Lernkarten
Robot Safety Standards.
There are 3 Standards. Name them
A-Level: Functional Safety (IEC 61508) / Assesement (ISO 12100 - Risk)
B-Level: EN ISO / IEC
C-Level: Integrated manufacturing systems / Robot System, cell / Robot
EU Definition of Artificial Intelligence
sense - think (plan) - act
Machine Learning
- (Deep Learning, Reinforced Learning)
- Reasoning - information processiong (Search, Planning, Knowledge) - Decision making
Research fields of diferent at Pichelrs institute:
- Object Detection
- Sematic Scene Segmentation
- Human Pose Detection
- Deep Reinforcement Learning
- Object Detection (3D needed for Robotics, Video mit Hund und Rad)
- Sematic Scene Segmentation (autonomous driving, what is the scene about? Meaning)
- Human Pose Detection (Video mit Sportlern, Tänzern) Auch hier 2D schon relativ gut, 3D noch nicht
- Deep Reinforcement Learning (Robots learning to move)
- Online Training (Robot learns objects, Robot dealing with unknown situations or objects)
- Learning Robot Grasping Policies (Greifarme, Objekte greifen)
- Imitation learning (Video mit Glas füllen)
- Deep Reinforcement learning (sorting out a bin, make space to grab and place things)
What is trust?
What is a trustfull person?
Cambridge Dictionary:
Trust is to believe that someone is good and honest and will not harm you, or that something is safe and reliable
Trustful person:
- Consistency and reliabilty (meet the expectations, avoid surprises and risks
- Adequacy and adaptability
- execution (always competent and professional)
- Honesty and openness (communicate inform and explain; point to room for imporovement)
Trustworthy Robots: Safety, Creditibility and Explainability
EU guidelines for Turstworthy AI published april 8, 2019: What does this document?
- it talks about requirements of trustworthy Ai
- Technical methods when realising explainable AI
- Also if you have a system how to assess that it is trustworthy
Framework for Trustworthy AI
Introduction (3)
Chapter 1 (2)
Chapter 2
Chapter 3
Introduction: Lawfull Ai, Ethical Ai, Robust AI
Chapter 1: Foundations of Trustworthy AI -> 4 Ethical Principles (Respect for human autonomy, Prevention of harm, frames, Explicability)
Chapter 2: Realisation or Trustworthy AI -> 7 key Requierements (Technical, non technical methods)
1. Human agency and oversight
2. Technical robustness and safety
3. Privacy and data governance
4. Transparancy
5. Diversity, non-discrimination and fairness
6. Societal and environmental wellbeing
7. accountability
Chapter 3: Assesment of Trustworthy AI -> Trustworthy AI Assesement List
7 key requierements of trustworthy Ai
Again: 7 Keyrequirements of Trustworthy AI:
- Human agency and oversight
- Technical Robustness and safety
- Privacy and Data governance
- Transparency
- Diversity, non-discrimination and fairness
- Societal and environmental wellbeing
- Accountability (Auditability and accounting)
Technical Methods for Trustworthy AI (5)
- Archticures for Trustworthy Ai
- Ethics and rule of law by design
- Explanation methods (X to AI)
- Testing and validating
- Quality of Service Indicators
