Encryption Klepsydra

Mission critical software for automotive

Challenges in mission critical software for automotive

The challenges in mission critical software for automotive that the industry will have to overcome in the near future are more than known before we can see them on the road, mainly related with safety issues.
Autonomous vehicles need a set of sensors to “see” the surrounded environment (360º) regardless of external conditions (weather, traffic, pedestrians, etc.) and without human interaction. All these sensors generate a huge amount of data (around 25 Gigabytes per hour) and this data has to be processed in milliseconds. On the other hand, autonomous systems will use machine learning to process the data that comes from their sensors and help them make the decisions about their next actions.

Klepsydra solutions overview

Thus, there are two immediate challenges where Klepsydra can help with their products:

1. Klepsydra SDK is able to collect all the data generated by all sensors and processes it more efficiently with zero data loss and with a reduction in power consumption.

2. Klepsydra AI is an inference engine where AI models can be run increasing the throughput and reducing processor power consumption at the same time.
With the combination of these two products, autonomous vehicles will be able to carry out detection and classification of data coming from sensors more efficiently and quicker than a human driver can.

Klepsydra solution for mission critical software for automotive

Klepsydra products have been created based on real-time and deterministic approaches. They are characterised by the following technical features:

 

Figure 1. Stream-processing style programming

  • Zero data loss. Based on trading software techniques, Klepsydra products have no data loss, which make them safer than market leaders.
  • Boosting data processing. Klepsydra can increase data processing throughput by x2-x8 times.
  • Processor power consumption reduction. A reduction of 30-50% can be reached.
  • Real-time operations. Klepsydra products can process data in real time with low latency. They are substantially more stable, predictable and deterministic than other edge solutions.

Benchmark performances

1. Xilinx/CAN Data Processing Benchmark

Technical Spec:

Benchmark Scenario:

  • Multi-sensor data processing
  • Traditional multi-thread vs Klepsydra’s processing engine

Figure 2. CPU usage

 

 

Figure 3. Data processing rate

 

 

Figure 4. Processing time

2. ROS Data Processing Benchmark

Technical Spec:

  • Processor: VMWare Fusion
  • OS: Ubuntu 18.04 Linux
  • Middleware: ROS Melodic

Benchmark Scenario:

  • Multi-sensor data processing
  • ROS SpinOnce, ROS Async and Klepsydra’s processing engine

 

Figure 5. CPU usage

 

 

Figure 6. Data processing rate

 

 

Figure 7. Processing time

Benchmark Scenario:

  • Multi-sensor data processing
  • Traditional multi-thread vs Klepsydra’s processing engine

Figure 2. CPU usage

 

 

Figure 3. Data processing rate

 

 

Figure 4. Processing time

Request our professional trial

We offer a 90 days trial license including email support. Phone and onsite support and training can be requested.

Please fill the form below and our team will be in contact to provide access to download our products.