase its cost and complexity. So presently, there is no junction temperature sensor installed in SiC MOSFET due to which there is great difficulty protecting SiC MOSFET from over temperature. When a junction temperature estimation
The reliability of Drive Unit (DU) oil pumps is critical to the performance and safety of electric vehicles, as these pumps provide essential lubrication and thermal management. In modern EV architectures, real-time health monitoring of these pumps typically relies on indirect signals than dedicated sensing hardware, a design choice optimized for cost, weight, and system complexity. This makes early fault detection a non-trivial challenge. To address this limitation, we present a novel, data-driven anomaly detection framework that leverages large-scale customer fleet telemetry and advanced machine learning to identify incipient pump degradation that traditional diagnostic methods often fail to capture. Specifically, we develop an XGBoost regression model trained on time-series features—including commanded pump speed, oil temperature, and historical pump current—to predict expected current behavior under nominal conditions. Deviations are quantified using the Mean Absolute Percentage
The roles of aerospace and defense engineers have profoundly changed. Systems integrators and acquisition programs require “standardized openness” while also wishing for boxes that take up less space, weight, and power. Despite the push towards Modular Open Systems Approach (MOSA), Sensor Open Systems Architecture (SOSA), and similar open standards, there are still opportunities to use non-standardized, small form factor (SFF) designs. As outlined in the project examples below, a purpose-built SFF module can address technical system requirements better than any current approach focused on open standards.
A new Microelectromechanical system (MEMS) grating modulator has been developed, offering significant advancements in optical efficiency and scalability for communication systems. By integrating a tunable sinusoidal grating with broadside-constrained continuous ribbons, a large-scale aperture of 30 × 30 mm is achieved and supports high-speed modulation up to 250 kHz.
Multimodal sensors, capable of simultaneously acquiring multiple physical or chemical signals, have shown broad application potential in fields such as health monitoring, soft robotics, and energy systems. However, current multimodal sensors often suffer from complex fabrication processes and signal decoupling challenges, which limit their practical deployment. To address these issues, this work presents a thin-film temperature–strain multimodal sensor (FTSMS) fabricated via laser processing. The temperature-sensing unit, based on the Seebeck effect, achieves a sensitivity of 9.08 μV/°C, while the strain-sensing unit, utilizing BaTiO₃/AlN@PDMS as the sensitive layer, exhibits a gauge factor (GF) of 43.2. By integrating distinct sensing mechanisms (thermovoltage for temperature and capacitance change for strain), the FTSMS enables self-decoupled measurements over 20–90 °C. Applied in LIB monitoring, it successfully captures real-time temperature and strain variations during charge
This paper presents a novel AI-based parking management system designed to enhance efficiency, reduce manual intervention, and optimize operational costs in modern parking facilities. By integrating computer vision with infrared (IR) sensors, the system continuously monitors parking areas in real time, accurately detecting vehicle occupancy and dynamically updating the space availability. The hybrid approach minimizes reliance on conventional sensors, improving accuracy and environmental robustness. Additional features include intelligent navigation assistance guiding drivers to available spots and integrated video surveillance for enhanced security through AI-driven suspicious activity detection. The user interface provides real-time updates ensuring a seamless and convenient parking experience. Overall, this system offers a comprehensive solution that advances parking technology through automation, real-time monitoring, and secure, user-friendly operation.
A new study from NC State University combines three-dimensional embroidery techniques with machine learning to create a fabric-based sensor that can control electronic devices through touch.
Accidents during lane changes are increasingly becoming a problem due to various human based and environment-based factors. Reckless driving, fatigue, bad weather are just some of these factors. This research introduces an innovative algorithm for estimating crash risk during lane changes, including the Extended Lane Change Risk Index (ELCRI). Unlike existing studies and algorithms that mainly address rear-end collisions, this algorithm incorporates exposure time risk and anticipated crash severity risk using fault tree analysis (FTA). The risks are merged to find the ELCRI and used in real time applications for lane change assist to predict if lane change is safe or not. The algorithm defines zones of interest within the current and target lanes, monitored by sensors attached to the vehicle. These sensors dynamically detect relevant objects based on their trajectories, continuously and dynamically calculating the ELCRI to assess collision risk during lane changes. Additionally
Side crashes are generally hazardous because there is no room for large deformation to protect an occupant from the crash forces. A crucial point in side impacts is the rapid intrusion of the side structure into the passenger compartment which need sufficient space between occupants and door trim to enable a proper unfolding of the side airbag. This problem can be alleviated by using the rising air pressure inside the door as an additional input for crash sensing. With improvements in the crash sensor technology, pressure sensors that detect pressure changes in door cavities have been developed recently for vehicle crash safety applications. The crash pulses recorded by the acceleration based crash sensors usually exhibit high frequency and noisy responses. The data obtained from the pressure sensors exhibit lower frequency and less noisy responses. Due to its ability to discriminate crash severities and allow the restraint devices to deploy earlier, the pressure sensor technology has
Items per page:
50
1 – 50 of 8102