DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March 2001 1 Adaptive Intelligent Mobile Robotics Leslie Pack Kaelbling Artificial Intelligence.

Slides:



Advertisements
Similar presentations
Mobile Robot ApplicationsMobile Robot Applications Textbook: –T. Bräunl Embedded Robotics, Springer 2003 Recommended Reading: 1. J. Jones, A. Flynn: Mobile.
Advertisements

Reactive and Potential Field Planners
Lecture 7: Potential Fields and Model Predictive Control
Hierarchical Reinforcement Learning Amir massoud Farahmand
DARPA Mobile Autonomous Robot SoftwareMay Adaptive Intelligent Mobile Robotics William D. Smart, Presenter Leslie Pack Kaelbling, PI Artificial.
Effective Reinforcement Learning for Mobile Robots Smart, D.L and Kaelbing, L.P.
The Vector Field Histogram Erick Tryzelaar November 14, 2001 Robotic Motion Planning A Method Developed by J. Borenstein and Y. Koren.
A Survey of Artificial Intelligence Applications in Water-based Autonomous Vehicles Daniel D. Smith CSC 7444 December 8, 2008.
LCSLCS 18 September 2002DARPA MARS PI Meeting Intelligent Adaptive Mobile Robots Georgios Theocharous MIT AI Laboratory with Terran Lane and Leslie Pack.
DESIGN OF A GENERIC PATH PATH PLANNING SYSTEM AILAB Path Planning Workgroup.
John S Gero Agents – Agent Simulations AGENT-BASED SIMULATIONS.
A new approach for modeling and rendering existing architectural scenes from a sparse set of still photographs Combines both geometry-based and image.
AI Lab Weekly Seminar By: Buluç Çelik.
Motor Schema Based Navigation for a Mobile Robot: An Approach to Programming by Behavior Ronald C. Arkin Reviewed By: Chris Miles.
Study on Mobile Robot Navigation Techniques Presenter: 林易增 2008/8/26.
High Speed Obstacle Avoidance using Monocular Vision and Reinforcement Learning Jeff Michels Ashutosh Saxena Andrew Y. Ng Stanford University ICML 2005.
Planetary Surface Robotics ENAE 788U, Spring 2005 U N I V E R S I T Y O F MARYLAND Lecture 8 Mapping 5 April, 2005.
Behavior- Based Approaches Behavior- Based Approaches.
Panos Trahanias: Autonomous Robot Navigation PATH PLANNING.
Exploration in Reinforcement Learning Jeremy Wyatt Intelligent Robotics Lab School of Computer Science University of Birmingham, UK
Sonar-Based Real-World Mapping and Navigation by ALBERTO ELFES Presenter Uday Rajanna.
8/9/20151 DARPA-MARS Kickoff Adaptive Intelligent Mobile Robots Leslie Pack Kaelbling Artificial Intelligence Laboratory MIT.
1 DARPA TMR Program Collaborative Mobile Robots for High-Risk Urban Missions Second Quarterly IPR Meeting January 13, 1999 P. I.s: Leonidas J. Guibas and.
Abstract Design Considerations and Future Plans In this project we focus on integrating sensors into a small electrical vehicle to enable it to navigate.
Vision-based Navigation and Reinforcement Learning Path Finding for Social Robots Xavier Pérez *, Cecilio Angulo *, Sergio Escalera + and Diego Pardo *
Behavior Based Robotics: A Wall Following Behavior Arun Mahendra - Dept. of Math, Physics & Engineering, Tarleton State University Mentor: Dr. Mircea Agapie.
On-line Novelty Detection With Application to Mobile Robotics Stephen Marsland Imaging Science and Biomedical Engineering University of Manchester.
SPIE'01CIRL-JHU1 Dynamic Composition of Tracking Primitives for Interactive Vision-Guided Navigation D. Burschka and G. Hager Computational Interaction.
Mean Shift Theory and Applications Reporter: Zhongping Ji.
Robot Crowd Navigation using Predictive Position Fields in the Potential Function Framework Ninad Pradhan, Timothy Burg, and Stan Birchfield Electrical.
Biologically-inspired Visual Landmark Navigation for Mobile Robots
Flow Fields Hao Li and Howard Hamilton. Motivation for Flow Fields Multiple AI algorithms in a computer game can produce conflicting results. The AI must.
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
