Smart Cities Archives - Page 376 of 570 - SmartCitiesElectronics.com

Maxim reduces cost and size for dynamic hand gesture sensing

Wed, Sep 23, 2020

Dynamic gesture sensing for automotive applications can be enabled at what is claimed to be the industry’s lowest cost and smallest size using the MAX25205 data acquisition system says Maxim Integrated Products.

The MAX25205 provides swipe and hand-rotation sensing at 10 times lower cost and up to 75 per cent smaller size than time of flight (ToF) camera-based systems, claims Maxim Integrated.

Featuring integrated optics and a 6 x 10 infrared (IR) sensor array, the MAX25205 detects swipe and hand rotation gestures without the complexity of ToF cameras to improve driver safety. Gesture and proximity sensing is expected to replace knobs and touchscreens for infotainment, phone, side mirror, climate, trunk, sunroof and reading lamp controls in vehicles.

The gesture and proximity sensing sensor is supplied in a 4.0 x 4.0mm chip, which is up to 75 per cent smaller than ToF camera-based solutions, claims Maxim. It is intended for use to complement voice commands, for use when voice command is not effective. It also means that automotive displays do not become smeared with fingerprints as drivers and passengers use the touchscreens.

According to Maxim, the MAX25205 allows developers to avoid complex software development and maintenance programs. The integration of a 60 photo diode array, LED driver and internal LDO result in a form factor that is “significantly smaller” than ToF camera solutions, says the company. It can be paired with a small microcontroller, rather than the larger microprocessors that more complex solutions require.

The versatile device delivers nine gestures, including swipe, rotations, air link and 3×2 proximity zones with low lag time in a single chip. Alternative solutions require three chips and a complicated microprocessor, says Maxim.

The MAX25205 is available at Maxim’s website and the company also offers an evaluation kit, the MAX25205EVKIT#.

Maxim Integrated develops analogue and mixed-signal products and technologies to make systems smaller and smarter, with enhanced security and increased energy efficiency. Its customers are used by customers in the automotive, industrial, healthcare, mobile consumer and cloud data centre markets.

http://www.maximintegrated.com

> Read More

SensiML automates dataset management via Google’s TensorFlow Lite

Tue, Sep 22, 2020

Users of TensorFlow Lite for Microcontrollers can leverage the SensiML Analytics Toolkit which seamlessly integrates with Google’s TensorFlow Lite for Microcontrollers to reduce errors and to build more efficient models even more quickly, says SensiML.

The company, a subsidiary of QuickLogic, develops AI tools for intelligent IoT endpoints. IoT developers working with Google’s TensorFlow Lite for Microcontrollers open source neural network inference engine can leverage SensiML’s powerful automated data labelling and pre-processing capabilities to reduce dataset errors, build more efficient edge models, and do so more quickly, says SensiML.

Following the standardised workflow within the model building pipeline, developers can collect and label data using the SensiML Data Capture Lab, and also create data pre-processing and feature engineering pipelines using the SensiML Analytics Studio. They can additionally perform classification using TensorFlow Lite for Microcontrollers to develop smart sensor algorithms capable of running on low power IoT endpoint devices.

TensorFlow Lite for Microcontrollers is a version of TensorFlow Lite from Google, which has been specifically designed to implement machine learning (ML) models on microcontrollers and other memory-limited devices. According to SensiML, the Analytics Toolkit delivers the easiest and most transparent set of developer tools for the creation and deployment of edge AI sensor algorithms for IoT devices. The tightly coupled integration of SensiML and Google’s TensorFlow enables developers to build intelligent sensor AI algorithms capable of running autonomously on IoT edge devices, adds SensiML.

“Without high-quality datasets, it is difficult to train models that can perform reliably in production. We talk a lot about how critical datasets are to building sensor-based edge AI applications, but currently don’t have a good solution for creating them,” said Pete Warden technical lead of Google’s TensorFlow mobile team. “SensiML’s Data Capture Lab fills this gap in the industry by providing tools to quickly collect and annotate high-quality sensor datasets,” he added.

Referring to the TensorFlow Lite for Microcontrollers framework, Chris Rogers, CEO of SensiML says it is intended for running neural network models on embedded devices. “SensiML’s end-to-end workflow automates the tedious and error-prone data cleansing and labeling process as well as pre-processing and feature extraction providing a powerful new capability for TensorFlow Lite for Microcontrollers users to improve performance and productivity for their edge AI projects,” he said.

