On Machine Learning and Structure for Mobile Robots

2018/06/15 by Markus Wulfmeier, Wulfmeier, Markus
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Robotic Path Planning Algorithms #Robotics (cs.RO) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.1806.06003

openalex publication_date 2018/06/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Distilling the Knowledge in a Neural Network
• Long Short-Term Memory
• A Practical Bayesian Framework for Backpropagation Networks
• Vision meets robotics: The KITTI dataset
• ImageNet Large Scale Visual Recognition Challenge
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual\n Recognition
• Social force model for pedestrian dynamics
• Metric Learning with Adaptive Density Discrimination
• End to End Learning for Self-Driving Cars
• Categorical Reparameterization with Gumbel-Softmax
• Learning to reinforcement learn
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• REBAR: Low-variance, unbiased gradient estimates for discrete latent\n variable models
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Mutual Alignment Transfer Learning
• Toward Geometric Deep SLAM
• SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning\n and Control
• Born Again Neural Networks
• Unsupervised CNN for Single View Depth Estimation: Geometry to the\n Rescue
• Addressing Appearance Change in Outdoor Robotics with Adversarial Domain\n Adaptation
• Weight Uncertainty in Neural Networks
• Xception: Deep Learning with Depthwise Separable Convolutions
• CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction
• Universal adversarial perturbations
• Accurate Single Stage Detector Using Recurrent Rolling Convolution
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Related

• Continual Learning of Visual Concepts for Robots through Limited\n Supervision
• A Survey of Deep Learning Techniques for Mobile Robot Applications
• From Machine Learning to Robotics: Challenges and Opportunities for\n Embodied Intelligence
• Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey
• Learning Mobile Manipulation