On Machine Learning and Structure for Mobile Robots
arXiv:1806.06003
Abstract
Due to recent advances - compute, data, models - the role of learning in autonomous systems has expanded significantly, rendering new applications possible for the first time. While some of the most significant benefits are obtained in the perception modules of the software stack, other aspects continue to rely on known manual procedures based on prior knowledge on geometry, dynamics, kinematics etc. Nonetheless, learning gains relevance in these modules when data collection and curation become easier than manual rule design. Building on this coarse and broad survey of current research, the final sections aim to provide insights into future potentials and challenges as well as the necessity of structure in current practical applications.
arXiv commentInformal Review
References in corpus (32)
- Distilling the Knowledge in a Neural Network
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Social Force Model for Pedestrian Dynamics
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Categorical Reparameterization with Gumbel-Softmax
- End to End Learning for Self-Driving Cars
- Weight Uncertainty in Neural Networks
- DeepXplore: Automated Whitebox Testing of Deep Learning Systems
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Born Again Neural Networks
- Learning to reinforcement learn
- Xception: Deep Learning with Depthwise Separable Convolutions
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
- Domain Adaptation for Visual Applications: A Comprehensive Survey
- CARLA: An Open Urban Driving Simulator
- Unsupervised Visual Representation Learning by Context Prediction
- Unsupervised Learning for Physical Interaction through Video Prediction
- REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
- Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robots
- Universal adversarial perturbations
- DART: Noise Injection for Robust Imitation Learning
- Generic 3D Representation via Pose Estimation and Matching
- CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction
- Metric Learning with Adaptive Density Discrimination
- Accurate Single Stage Detector Using Recurrent Rolling Convolution
- Toward Geometric Deep SLAM
- SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control
- Mutual Alignment Transfer Learning
- Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation