Explainable Autonomous Robots: A Survey and Perspective
arXiv:2105.02658
Abstract
Advanced communication protocols are critical to enable the coexistence of autonomous robots with humans. Thus, the development of explanatory capabilities is an urgent first step toward autonomous robots. This survey provides an overview of the various types of "explainability" discussed in machine learning research. Then, we discuss the definition of "explainability" in the context of autonomous robots (i.e., explainable autonomous robots) by exploring the question "what is an explanation?" We further conduct a research survey based on this definition and present some relevant topics for future research.
References in corpus (11)
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy
- Recurrent World Models Facilitate Policy Evolution
- State Representation Learning for Control: An Overview
- Symbol Emergence in Robotics: A Survey
- Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations
- Enabling Robots to Communicate their Objectives
- Autonomous Self-Explanation of Behavior for Interactive Reinforcement Learning Agents
- World Model as a Graph: Learning Latent Landmarks for Planning
- The Emerging Landscape of Explainable AI Planning and Decision Making
- Sequential Explanations with Mental Model-Based Policies