Once reserved solely for humans, now using deep learning, sensors can perform intelligent actions in the automated detection, testing, and classification of objects or features. Deep learning, a sub-area of machine learning, ranks among the most significant of future technologies in the field of artificial intelligence, and is a long-term driver of Industry 4.0.
SICK will be showcasing its newest deep learning and sensing capabilities in Booth #144 at the Robotics Summit & Expo from June 5-6 in Boston. The Robotics Summit & Expo will feature 70-plus exhibitors, 60-plus speakers, AWS RoboMaker Immersion Day, the Future of Mechatronics and Robotics Engineering Workshop, the MassRobotics Engineering Career Fair networking receptions and more fun surprises. Full conference passes are $595, while expo-only passes are just $50. Academic discounts are available, and academic full conference rates are $295. Register today.
After SICK reported the successful application of deep learning algorithms in the first pilot programs in January, the company is now announcing a new software application for system business in factory and logistics automation applications. In a logistics application, the deep learning system detects whether a sorting tray in a logistics hub is actually loaded with only one object. This makes the stream of goods more efficient. The same principle can be applied to a factory automation setting to ensure the steady stream of goods.
Training the sensor with neural networks
Neural networks are used to make deep learning a reality. Compared to the classic process for developing algorithms, which is mainly characterized by manual development of a suitable feature representation, a neuronal network is trained to optimal features for its task and can be retrained again and again with suitable data in order to adapt to new circumstances.
SICK uses a powerful, independent in-house computer and IT base as the executing unit. It collects and assesses thousands of images and examples for the training data set and neuronal networks.
The extensive computation of the complex operations of the deep learning solution for training is done on computers with high GPU performance specially equipped for this purpose. The new deep learning algorithms generated in this way are provided locally on the sensor, making them fail-safe and directly available, for example, on an intelligent camera.
Development of deep learning sensor portfolio
With the implementation of deep learning in selected sensors and sensor systems, SICK is implementing the next level in AppSpace after the SICK AppSpace ecosystem–a new sensor software concept which creates adaptable and future-proof solutions for automation applications.
Other image-processing sensors and cameras are also included in the coming products, which work with the new technology with customer-specific adaptation that generate real added value for the user.
The concept of the sensor specialized with artificial intelligence can be used principally on simple sensors, such as inductive proximity sensors, photoelectric retro-reflective sensors, ultrasonic sensors, and others. In addition, system solutions such as increasingly challenging vehicle classification at toll stations offer potential for a deep learning-supported classification of vehicles into toll classes.
outdoorScan3 laser scanner for AGVs
SICK will also be showing its new outdoorScan3 safety laser scanner, which it claims is the first safety laser scanner certified to IEC 62998 for use in outdoor applications.
The outdoorScan3 allows automated guided vehicles (AGVs) to navigate safely through outdoor industrial environments. SICK says the outdoorScan3 works safely and reliably in all weather conditions. The outdoorScan3 can work without errors, SICK says, when exposed to sunlight with an illumination intensity of up to 40,000 lux. SICK says the outdoorScan3 uses softwares to filter out these environmental influences. For example, rain up to a precipitation intensity of 10 mm/h can be filtered out. Even in fog with a meteorological visual range of up to 50 m, the outdoorScan3 detects all obstacles.
TDC-E Telematic Data Collector
SICK will also be showing the TDC-E Telematic Data Collector, the newest addition to SICK’s portfolio of gateway systems. The TDC gateway systems are used to collect, analyze, store, and transmit sensor data in mobile and stationary applications.
This new solution offers extended functionalities for capturing, processing, and transmitting process and sensor data. As a high-performance communication platform with an open end-to-end IoT architecture, the TDC-E now offers numerous analog and digital connectivity options for connecting autonomous sensors and sensor systems.
The mobile communication options have been extended with WLAN and WPAN, allowing for additional functionalities such as the indoor localization of mobile machines. The data collected, analyzed, and individually visualized by the TDC-E means that the operational status of the networked sensors, as well as the processes in which they are used, are completely transparent.
Optionally, SICK also offers customer-specific cloud solutions for further processing at a higher level. These solutions support the TDC-E with the MQTT, OPC UA, and JSON protocols via suitable interfaces such as GSM 3G+, WLAN, and Ethernet.
Navigating mobile robotics with 2D safety LIDAR
Joe Gelzhiser, SICK’s Supervisor of Safety Application Specialists, will also be delivering a talk on Thursday, June 6 from 2-2:45 PM called “Navigating Mobile Robotics with 2D Safety LIDAR – Proper Application for the Safe Detection of Persons.” In this talk Gelzhiser will cover the proper application of 2D safety LIDAR for both navigation and the safe detection of persons, according to current North American and International consensus safety standards. He will also share application examples and case studies and detail how to use an iterative Risk Assessment process for the correct application of 2D LIDAR technology for both safety and navigation in indoor and outdoor environments.
Gelzhiser is a Certified FS Engineer with over 15 years of experience in the area of machine safety. He began his career with Northrop Grumman, where he worked on biohazard detection systems used to protect the public from biohazards being delivered through the United States Postal Service.