Towards Robust One-shot Task Execution using Knowledge Graph Embeddings

Requiring multiple demonstrations of a task plan presents a burden to end-users of robots. However, robustly executing tasks plans from a single end-user demonstration is an ongoing challenge in robotics. We address the problem of one-shot task execution, in which a robot must generalize a single demonstration or prototypical example of a task plan to a new execution environment. Our approach integrates task plans with domain knowledge to infer task plan constituents for new execution environments. Our experimental evaluations show that our knowledge representation makes more relevant generalizations that result in significantly higher success rates over tested baselines. We validated the approach on a physical platform, which resulted in the successful generalization of initial task plans to 38 of 50 execution environments with errors resulting from autonomous robot operation included.

Authors

• Angel Andres Daruna
• Lakshmi Nair 0001
• Weiyu Liu
• Sonia Chernova

Keywords

• Automation
• Conferences
• Knowledge representation
• Task analysis
• Context modeling
• Autonomous robots
• Task Execution
• Knowledge Graph Embedding
• Cognitive Domains
• Ongoing Challenge
• Task Planning
• Execution Environment
• Physical Platform
• Robotics Challenge
• Ablation
• Visuospatial
• Cognitive Learning
• Object Properties
• Semantic Knowledge
• Random Perturbations
• Entity Types
• Dataset Split
• Task Domain
• General Number
• Inverse Reinforcement Learning
• Physical Robot
• Incremental Update
• Queue Size
• Improve Success Rates
• Execution Plan
• Strong Statistical Significance
• Number Of Demonstrations