AED: Adaptable Error Detection for Few-shot Imitation Policy Jia-Fong Y eh 1 Kuo-Han Hung 1, Pang-Chi Lo1, Chi-Ming Chung 1
–Neural Information Processing Systems
We introduce a new task called Adaptable Error Detection (AED), which aims to identify behavior errors in few-shot imitation (FSI) policies based on visual observations in novel environments. The potential to cause serious damage to surrounding areas limits the application of FSI policies in real-world scenarios.
Neural Information Processing Systems
Feb-18-2026, 18:03:13 GMT
- Country:
- Asia
- Middle East > Jordan (0.04)
- Taiwan (0.04)
- North America
- Canada > Ontario
- Toronto (0.04)
- United States > California
- Alameda County > Berkeley (0.04)
- Canada > Ontario
- Asia
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Information Technology (0.46)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning
- Neural Networks (1.00)
- Performance Analysis > Accuracy (1.00)
- Natural Language (0.93)
- Robots (1.00)
- Vision (0.93)
- Machine Learning
- Data Science > Data Mining (0.95)
- Artificial Intelligence
- Information Technology