When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

Abstract

With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making and control for autonomous systems have improved significantly in the past years. When autonomous systems consider the performance of accuracy and transferability, several AI methods, like adversarial learning, reinforcement learning (RL) and meta-learning, show their powerful performance. Here, we review the learning-based approaches in autonomous systems from the perspectives of accuracy and transferability. Accuracy means that a well-trained model shows good results during the testing phase, in which the testing set shares a same task or a data distribution with the training set. Transferability means that when a well-trained model is transferred to other testing domains, the accuracy is still good. Firstly, we introduce some basic concepts of transfer learning and then present some preliminaries of adversarial learning, RL and meta-learning. Secondly, we focus on reviewing the accuracy or transferability or both of them to show the advantages of adversarial learning, like generative adversarial networks (GANs), in typical computer vision tasks in autonomous systems, including image style transfer, image superresolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation, pedestrian detection and person re-identification (re-ID). Then, we further review the performance of RL and meta-learning from the aspects of accuracy or transferability or both of them in autonomous systems, involving pedestrian tracking, robot navigation and robotic manipulation. Finally, we discuss several challenges and future topics for using adversarial learning, RL and meta-learning in autonomous systems.

References in corpus (55)

• Continuous control with deep reinforcement learning
• Conditional Generative Adversarial Nets
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Playing Atari with Deep Reinforcement Learning
• Generative Adversarial Networks: An Overview
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Trust Region Policy Optimization
• Learning Transferable Features with Deep Adaptation Networks
• Generative Adversarial Text to Image Synthesis
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• NIPS 2016 Tutorial: Generative Adversarial Networks
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• Clearing the Skies: A deep network architecture for single-image rain removal
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Deep Reinforcement Learning: An Overview
• Semantic Segmentation using Adversarial Networks
• Learning to reinforcement learn
• A Comprehensive Review of Image Enhancement Techniques
• Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
• Hindsight Experience Replay
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
• One-Shot Visual Imitation Learning via Meta-Learning
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Mode Regularized Generative Adversarial Networks
• Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
• Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
• Meta-Learning: A Survey
• Meta-Reinforcement Learning of Structured Exploration Strategies
• Unsupervised Learning via Meta-Learning
• Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
• Towards Monocular Vision based Obstacle Avoidance through Deep Reinforcement Learning
• Synthesizing Programs for Images using Reinforced Adversarial Learning
• Evolved Policy Gradients
• Adaptive Guidance and Integrated Navigation with Reinforcement Meta-Learning
• Reinforcement and Imitation Learning for Diverse Visuomotor Skills
• InstaGAN: Instance-aware Image-to-Image Translation
• Connecting Generative Adversarial Networks and Actor-Critic Methods
• Demystifying Neural Style Transfer
• Unsupervised Meta-Learning for Reinforcement Learning
• One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
• Unified Single-Image and Video Super-Resolution via Denoising Algorithms
• Autonomous Quadrotor Landing using Deep Reinforcement Learning
• Joint Transmission Map Estimation and Dehazing using Deep Networks
• Unsupervised Curricula for Visual Meta-Reinforcement Learning
• RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion
• Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
• Playing to Learn Better: Repeated Games for Adversarial Learning with Multiple Classifiers