Fraunhofer Institute for Cognitive Systems IKSDependable person detection: approaches for safe human-machine collaboration
Contemporary manufacturing facilities aim to enhance flexibility and efficiency while ensuring the safety of workers. The inclusion of autonomous machines can boost productivity even further, but it is vital to demonstrate their safe operation alongside human personnel.
Conventional safety measures often restrict the operational capabilities of autonomous machines too much. To address this, perception systems that integrate Artificial Intelligence (AI) have emerged as a promising solution, but AI currently faces its own technical and legislative challenges regarding safety. Recently the automotive industry has pioneered efforts to develop AI specific standards, e.g. ISO/PAS 8800, which includes a detailed ML Safety Lifecycle emphasizing an iterative AI development process.
This paper outlines the activities involved in developing a dependable person detection system within an industrial context. It highlights the individual steps of the ML Safety Lifecycle’s iterative approach to safety assurance.
The ML Safety Lifecycle of Fraunhofer IKS
- Defining safety requirements
- Data specification and collection
- Algorithm selection
- Performance evaluation
- Mitigation strategies
What to expect in this white paper:
- Overview of each phase in the ML Safety Lifecycle, including lessons learned
- Relevant norms and standards for safety requirement elicitation and data collection
- General considerations and procedures for algorithm selection, performance evaluation and mitigation strategies
- Practical examples from real-world experience
- Recommendations for safe person detection using AI in industrial environments