Global Parametrization of Range Image Sets Nico Pietroni, Marco Tarini, Olga Sorkine, Denis Zorin.
Mobile Robot Navigation Using Fuzzy logic Controller
Weak AI: Can Machines Act Intelligently? Some things they can do: –Computer vision: face recognition from a large set –Robotics: autonomous (mostly) car.
Spatio-Temporal Case-Based Reasoning for Behavioral Selection Maxim Likhachev and Ronald Arkin Mobile Robot Laboratory Georgia Tech.
1 Distributed and Optimal Motion Planning for Multiple Mobile Robots Yi Guo and Lynne Parker Center for Engineering Science Advanced Research Computer.
Motion Analysis using Optical flow CIS750 Presentation Student: Wan Wang Prof: Longin Jan Latecki Spring 2003 CIS Dept of Temple.
1 Research Question  Can a vision-based mobile robot  with limited computation and memory,  and rapidly varying camera positions,  operate autonomously.
Topological Path Planning JBNU, Division of Computer Science and Engineering Parallel Computing Lab Jonghwi Kim Introduction to AI Robots Chapter 9.
Raquel A. Romano 1 Scientific Computing Seminar May 12, 2004 Projective Geometry for Computer Vision Projective Geometry for Computer Vision Raquel A.
Learning to Navigate Through Crowded Environments Peter Henry 1, Christian Vollmer 2, Brian Ferris 1, Dieter Fox 1 Tuesday, May 4, University of.
CUHK Learning-Based Power Management for Multi-Core Processors YE Rong Nov 15, 2011.
UNC Chapel Hill M. C. Lin Introduction to Motion Planning Applications Overview of the Problem Basics – Planning for Point Robot –Visibility Graphs –Roadmap.
Representing hierarchical POMDPs as DBNs for multi-scale robot localization G. Thocharous, K. Murphy, L. Kaelbling Presented by: Hannaneh Hajishirzi.
Computer Science Readings: Reinforcement Learning Presentation by: Arif OZGELEN.
Behavior-based Multirobot Architectures. Why Behavior Based Control for Multi-Robot Teams? Multi-Robot control naturally grew out of single robot control.
DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; January Adaptive Intelligent Mobile Robotics Leslie Pack Kaelbling Artificial Intelligence.
Computer Animation Rick Parent Computer Animation Algorithms and Techniques Behavioral Animation: Crowds.
Selection of Behavioral Parameters: Integration of Case-Based Reasoning with Learning Momentum Brian Lee, Maxim Likhachev, and Ronald C. Arkin Mobile Robot.
Learning Momentum: Integration and Experimentation Brian Lee and Ronald C. Arkin Mobile Robot Laboratory Georgia Tech Atlanta, GA.
Crowd Self-Organization, Streaming and Short Path Smoothing 學號: 姓名:邱欣怡 日期: 2007/1/2 Stylianou Soteris & Chrysanthou Yiorgos.
Ghislain Fouodji Tasse Supervisor: Dr. Karen Bradshaw Computer Science Department Rhodes University 24 March 2009.
Autonomous Robots Robot Path Planning (3) © Manfred Huber 2008.
1 ECE 517: Reinforcement Learning in Artificial Intelligence Lecture 21: Dynamic Multi-Criteria RL problems Dr. Itamar Arel College of Engineering Department.
Artificial Intelligence in Game Design Lecture 8: Complex Steering Behaviors and Combining Behaviors.
Learning for Physically Diverse Robot Teams Robot Teams - Chapter 7 CS8803 Autonomous Multi-Robot Systems 10/3/02.
MIT Artificial Intelligence Laboratory — Research Directions Intelligent Agents that Learn Leslie Pack Kaelbling.
Representing Moving Images with Layers J. Y. Wang and E. H. Adelson MIT Media Lab.
Learning minimal representations for visual navigation Dr. William H. Warren Dept. of Cognitive & Linguistic Sciences Dr. Leslie Kaelbling Dept. of Computer.
Crowds (and research in computer animation and games)
Vision-Guided Humanoid Footstep Planning for Dynamic Environments
Crowd Modelling & Simulation
COGNITIVE APPROACH TO ROBOT SPATIAL MAPPING
Schedule for next 2 weeks
Crowds (and research in computer animation and games)
Representing Moving Images with Layers
Hierarchical POMDP Solutions
Behavior Based Systems
Presentation transcript:

