Teaching a Machine to Read Maps with Deep Reinforcement Learning

Slides:



Advertisements
Similar presentations
A machine learning perspective on neural networks and learning tools
Advertisements

Introduction to Probabilistic Robot Mapping. What is Robot Mapping? General Definitions for robot mapping.
Chapter 10 Artificial Intelligence © 2007 Pearson Addison-Wesley. All rights reserved.
Project Proposal Coffee delivery mission Oct, 3, 2007 NSH 3211 Hyun Soo Park, Iacopo Gentilini Robotic Motion Planning Potential Field Techniques.
Honte, a Go-Playing Program Using Neural Nets Frederik Dahl.
Robot Learning Jeremy Wyatt School of Computer Science University of Birmingham.
Ratbert: Nearest Sequence Memory Based Prediction Model Applied to Robot Navigation by Sergey Alexandrov iCML 2003.
Exploration in Reinforcement Learning Jeremy Wyatt Intelligent Robotics Lab School of Computer Science University of Birmingham, UK
CS B 659: I NTELLIGENT R OBOTICS Planning Under Uncertainty.
CS Reinforcement Learning1 Reinforcement Learning Variation on Supervised Learning Exact target outputs are not given Some variation of reward is.
ROBOT LOCALISATION & MAPPING: NAVIGATION Ken Birbeck.
Learning BlackJack with ANN (Aritificial Neural Network) Ip Kei Sam ID:
Study on Genetic Network Programming (GNP) with Learning and Evolution Hirasawa laboratory, Artificial Intelligence section Information architecture field.
I'm thinking of a number. 12 is a factor of my number. What other factors MUST my number have?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 11: Artificial Intelligence Computer Science: An Overview Tenth Edition.
Curiosity-Driven Exploration with Planning Trajectories Tyler Streeter PhD Student, Human Computer Interaction Iowa State University
Learning to Navigate Through Crowded Environments Peter Henry 1, Christian Vollmer 2, Brian Ferris 1, Dieter Fox 1 Tuesday, May 4, University of.
Mutation Operator Evolution for EA-Based Neural Networks By Ryan Meuth.
Design and Implementation of General Purpose Reinforcement Learning Agents Tyler Streeter November 17, 2005.
Towards the autonomous navigation of intelligent robots for risky interventions Janusz Bedkowski, Grzegorz Kowalski, Zbigniew Borkowicz, Andrzej Masłowski.
AI: AlphaGo European champion : Fan Hui A feat previously thought to be at least a decade away!!!
CS 5751 Machine Learning Chapter 13 Reinforcement Learning1 Reinforcement Learning Control learning Control polices that choose optimal actions Q learning.
Deep Reinforcement Learning
Ikarus: Large-scale Participatory Sensing at High Altitudes
Reinforcement Learning
COGNITIVE APPROACH TO ROBOT SPATIAL MAPPING
Convolutional Neural Network
Reinforcement Learning
Reinforcement Learning
Chapter 11: Artificial Intelligence
Deep Reinforcement Learning
2009: Topics Covered in COSC 6368
CSE 190 Neural Networks: How to train a network to look and see
Department of Cybernetics
CS b659: Intelligent Robotics
Reinforcement Learning
A Crash Course in Reinforcement Learning
State Machines Chapter 5.
Pursuit-Evasion Games with UGVs and UAVs
JamBot: Music Theory Aware Chord Based Generation of Polyphonic Music with LSTMs Gino Brunner, Yuyi Wang, Roger Wattenhofer, Jonas Wiesendanger Distributed.
Real-time Wall Outline Extraction for Redirected Walking
CH. 1: Introduction 1.1 What is Machine Learning Example:
Reinforcement Learning
AV Autonomous Vehicles.
Reinforcement Learning
Reinforcement learning with unsupervised auxiliary tasks
Hybrid computing using a neural network with dynamic external memory
"Playing Atari with deep reinforcement learning."
FUNDAMENTALS OF MACHINE LEARNING AND DEEP LEARNING
Deep Reinforcement Learning in Navigation
Joelle Pineau: General info
Power and limits of reactive intelligence
Continous-Action Q-Learning
Sensorimotor Learning and the Development of Position Invariance
Reinforcement Learning
CHAPTER 14 ROBOTICS.
Chapter 1: Introduction
Deep Neural Networks: A Hands on Challenge Deep Neural Networks: A Hands on Challenge Deep Neural Networks: A Hands on Challenge Deep Neural Networks:
Designing Neural Network Architectures Using Reinforcement Learning
Learning Control for Dynamically Stable Legged Robots
Visual Navigation Yukun Cui.
Chapter 10: The cognitive brain
2004: Topics Covered in COSC 6368
Deep Learning Authors: Yann LeCun, Yoshua Bengio, Geoffrey Hinton
Unsupervised Perceptual Rewards For Imitation Learning
Recurrent Neural Networks (RNNs)
Lecture 09: Introduction Image Recognition using Neural Networks
Machine Learning.
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 7
Morteza Kheirkhah University College London
Presentation transcript:

Teaching a Machine to Read Maps with Deep Reinforcement Learning Gino Brunner, Oliver Richter, Yuyi Wang, Roger Wattenhofer ETH Zurich

Our map Our view Deepmind randomly generated, starting on small maps

Reinforcement Learning Environment Reward State Action Finding the target Bumping into walls Compass Agent

What does it mean to read a map? Localize

What does it mean to read a map? Localize Find a path to the target Follow the path I think I’m here

t + 1 Visual Input I think I’m here Estimated Position Map Input Compass Visible Local Map Network Recurrent Localization Cell Estimated Position I think I’m here Map Input Policy π Location Uncertainty Acting Agent Map Interpretation Network Short Term Target Direction

Modular design as key to success Visible Local Map Network Map Interpretation Network Acting Agent Recurrent Localization Cell Estimated Position Reward Prediction Policy π Actual Position Actual Reward Reinforcement Learning Neural nets, heuristics, explicit algorithms

Results

Questions? Oliver Richter richtero@ethz.ch

We and robots navigate with maps and gps Or SLAM >no sensors but map> human

Visible Local Map Network FC Orientation Visual Input Visible Local Map FC Visible Field Map Excerpt CNN FC