Leuze has integrated artificial intelligence (AI) to enhance the performance of optical distance sensors, addressing the challenges faced in industrial environments.
By utilising AI, these sensors achieve heightened precision without the necessity for additional computing resources during active operation. The improvement is achieved through the application of a neural network.
Addressing surface-related challenges
Optical distance sensors employing time-of-flight (TOF) technology are noted for their ability to measure large distances efficiently. They function by timing the journey of emitted light to an object and back, using laser or LED pulses. While TOF sensors perform well, surface characteristics can affect their accuracy, especially when dealing with objects of varying reflectivity.
Dark surfaces can cause weaker signals and delayed echoes, while brighter surfaces enhance signal strength, resulting in premature detection. These discrepancies necessitate error corrections.
The role of polynomial functions
Traditional methods have used polynomial functions to address these errors, deriving correction values
Traditional methods have used polynomial functions to address these errors, deriving correction values from complex algorithms suited for different surfaces and distances.
These functions, while capable of producing stable error curves, struggle with complex surface variations due to their fixed parameters, which limits adaptability to changing conditions.
A shift to neural networks
In contrast, Leuze applies a neural network for calculating correction values. This advanced AI model mimics brain-like operations, consisting of interconnected neurons across multiple layers.
It processes input data through these layers, enabling the network to learn complex relationships beyond traditional calculations. The network's activation functions determine the flow of information between neurons, leading to precise outcomes.
Training through data
AI-driven solution is educated using data that captures how different brightness levels and surface textures
The AI-driven solution is educated using data that captures how different brightness levels and surface textures impact sensor measurements. This helps in refining corrections. During its training, the neural network processes initial distance values and pulse widths to create standardised correction outputs.
It collects extensive data during production from various surfaces and distances, informing the facility's control system which, in turn, adjusts the sensor based on learnt values, avoiding extra computational demands during use.
Achieving precision with five layers
The Leuze neural network employs five fully connected layers, with each neuron linked to every other within its layer, allowing for comprehensive data handling. The ReLU activation function ensures only positive values, facilitating stable learning without computational errors.
Ultimately, the output layer uses the 'tanh' activation function, confining results to a predictable range, guiding sensor adjustments for accurate distance readings.
Applications in industrial settings
AI-enhanced time-of-flight sensors are particularly advantageous in automation settings where accuracy is crucial. They are deployed in:
- Robotics for navigation and collision avoidance
- Materials handling to monitor positions on conveyor systems
- Quality assurance, inspecting workpieces on varied surfaces
- Automated Guided Vehicles (AGVs) for precise distance manoeuvring
- Safety, ensuring proximity detection around machinery
In summary, Leuze's AI integration significantly reduces measurement errors, enhancing sensor performance amidst variable surfaces. The innovative approach fosters robust measurements without requiring additional operational efforts, offering a fitting solution for demanding industrial applications.
Advantages of Leuze's AI solution
- Diminished measurement errors for greater accuracy
- Versatile application across different sensor types and surfaces
- Adaptive learning from real-world data, even with complex surface variations
- No increase in computational load during use
- Future-readiness through modern AI technology
Leuze uses artificial intelligence (AI) to significantly improve the measurement accuracy of optical distance sensors for challenging industrial applications.
This innovation improves measurement accuracy without the need for additional computing resources during operation. The solution is based on a neural network.
Object surfaces as challenges
Optical distance sensors with time-of-flight technology (TOF) offer practical benefits. The sensors enable fast, contactless measurement of large distances, are insensitive to ambient light and provide continuous distance data in real time. The sensor’s operating principle measure distances by recording the time it takes for emitted light to travel to the object and back. Laser or LED pulses are generally used for this purpose.
However, time-of-flight technology also has limitations in measurement accuracy: How precise the results are depends heavily on the nature of the object surface. Dark surfaces can weaken the reflected signal. They generate narrower pulses and the echo is detected later. Bright surfaces, on the other hand, generate stronger signals with a wider pulse width that are detected earlier. That means the returning signal is detected at different times depending on whether the object’s surface is light or dark. This can cause measurement errors that must be compensated for.
Polynomial function: Limited flexibility
Until now, mathematical models based on defined algorithms have been used to correct these errors. A correction value is calculated for many different surfaces and distances, which is later applied automatically. This calculation is based on a so-called polynomial function.
Polynomial functions offer an efficient solution for stable, continuous error curves. One disadvantage, however, is the limited imaging accuracy in the case of complex factors, such as strongly varying surface reflections. As the model parameters are fixed, the functions cannot automatically adapt to changing environmental conditions.
Neural network for correction value calculations
Leuze have a much more precise and flexible solution. Instead of working with rigid formulas, Leuze uses a neural network to determine the correction value. A neural network is a form of artificial intelligence that is modelled on the human brain. It consists of nodes (neurons) in three types of layers: the input layer, hidden layers and the output layer.
The neural network processes information by passing input data step through these one layer at a time. The neurons weigh their results, summarise them and convert them using functions so that a precise result is produced at the end. A so-called activation function decides how strongly a neuron becomes ‘active’, i.e., what value it passes on to the next layer. This activation function enables the network to learn even complex, non-linear relationships and is not limited to simple calculation patterns.
Learning from real data
The AI solution developed by Leuze uses sample data to learn how brightness and surface texture affect the optical distance sensor’s measurements. This makes it much easier to correct the measured values. The neural network is trained with data consisting of raw distance values and pulse widths as input parameters as well as the corresponding standardised correction values at the output.
The training data can be generated from the production process, in which many measured values are collected: for light, dark and differently textured surfaces as well as for different distances. These measured values are communicated to the production facility’s control system. From this, the production facility’s neural network calculates the correction values for the sensor. The sensor then requires no additional computing power during operation – the AI has already ‘learned’ everything.
Five steps for precise values
The Leuze neural network consists of five layers. In each layer, all neurons are fully connected to each other. This means that all information flows into the calculation. A so-called ReLU activation function is used: ReLU stands for ‘Rectified Linear Unit’. This ensures that the network sets negative counters to zero and only processes positive values – similar to a filter that only lets positive signals through, making the learning process stable and reliable.
This has two advantages: Firstly, the network works faster, and secondly, it avoids the computing problems that can occur with other methods. The last layer of the network – the output layer – determines the final correction value. Here, ‘tanh’ (hyperbolic tangent) is used as the activation function. This ensures that the calculated correction value is always within a defined range between -1 and +1. The system then converts this value so that it directly indicates how much the sensor must correct the measured distance in order to deliver precise results.
Calibrated to Leuze sensors
Time-of-flight distance sensors with AI-based correction are particularly useful in industrial automation where precise measurement results are essential.
Typical applications include:
- Navigation and collision avoidance: On robots and mobile platforms
- Materials handling: Checking positions and distances on conveyor belts
- Quality assurance: Checking distances on workpieces with difficult surfaces
- Automated guided vehicle systems (AGVs): Precise distance control when parking and maneuvering
- Safety applications: Detection of proximity to machines and systems
Summary
Leuze is raising the precision of optical distance sensors to a new level with artificial intelligence. Tests have shown that the method's AI-based calibration reduces systematic measurement errors, i.e. the dependence of measurement results on surface and distance, by more than half.
Customers benefit from more robust and accurate measurements without any effort during operation, even with difficult surfaces. This makes it the ideal solution for challenging industrial applications.
Benefits at a glance:
- Fewer measurement errors – delivering significantly more precise results
- Flexible use with different sensor types and surfaces
- Learns better from real data, even with strongly oscillating 3D curve characteristics
- No additional computing load during operation
- Future-proof thanks to modern AI
