Integrating Trustworthy Artificial Intelligence with Energy-Efficient Robotic Arms for Waste Sorting
This paper presents a methodology integrating trustworthy artificial intelligence with an energy-efficient robotic arm for waste sorting. Using a convolutional neural network enhanced by transfer learning with MobileNetV2, the system classifies waste into six categories with a training accuracy of 99.8% and validation accuracy of 80.5%. Additionally, a robotic arm simulation calculates the energy cost for each action using Euclidean distance to achieve optimal, efficient movement.
Summary and content fields are drawn from the document text and are pending editorial review.
Who issued it
Who it governs
Researchers and developers in AI and robotics looking to design energy-efficient and trustworthy smart waste management systems.
What the document contains
The document covers the integration of deep learning classification using MobileNetV2 and energy-aware path planning for simulated robotic waste sorting. It addresses dataset preparation, model evaluation metrics, energy consumption formulas, and trustworthy AI implementations.
It does not provide legal regulatory enforcement mechanisms, governmental policy mandates, or physical hardware deployment details.
- A lightweight CNN based on MobileNetV2 was utilized with transfer learning to classify waste into six categories.
- The waste classification model achieved 99.8% training accuracy and 80.5% validation accuracy.
- A robotic arm simulation was implemented to perform virtual sorting and calculate energy costs using Euclidean distance.
- The framework integrates trustworthy AI principles including transparency, robustness, fairness, and safety.
- Optimized path planning yielded a 25-30% reduction in estimated energy consumption compared to naive linear movements.
· I. Introduction · II. Related Works · III. Methodology · IV. Results and Discussion · V. Trustworthy AI Elements · VI. Hardware Realization Challenges · VII. Conclusion and Future Work · VIII. Environmental and Ethical Considerations
How it scores
Each score is backed by a quote verified against the document text. Editorial review has not yet confirmed them.
Accountability
0/5Clear responsibility for AI outcomes
screening score · 2026-10-23
Fairness
3/5Non-discrimination and equitable treatment
We also make sure the system is fair by using a balanced dataset that includes all six types of waste
V. Trustworthy AI Elements
screening score · 2026-10-23
Human Dignity
0/5Respect for the inherent worth of persons
screening score · 2026-10-23
Privacy
0/5Protection of personal data and private life
screening score · 2026-10-23
Transparency
3/5Openness about how AI systems work and are used
We keep everything clear by sharing details about how the model is built, what settings are used, and how it was trained.
V. Trustworthy AI Elements
screening score · 2026-10-23
Enforcement
0/5Consequences and compliance mechanisms with real force
screening score · 2026-10-23
Impact Assessment
3/5Required assessment of an AI system's risks/impacts before or during use
To further assess model performance, the gap between training and validation accuracies was calculated.
III. Methodology
screening score · 2026-10-23