The SensiML Analytics Toolkit with support for TensorFlow Lite for Microcontrollers is available now from SensiML.

https://sensiml.com/tensorflow-lite

> Read More

Radar multi-target simulator expands Keysight’s automotive portfolio

Tue, Sep 22, 2020

Automotive engineers can access a radar target simulator and automotive Ethernet channel test software which have been added by Keysight Technologies.

The radar target simulator (RTS) saves engineers time and cost savings during development with a real world test environment in the lab, says Keysight. It performs multi-target, multi-angle testing for radar modules to deliver fast, accurate and reliable results, says the company. Design and verification engineers can quickly validate the performance of radar products, and it can be used by manufacturing and design validation engineers to simulate multiple objects at variable distances.

Automotive industry engineers, designers and manufacturers can develop high-performance products that improve safety and enable advanced driver assistance systems (ADAS), both of which rely on sensitive and accurate automotive radar technology. The RTS can help automotive electronics manufacturers simulate radar targets in realistic scenarios, says Keysight.

Next-generation ADAS systems require camera and radar systems with high resolution, which require increased speed and bandwidth. Automotive Ethernet enables faster data communication to meet the demands of today’s vehicles and the connected vehicles of the future. However, the channel or link in a system can create a point of failure and the new software addresses this challenge. Keysight says its automotive Ethernet channel test software can verify that information is carried, without loss or cross talk, to its intended destination.

The automotive Ethernet channel test software includes a test plan that includes all required tests as per the specification and automatic set up of the network analyser for each measurement and it applies defined test limits. There is also detailed reporting for each test that has been run.

Keysight’s automotive Ethernet suite provides the hardware, software, cables and accessories needed to enable compliance testing. There is a new receiver testing software and an updated transmit compliance application which offers four data rates, including the preliminary version of Multi-Gig IEEE 802.3ch, in one application.

http://www.keysight.com

> Read More

Lattice extends MachXO3 FPGA security for automotive use

Fri, Sep 18, 2020

New versions of Lattice Semiconductor’s MachXO3LF and MachXO3D FPGAs have been announced. The MachXO3LF FPGAs are for automotive control applications and the MachXO3D FPGAs are for system security that support extended temperature operating ranges for automotive and other ruggedised applications.

The MachXO3D FPGAs augment the popular system control capabilities of the Lattice MachXO FPGA architecture, says Lattice Semiconductor. They include hardware Root of Trust (RoT), platform firmware resilience (PFR), and secure dual-boot support. The MachXO3D and MachXO3LF FPGAs target control, bridging, and I/O expansion applications for reliable operation in rugged environments, including advanced driver assistance systems (ADAS), infotainment, motor control, 5G communications infrastructure, industrial robots and automation systems, and defence systems, Lattice advises. They also support for an extended operating range -40 to +125 degrees C (junction temperature). They require a single 3.3V or 1.2V supply.

As more sensors and electric motors are integrated into vehicles, automotive systems will become exposed to the risk of malicious attacks and hacks. To immediately detect vulnerabilities and combat cyber attacks OEMs will demand electronic systems capable of reliable and secure operation in rugged environments, in different weather conditions, vibration and connectivity parameters.

The MachXO3D FPGAs’ security features include on-chip flash memory which secures bitstream and user data against malicious attacks via OTP mode and password protection. There is also an immutable embedded security block to enable security compliant with NIST SP-800-193 Platform Firmware Resilience (PFR) guidelines to protect, detect and recover firmware from unauthorised access. The on-chip flash enables single-chip, instant-on, and dual-boot images for fail-safe programming and in-field updates with flexible system with secure reprogramming to support reliable in-system updates.

“By collaborating with Lattice, the leading provider of low power FPGAs, we are able to provide developers in the automotive market with ready-to-use IPs that simplify their design efforts by accelerating implementation of networking controllers for CAN and LIN,” said Nikos Zervas, CEO of CAST. “With the extended temperature range for automotive and other ruggedised applications, the new MachXO3D automotive family of FPGAs will allow developers to achieve their performance and power consumption goals and get their products to market faster, while enhancing the security of their control systems,” he added.

MachXO3LF and MachXO3D FPGAs are supported by Lattice’s integrated design software suite, Lattice Diamond, a graphic user interface (GUI) -based FPGA design and verification environment with design and implementation tools optimised for low-power Lattice FPGAs. The latest version of Lattice Diamond, version 3.11.3, is now available.

http://www.latticesemi.com

> Read More

Maxim reduces cost and size for dynamic hand gesture sensing

SensiML automates dataset management via Google’s TensorFlow Lite

Radar multi-target simulator expands Keysight’s automotive portfolio

Lattice extends MachXO3 FPGA security for automotive use

About Smart Cities