The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning

2024/05/06 by Ransalu Senanayake, Senanayake, Ransalu · 2 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2405.03164

openalex publication_date 2024/05/06 · openalex created_date 2024/05/10 · openalex updated_date 2026/07/28

Abstract

Uncertainty has long been a critical area of study in robotics, particularly when robots are equipped with analytical models. As we move towards the widespread use of deep neural networks in robots, which have demonstrated remarkable performance in research settings, understanding the nuances of uncertainty becomes crucial for their real-world deployment. This guide offers an overview of the importance of uncertainty and provides methods to quantify and evaluate it from an applications perspective.

Cited by

• Joint Flow Trajectory Optimization For Feasible Robot Motion Generation from Video Demonstrations
• Cross-Modal Instructions for Robot Motion Generation

Related

• Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks\n with Sparse Gaussian Processes
• Uncertainty Aware Learning from Demonstrations in Multiple Contexts\n using Bayesian Neural Networks
• f-Cal: Calibrated aleatoric uncertainty estimation from neural\n networks for robot perception
• Towards Identifying and Managing Sources of Uncertainty in AI and Machine Learning Models - An Overview
• A survey of uncertainty in deep neural networks