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Adaptive Intelligent Mobile Robotics Leslie Pack Kaelbling Artificial Intelligence Laboratory MIT

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Pyramid Addressing problem at multiple levels Planning Built-in Behaviors Learning

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Built-in Behaviors Goal: general-purpose, robust visually guided local navigation optical flow for depth information finding the floor optical flow information Horswill’s ground-plane method build local occupancy grids navigate given the grid reactive methods dynamic programming

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Reactive Obstacle Avoidance Standard method in mobile robotics is to use potential fields attractive force toward goal repulsive forces away from obstacles robot moves in direction given by resultant force New method for non-holonomic robots: move the center of the robot so that the front point is holonomic

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Human Obstacle Avoidance Control law based on visual angle and distance to goal and obstacles Parameters set based on experiments with humans in large free-walking VR environment

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Humans are Smooth!

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Behavior Learning Typical RL methods require far too much data to be practical in an online setting. Address the problem with strong generalization techniques locally weighted regression “skeptical” Q-Learning bootstrapping from human-supplied policy need not be optimal and might be very wrong shows learner “interesting” parts of the space “bad” initial policies might be more effective

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Two Learning Phases Learning System Supplied Control Policy Environment Phase One ARO

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Two Learning Phases Learning System Supplied Control Policy Environment ARO Phase Two

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March New Results Drive to goal, avoiding obstacles in visual field Inputs (6 dimensions): heading and distance to goal image coordinates of two obstacles Output: steering angle Reward: +10 for getting to goal; -5 for running over obstacle Training: simple policy that avoids one obstacle

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Robot’s View

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Local Navigation

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Map Learning Robot learns high-level structure of environment topological maps appropriate for large-scale structure low-level behaviors induce topology based on previous work using sonar vision changes problem dramatically no more problems with many states looking the same now same state always looks different!

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Sonar-Based Map Learning DataTrue Model

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Current Issues in Map Learning segmenting space into “rooms” detecting doors and corridor openings representation of places stored images gross 3D structure features for image and structure matching

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Large Simulation Domain Use for learning and large-scale experimentation that is impractical on a real robot built using video-game engine large multi-story building packages to deliver battery power management other agents (to survey) dynamically appearing items to collect general Bayes-net specification so it can be used widely as a test bed

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Hierarchical MDP Planning Large simulated domain has unspeakably many primitive states Use hierarchical representation for planning logarithmic improvement in planning times some loss of optimality of plans Existing work on planning and learning given a hierarchy temporal abstraction: macro actions spatial abstraction: aggregated states Where does the hierarchy come from? combined spatial and temporal abstraction top-down splitting approach

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Region-Based Hierarchies Divide state space into regions each region is a single abstract state at next level polices for moving through regions are abstract actions at next level

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Choosing Macros Given a choice of a region, what is a good set of macro actions for traversing it? existing approaches guarantee optimality with a number of macros exponential in the number of exit states our method is approximate, but works well when here are no large rewards inside the region

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Point-Source Rewards Compute a value function for each possible exit state, offline Given a new valuation of all exit states online Quickly combine value functions to determine near-optimal action

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Approximation is Good

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March How to Use the Hierarchy Off line: Decompose environment into abstract states Compute macro operators On line: Given new goal, assign values to exits at highest level Propagate values at each level In current low-level region, choose action

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March What Makes a Decomposition Good? Trade off decrease in off-line planning time decrease in on-line planning time decrease in value of actions We can articulate this criterion formally but… … we can’t solve it Current research on reasonable approximations

DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Next Steps Low-level apply JAQL to tune obstacle avoidance behaviors Map learning landmark selection and representation visual detection of openings Hierarchy algorithm for constructing decomposition test hierarchical planning on huge simulated domain